Daily edition
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
Welcome to the August 2026 edition of the Linux Foundation Newsletter The Linux Foundation is celebrating 35 years of Linux, and training is discounted through August 18. Use code TUX35 for 35% off certifications,…
Today we're announcing the general availability of Oracle Exadata Database Service on Exascale Infrastructure (ExaDB-XS) for Oracle Database@AWS. ExaDB-XS brings Exadata-class performance and availability through a…
A surge of openness in AI has defined 2026. Amid calls for both caution and support, prevailing trends point to a future in which models are built and released openly. Recent research offers new insight into the…
Learn how to write your first prompt in the GitHub Copilot app, choose the right context and model, and start your first task with confidence. The post Write your first prompt with the GitHub Copilot app appeared first…
2.52.1 2026-08-12 AWS Glue Features Documentation updates for materialized views APIs. AWS Identity and Access Management Features Introduced role manager, an IAM capability that automatically sets up the IAM roles your…
3.1109.0(2026-08-12) Documentation Changes client-glue: Documentation updates for materialized views APIs. (dae03968) New Features client-quicksight: Added APIs for DLP with Microsoft Purview (manage configs with label…
Tagging 2.36.22 release.
AI contributors are already in your queue. AutoGPT maintainer Nicholas Tindle shares the repo instructions, gates, and boundaries that keep maintainers in control. The post Your contributors are AI-first now. Is your…
Amazon Elastic Kubernetes Service (Amazon EKS) now supports configuring parameters for Kubernetes control plane components including the scheduler, controller manager, and API server. You can tune pod placement…
The DSF Board hosts open office hours every Wednesday at 6:00 PM UTC (check your local time). Anyone in the Django community is welcome to drop in. You do not need an agenda or an invitation. Video call details are on…
Amazon Connect Customer now lets agents view and self-assign queued agent-first callbacks alongside emails, tasks, and chats. This gives agents the option to prioritize work that needs immediate follow-up or for which…
AWS Outposts brings AWS infrastructure into your data center with low latency and data locality. But an Outposts rack has fixed compute. Learn how to build a Burst to Region pattern that overflows workloads to Amazon…
Supercharge your GKE stateful apps with Google Cloud NetApp Volumes. Learn more and start your trial today: https://goo.gle/4wqhXdh Ready to level up your stateful applications on GKE? Unlock enterprise-grade…
[RELEASE] - Bump version to 3.38.2
*Featured in this video:* Maureen Makes, VP of Engineering at Recursion *Executive summary:* Recursion, a leading biotech company, partnered with Google Cloud to develop the Recursion OS, a drug discovery and…
The compiler can automatically generate operator!= in C++20 #176662 Pull Request resolved: #184795 Approved by: https://github.com/cyyever, https://github.com/eqy
Standard upgrade paths break active Debezium CDC replication slots on Amazon Aurora PostgreSQL, forcing hours-long re-snapshots. This post shows how to use native PostgreSQL logical replication to bridge a source and…
Strict pyrefly checking: type torch/_numpy (small + medium files) (#1…
Major changes #55629 - [3.x] Add post-quantum cryptography (PQC) support to TLS registry Complete changelog #47598 - Quarkus REST issue with UriInfo and matrix parameters #48889 - Introduce another Qute escape…
https://github.com/patroni/patroni/blob/master/docs/releases.rst#version-415
Previous check unwittingly included SM 11.0 authored with codex Pull Request resolved: #192386 Approved by: https://github.com/Skylion007, https://github.com/drisspg
https://github.com/patroni/patroni/blob/REL_4_0/docs/releases.rst#version-4011
Kevin Dugan, VP of Analytics and Marketing Intelligence, DMi Partners Executive summary: DMi Partners, a digital marketing agency, wanted to offer its premium affiliate marketing strategies to a wider range of brands,…
Python 3.12.14
Motivation As title Pull Request resolved: #191165 Approved by: https://github.com/EikanWang ghstack dependencies: #188888
We’re thrilled to announce Arduino App Lab 0.10, our biggest release yet. With this update, you can now build applications alongside an AI agent that actively works on your project, not one that just answers questions…
Add FlyDSL as a native op backend in torch/_native, following the existing CuTeDSL/Triton/Helion integration pattern. This introduces the runtime availability gate, a JIT compile cache, and an instrumentation entry…
[Testcase Refactoring] Enable PrivateUse1 tests and add hw-classifica…
*Featured in this video:* Johannes Rath, COO of Signal Iduna *Executive summary:* SIGNAL IDUNA, one of Germany’s leading insurance providers, partnered with Google Cloud to deploy the Gemini Enterprise app across its…
Human Note FA4 has different constraints than FA2. This one speicfically is for enabling DSv3 style mla training. Follows the same pattern for communciating FA3 is being used; set in context and update sdp utils to use…
[profiler][cupti] Give logical lanes their own reserved id range (#19…
AI data centers in space sound great, but practically speaking, they may be next to impossible. For tech bros, it The post Why space is actually a terrible place to cool a data center appeared first on The New Stack.
The Mission Robotic Vehicle is making the first attempt to attach a new thruster to an aging satellite.
Bu serinin yazarı Güray: AI geliştirmecisi, prompt ve analiz mühendisi. Kodun büyük kısmını bir LLM ajanıyla pair programming yaparak yazıyorum. Seri, kafa1milyon.com'un perde arkasını mühendis gözüyle belgeliyor. Bölüm…
CNCF feels different because people collaborate instead of compete. Arsh Sharma, CNCF Ambassador, shared why at KubeCon + CloudNativeCon Japan. #KubeCon #CloudNative
"How many days until the deadline?" sounds trivial until you actually write the code and get bitten by time zones, daylight saving time, and off-by-one errors. Here's a clear, correct way to do it. The naive version…
OpenAI research reveals how enterprises are adopting agentic AI, using ChatGPT and Codex, and how frontier firms are pulling ahead in AI adoption.
Buy Verified Binance Accounts 💠🌀⚜️🔱 Telegram: @progmbofficial 💠🌀⚜️🔱 WhatsApp: +1 (920) 212-9737 💠🌀⚜️🔱 Telegram: @progmbofficial 💠🌀⚜️🔱 Email: progmb.contact@gmail.com Buy Verified Binance Accounts. Get fully verified…
What is a Telegram account? 💠🌀⚜️🔱 Telegram: @progmbofficial 💠🌀⚜️🔱 WhatsApp: +1 (920) 212-9737 💠🌀⚜️🔱 Telegram: @progmbofficial 💠🌀⚜️🔱 Email: progmb.contact@gmail.com Telegram account is a user profile created on the…
"If this was opt-in, nobody would opt in," Twitch CPO Mike Minton said on a livestream responding to user feedback. "That's honestly the answer."
# TypeScript 7 Goes Native: What Breaks on Upgrade TypeScript 7 (the release everyone's been calling Project Corsa) is not a normal version bump. The compiler and language service got rewritten from JavaScript into Go,…
Most lead-capture advice assumes a contact form sits at the center of the funnel. For a lot of local service businesses in Latin America, that assumption is wrong. The form is not where the leads happen. WhatsApp is. I…
In the rapidly evolving digital economy, payment processing platforms like Stripe have become essential infrastructure for businesses of all sizes. From e-commerce stores and subscription services to freelancers and…
SpaceXAI released Grok 4.6 on Wednesday, less than a month after Grok 4.5. The company says Grok 4.6 can research The post SpaceXAI trained Grok 4.6 on something most AI labs throw away appeared first on The New Stack.
◈═━👑━═◈➜Fast Reply 24/7 | Instant Support 🚀 ◈═━👑━═◈➜Telegram: @progmbofficial ◈═━👑━═◈➜WhatsApp: +1 (920) 212-9737 ◈═━👑━═◈➜Telegram Channel: @progmbofficial ◈═━👑━═◈➜Email: progmb.contact@gmail.com ◈═━👑━═◈➜Visit Our…
Buy Verified Airbnb Accounts – Safe, Fast, and Affordable 💠🌀⚜️🔱 Telegram: @progmbofficial 💠🌀⚜️🔱 WhatsApp: +1 (920) 212-9737 💠🌀⚜️🔱 Telegram: @progmbofficial 💠🌀⚜️🔱 Email: progmb.contact@gmail.com Buy Verified Airbnb…
[Testcase Refactoring] Add hw_classification to generic dynamo test f…
I had a text-compare tool that asked people to compare two things it would not show them at the same time. One textarea, then another textarea underneath it, then a single-column unified diff below that — removals in…
Every local service business site (roofing, plumbing, HVAC, contracting) lives or dies by its quote-request form. Get the engineering wrong and you either drown the sales team in bot spam or lose real leads to friction.…
One of the great things of Linux as an ecosystem is that there is so much choice. Yet this is also its greatest weakness, as unlike on MacOS and Windows …read more
How to Build a Chrome Extension That Makes Money tags: javascript, chrome, extension, money tags: javascript, chrome, extension, money tags: javascript, chrome, extension, money tags: javascript, chrome, extension,…
feat: Bump admin-api to 0.114.0 (#2342) admin-api 0.114.0 contains optimized orioledb config feature according to the worksheet https://linear.app/supabase/issue/ORI-119/orioledb-variable-guc-settings-depending-on-ec2-si…
This PR is auto-generated nightly by this action. Update the pinned torchcomms hash. Pull Request resolved: #193062 Approved by: https://github.com/pytorchbot
Synesthesia now! robots are taking all the fun jobs! A team spread across multiple universities developed the new type of sensor. A robotic fingertip with synthetic skin that detects mechanical deformations by reading…
The Raspberry Pi Official Magazine – Issue 168 features the Adafruit CYBERDECK HAT for Raspberry Pi 400 & 500. Cut the build and connect a screen to Raspberry Pi’s all-in-one computer with Adafruit’s Cyberdeck HAT for…
Checks are being mailed from Grubhub's $23.8 million fine from the FTC after it settled allegations over its business practices.
Storage code has to cope with hardware that fails in inconvenient ways, but coaxing a healthy disk into producing those failures on demand, for testing, is usually not possible. The kernel provides several ways to…
The Raspberry Pi Official Magazine – Issue 168 shows the Alien Typeframe PS-85 cyberdeck by Jeff Merrick: Starting with a set of Semiotic Symbols keycaps based on Ron Cobb’s futuristic symbols in Alien, cosplayer Jeff…
Now that MCUs like the ESP32-S3 are quite capable computer systems including USB host functionality, it only makes sense that you can connect USB peripherals like Logitech racing wheels to …read more
SIG Node Meeting for 2026-08-12
Cognition may be looking to raise another mega round just a few months after raising $1 billion at a $26 billion valuation.
The Raspberry Pi Official Magazine – Issue 168: Cyberdeck Projects In this issue: We love customising our computer setups – and anything else – so we’re thrilled to find that the cyberdeck has well and truly taken off.…
At Ai4, three of the world's most respected AI experts — Geoffrey Hinton, Fei-Fei Li, and Andrew Ng — debated regulation, open source access, and how America can compete as China advances in Asia.
Thrive Holdings has raised $2 billion in new funding at a $12 billion valuation from investors like SoftBank, D1 Capital Partners, and Altimeter Capital.
If you missed this week’s livestream of John Park’s Product Pick(s) of the Week, not to worry, here’s the video. This week’s pick is the Adafruit FT232H Breakout – General Purpose USB to GPIO, SPI, I2C – USB C & Stemma…
An extortion gang known for targeting transportation companies and private equity firms has taken credit for a breach at Uber Freight.
JCB has invested heavily in hydrogen to power its diggers and other machinery.
A few weeks ago, we put out the call for participation for this year’s 2026 Hackaday Supercon, taking place in Pasadena, CA this November. Today was going to be the …read more
Originally designed to make software predictable for humans, Google Go is now positioning itself as a language tailored for machine The post Code that passes every test can still break the next AI agent that touches it…
Mesh, an AI-powered contacts app and relationship manager from Automattic, is now an Android app.
Business and technology leaders need no convincing that the time of agentic AI is here. Organizations are rapidly adopting agents, and few executives doubt the technology’s potential to transform work. But many…
During AI DevCon in London this summer, Lamis Mukta, member of technical staff at Anthropic, hosted a stage presentation session The post Anthropic gave agents the ability to dream. Then developers woke up. appeared…
Kubernetes SIG Release for 2026-08-12T15:57:44Z.mp4
AI notetaking hardware has taken off over the past couple of years, with credit-card-sized devices, pendants, pins, and even transcribing earbuds all promising to capture your meetings and turn them into summaries and…
Merge pull request #22225 from A4-Tacks/arith-op-fixup fix: check original type for replace_arith_op
Trump admin claims New York suing Kalshi created "market emergency."
What's Changed ci/nix-install-ephemeral: Drop sticky disk config by @mmlb in #2346 ci: Fix nix-build PUSH_TO_CACHE by @mmlb in #2345 Lots of bootstrap script clean ups by @mmlb in #2326 ci: Delete nix-eval workflow by…
Walmart co-locates red and blue teams to build trust and improve security through collaborative purple teaming exercises
feat: Bump admin-api to 0.114.0 (#2342) admin-api 0.114.0 contains optimized orioledb config feature according to the worksheet https://linear.app/supabase/issue/ORI-119/orioledb-variable-guc-settings-depending-on-ec2-si…
pokeemerald-rp2350 is Pokémon Emerald running natively on a $6 microcontroller — the full game, running at 60 fps, with HDMI video out, real buttons, and saves that survive a power cycle. No emulator: the pret…
Tesla wants to build a massive solar factory in Texas, but first it wants the state to chip in to defray the costs.
Form Energy has landed Google and Crusoe as customers. Now, it has raised $750 million to expand manufacturing to deliver its massive, 100-hour batteries.
feat: Bump admin-api to 0.114.0 (#2342) admin-api 0.114.0 contains optimized orioledb config feature according to the worksheet https://linear.app/supabase/issue/ORI-119/orioledb-variable-guc-settings-depending-on-ec2-si…
This new funding comes after Lovable hit $500 million in annualized run rate revenue in June, the startup told TechCrunch.
Dasha is an open source performance dashboard for PostgreSQL fleets. It connects to your clusters with a read-only role, shows what the databases are doing right now, and explains what to do about it. Nothing is…
Dear Community Members, We are excited to announce the release of SynchDB 1.4, a PostgreSQL extension for real-time replication from heterogeneous source databases into PostgreSQL/IvorySQL. This release extends Oracle…
Sehrope Sarkini along with Claude has written a new JDBC driver from scratch. It's currently in pre-release. Here's an excerpt from his blog PostgreSQL-first. The native API is designed around PostgreSQL's wire protocol…
What plx is plx is a PostgreSQL extension that lets you write stored functions and triggers in the dialect you already know (the current set is listed below). When you run CREATE FUNCTION, plx transpiles the body to…
Learn how a Java MCP server can embrace the latest MCP specification without breaking existing integrations or forcing immediate client upgrades.
Anish Singhani and Benjamin Devlin have designed a puzzle, a chip, but they’re only providing the layout. We’ve designed an ASIC, and we’re giving you its final mask: all of its metal, routing, and active transistor…
feat: Bump admin-api to 0.114.0 (#2342) admin-api 0.114.0 contains optimized orioledb config feature according to the worksheet https://linear.app/supabase/issue/ORI-119/orioledb-variable-guc-settings-depending-on-ec2-si…
The new app launches with Facebook's AI creator assistant built into it, providing creators with personalized recommendations based on their content style, performance, audience engagement, and goals.
feat: Bump admin-api to 0.114.0 (#2342) admin-api 0.114.0 contains optimized orioledb config feature according to the worksheet https://linear.app/supabase/issue/ORI-119/orioledb-variable-guc-settings-depending-on-ec2-si…
feat: Bump admin-api to 0.114.0 (#2342) admin-api 0.114.0 contains optimized orioledb config feature according to the worksheet https://linear.app/supabase/issue/ORI-119/orioledb-variable-guc-settings-depending-on-ec2-si…
Daniel Balsom on Adventures in PC Emulation was playing around with a web application – an online disassembler for the x86 – when emoji were being encoded into the url. I pasted a goat emoji, 🐐 and I noticed the…
When your AI agent serves more than one person, every tool call must answer: who's the agent acting for? Let's learn how to solve this by building an AI agent that connects with Slack and GitHub. A Sl
Investors are still waiting for their share of the $250 million windfall, and VideoVerse co-founder Vinayak Shrivastav is now at the center of multiple legal cases.
PDF editing isn't limited to adding signatures or merging documents. Sometimes you simply want to improve the appearance of a PDF by increasing brightness, boosting contrast, adding blur, converting i
There are a number of small, inexpensive, low-powered e-reader or e-paper devices that have promise as ebook readers with one minor problem: the firmware they ship with does not realize their full potential. To solve…
In a few hours, there is a solar eclipse that will be visible with a track that goes from Spain up through Greenland. Too late to travel for it, but …read more
Version 11.1 of the QEMU emulator has been released. The release contains more than 3,200 commits from 285 authors and includes a long list of improvements; see the announcement and changelog for the details.
AI firms quietly bulk buying rare books face resistance from booksellers.
This is the latest zero-day released by security researcher Nightmare Eclipse, despite Microsoft publicly threatening to take legal action against them.
Social engineering and malware combine to enable financial fraud before banks have time to act
The Road to Battlefield competition is now in its second year, and its purpose is to give founders across Central Eurasia a direct route to Startup Battlefield
SPONSORED POST: Sovereign AI is becoming a strategic infrastructure priority, explain HPE's Thierry Pienaar and NVIDIA's Kaushik Shirhatti
Helix claims nearly a million files, while the logistics biz says operations never hit the brakes
The Python for Microcontrollers Newsletter is the place for the latest news involving Python on hardware (microcontrollers AND single board computers like Raspberry Pi). This ad-free, spam-free weekly email is filled…
Don't miss out! Join us at our next KubeCon + CloudNativeCon events in Shanghai, China (8-9 September, 2026) and Salt Lake City, United States (Nov 9–12, 2026). Connect with our current graduated, incubating, and…
From the Pixel 11 series and a brand new competitor to Apple’s AirTag, here are all the announcements from the Made by Google 2026 event.
Google's Quick Share feature is getting a tap-to-share mode for quickly exchanging contacts, photos, videos, and more.
Google focuses more on AI and curated experiences than spec upgrades in 2026.
When we last left off, I had just set up a new SLA resin printer and was on the verge of doing the initial round of printing to see just …read more
Huy Vector and HVT Lab made the cutest little robot friend! This AI-powered WALL-E inspired robot build “can see through its camera, chat naturally, recognize objects, and respond to voice commands.” Adafruit Crickit…
The new smartwatch, which starts at $399, can track blood pressure patterns and insulin resistance, as well as deliver personalized help and better sleep tracking.
The Google Pixel 11 series starts $100 costlier than the last year, but offers 256GB base storage.
Learn how to integrate OpenTelemetry with a FastAPI app in Python to instrument endpoints, export traces, add custom spans, and correlate logs.
Attackers continue to target critical infrastructure and government-linked organizations in the country, mirroring the increased activity across Latin America.
The warning is correct. And the recommended fixes you've probably seen are wrong. Here's what you can do instead to properly fix the issue. Blocked aria-hidden: The Warning is Right, and Every Fix You’ve Found is Wrong…
Nobody patched the CMS or read the alerts, and ACRO still cannot tell whether info was exfiltrated
A public AI tool found the dangerous Zoom flaw in under 20 prompts.
The deal starts with the arrival of the GEN4 car and 2026-27 season this December.
Security updates have been issued by AlmaLinux (fence-agents, firefox, frr10, gstreamer1-plugins-good, iscsi-initiator-utils, isns-utils, kernel, kernel-rt, perl-DBI:1.641, postgresql, postgresql:12, and…
Gives a whole new meaning to Safe Mode
Meta released Muse Glimmer on Monday, a 30-billion-parameter open-weight model distilled from Muse Spark and licensed under Apache 2.0. The The post Meta stopped worrying about distillation and just shipped the pipeline…
The big-box giant has scaled its defenses by encouraging trust and innovation. Good communications, transparency, and team spirit are key factors.
In a recent study, evolution gets even messier than usual.
Even two-tenths of a watt matters when your spacecraft launched in 1977
Instrument a FastAPI app with OpenTelemetry to export traces, add custom spans, and correlate your application logs with traces.
Autonomous coding agents ignore contribution rules in open source communities, finds a new study from researchers at Peking University. That’s The post Coding agents ignore open source contribution guidelines,…
Victoria is the first stop as privacy campaigners warn the technology is becoming routine
In these days of hundred-gigabyte-and-more monster games, it can be nice to stop and remember what a human can do with assembly language and very, very little storage space. In …read more
Apollo Automation’s ESPHome Starter Kit is the first official ESPHome starter kit designed and engineered by Apollo Automation in partnership with the Open Home Foundation. It features the ESPHome C6 board with the…
AI gave hyperscalers first dibs on scarce kit, and business buyers may have little choice but to rent it back
What would be your tip for this stricken device?
Forlinx Embedded AM62L32 Local EVM is a low-power industrial SBC built around the Texas Instruments AM62L32 Arm Cortex-A53/M4 hybrid SoC. It is designed for industrial control, IoT gateways, edge computing, embedded…
There is no shortage of PostgreSQL operators for Kubernetes. Projects such as CloudNativePG, the Zalando postgres-operator, Crunchy PGO, and StackGres have all helped shape the ecosystem. So why did we build another…
SIG Contribex Meeting for 2026-08-12
Global players dominate the market. Will public sector buyers give local suppliers a look-in?
WG Checkpoint Restore Meeting for 2026-08-12
Although lighting 3D prints on fire is rarely the intended outcome, it’s possible that said print will at some point in its future come into contact with either an open …read more
SPONSORED FEATURE: Toolstation swapped aging Linux tills across branches for compact ASUS NUCs on ChromeOS Flex, cutting support tickets and freeing counter space
Kubernetes SIG Release for 2026-08-12T07:20:58Z.mp4
Let's all go a bit mad scientist and see if software can validate our wildest theories
Manus AI will delete some data to satisfy legal requirements
Jueves de Quack con Bruno
The Agent Baseline defines 35 controls across six security outcomes—but the right starting point depends on how your organization uses agents. Learn how to sequence controls for coding, internal, and production agents.
arXiv:2606.15821v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have produced many specialized multimodal LLMs (MLLMs) that share common foundational LLMs, forming distinct…
arXiv:2608.10010v1 Announce Type: new Abstract: Low-precision datatypes reduce language-model cost, but most formats optimize scalar fidelity while leaving the arithmetic induced by their products unchanged. We…
arXiv:2608.11173v1 Announce Type: cross Abstract: The attention mechanism forms the foundation of many modern AI models such as the Transformer. In one subclass of problems where attention is used, inputs and outputs…
arXiv:2608.10798v1 Announce Type: cross Abstract: Most image colorization systems operate in $Lab$ space by predicting chroma ($ab$) while preserving an input-derived luminance channel ($L$). While effective on standard…
arXiv:2608.10406v1 Announce Type: cross Abstract: Web search, product search, and question-answering retrieval systems often assign a relevance label and confidence score to each query-candidate pair. The relevance…
arXiv:2601.18128v2 Announce Type: replace-cross Abstract: High-dimensional data often exhibit variation that can be captured by lower-dimensional factors. For high-dimensional data from multiple studies, one goal is to…
arXiv:2604.22005v2 Announce Type: replace-cross Abstract: Accurate yet low-latency channel state information (CSI) acquisition is essential for multiple-input multiple-output (MIMO) communication systems. While advanced…
arXiv:2606.21806v2 Announce Type: replace Abstract: Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains. A common source is an…
arXiv:2608.10526v1 Announce Type: new Abstract: Motivated by decentralized applications, we study cooperative multi-agent bandits in continuous (Lipschitz) action spaces when the Lipschitz constant is unknown. We…
arXiv:2608.11027v1 Announce Type: new Abstract: Benchmark leaderboards summarize how well a language model performs, but not how its behavior relates to that of other models or changes across generations. We…
arXiv:2602.24188v2 Announce Type: replace-cross Abstract: We present a scalable and verifiable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require…
arXiv:2604.26508v2 Announce Type: replace Abstract: Deploying Vision-Language Models (VLMs) on edge devices remains challenging due to their substantial computational and memory demands, which exceed the capabilities of…
arXiv:2607.00642v2 Announce Type: replace-cross Abstract: Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to…
arXiv:2607.24850v2 Announce Type: replace-cross Abstract: Recent advances in large language models (LLMs) have enabled search agents to autonomously tackle complex tasks across extended search and reasoning horizons.…
arXiv:2602.23035v2 Announce Type: replace Abstract: Cardiac blood flow patterns contain rich information about disease severity and clinical interventions, yet current imaging and computational methods fail to capture…
arXiv:2509.06191v2 Announce Type: replace-cross Abstract: Recent 3D generative models, which are capable of generating full object shapes from just a few images, now open up new opportunities in robotics. In this work,…
arXiv:2608.11167v1 Announce Type: cross Abstract: Existing Multimodal Large Language Models (MLLMs) predominantly rely on image-text pairs for modality alignment pretraining, mapping global image representations to long…
arXiv:2608.11052v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) aims to recover a reward function under which the resulting policy reproduces the behavior observed in expert demonstrations. A…
arXiv:2608.10016v1 Announce Type: new Abstract: Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing modalities, model…
arXiv:2608.10850v1 Announce Type: new Abstract: We study continual pre-training (CPT) as a mechanism for adapting general-purpose large language models to specialized domains: mathematics, instruction, code, and natural…
arXiv:2602.09924v4 Announce Type: replace-cross Abstract: Running LLMs with extended reasoning on every problem is expensive, but determining which inputs actually require additional compute remains challenging. We…
arXiv:2608.10566v1 Announce Type: cross Abstract: How many directions does a neural representation use to encode a concept? A common answer repeatedly erases probe directions and reports the stopping count or cumulative…
arXiv:2608.10234v1 Announce Type: cross Abstract: Operator learning is a rapidly advancing area of computational science. It is particularly well suited to problems where a partial differential equation (PDE) must be…
arXiv:2511.18539v3 Announce Type: replace Abstract: We propose TimePre, a simple framework that unifies the efficiency of Multilayer Perceptron (MLP)-based models with the distributional flexibility of Multiple Choice…
arXiv:2608.10553v1 Announce Type: new Abstract: Conformal prediction (CP) provides distribution-free prediction intervals for fixed forecasters, but its standard calibration procedure is often inefficient for time…
arXiv:2608.09966v1 Announce Type: cross Abstract: European summer warming reflects interactions among background change, persistent ocean--land--circulation states, and same-season variability. We develop an empirical…
arXiv:2606.27199v2 Announce Type: replace-cross Abstract: Successful forecasting involves identifying patterns between historical and future states of the world which generalize to future observations. We apply LLMs to…
arXiv:2603.20861v2 Announce Type: replace-cross Abstract: The homology of an ample groupoid is computed from the complex of compactly supported continuous functions on the nerve. Two hypotheses routinely imposed on this…
arXiv:2601.22012v3 Announce Type: replace Abstract: Catastrophic forgetting in continual learning is often measured at the performance or last-layer representation level, overlooking the underlying mechanisms. We…
arXiv:2608.09617v2 Announce Type: replace Abstract: Symbolic regression is the problem of finding an algebraic expression describing a stochastic dependence of a target variable on a set of inputs. Unlike forms of…
arXiv:2606.12489v2 Announce Type: replace-cross Abstract: Molecular communication (MC) suffers from severe diffusion memory because molecules released for one symbol may arrive during later symbol intervals. Neural…
arXiv:2604.22627v2 Announce Type: replace-cross Abstract: Joint measurements on multiple copies of a quantum state provide access to nonlinear observables such as $\operatorname{tr}(\rho^t)$, but whether replica number…
arXiv:2608.10249v1 Announce Type: new Abstract: We present a scalable framework for unsupervised clustering of maritime trajectories derived from terabyte-scale Automatic Identification System (AIS) archives.…
arXiv:2606.11990v3 Announce Type: replace Abstract: Remaining Useful Life (RUL) prediction is essential for industrial predictive maintenance, yet many learning-based approaches rely on extensive feature engineering or…
arXiv:2608.10766v1 Announce Type: cross Abstract: Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision. We propose ''Rule of Thumb''…
arXiv:2608.10401v1 Announce Type: cross Abstract: Intracytoplasmic sperm injection (ICSI) operators frequently adjust the field-of-view (FOV) during procedures, which interrupts workflow and increases procedure time.…
arXiv:2608.09986v1 Announce Type: cross Abstract: Most existing multimodal sentiment analysis approaches assume access to complete multimodal inputs. However, real-world applications frequently encounter incomplete or…
arXiv:2608.10857v1 Announce Type: new Abstract: Determining the complexity, or Intrinsic Dimension (ID), of data is fundamental to efficient and interpretable representation learning. This is particularly challenging in…
arXiv:2608.10349v1 Announce Type: cross Abstract: Machine-learning intrusion-detection studies commonly emphasize predictive accuracy while treating explanation generation as a computationally free post-processing step.…
arXiv:2605.07284v2 Announce Type: replace Abstract: A late-layer change learned during post-training may work on the base model's earlier state, or it may depend on earlier computation learned with it. We distinguish…
arXiv:2608.11045v1 Announce Type: new Abstract: ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (RTN) schemes when…
arXiv:2608.05025v2 Announce Type: replace Abstract: Joint Energy-Based Models (JEM) unify classification and generation within a single network and support out-of-distribution (OOD) detection. Canonical JEM training…
arXiv:2608.11152v1 Announce Type: cross Abstract: Modern reinforcement learning (RL) post-training pipelines for large language models (LLMs) increasingly combine rollout workloads across multiple domains and feedback…
arXiv:2607.19378v3 Announce Type: replace Abstract: Subquadratic alternatives to attention require compromises when applied to multi-dimensional data: standard convolutions lack global receptive fields and input…
arXiv:2608.10120v1 Announce Type: new Abstract: Modern sequence models, from Transformers to State Space Models, have enabled powerful generative modeling across diverse domains, yet they are typically trained to…
arXiv:2603.18446v2 Announce Type: replace-cross Abstract: Long-context inference remains challenging for large language models due to attention dilution and out-of-distribution degradation. Context selection mitigates…
arXiv:2603.00408v4 Announce Type: replace Abstract: We present an Ising-compatible framework for formal neural-network robustness verification under bounded input perturbations. For piecewise-linear activations, the…
arXiv:2510.15770v4 Announce Type: replace-cross Abstract: Although deep neural networks achieve strong predictive performance, their internal reasoning often remains difficult to inspect and control. Concept Bottleneck…
arXiv:2608.10288v1 Announce Type: new Abstract: The Large Language Model from Power Law Decoder Representations (PLDR-LLM) and its attention, Power Law Graph Attention (PLGA), replace the fixed bilinear form of scaled…
arXiv:2608.10699v1 Announce Type: new Abstract: Text-Attributed Graphs (TAGs), endowed with abundant textual content along with topological structures, have emerged as a versatile backbone for real-world anomaly…
arXiv:2608.10464v1 Announce Type: cross Abstract: Incremental learning models are required to learn new classes sequentially without catastrophic forgetting, while operating under parameter and memory constraints. In…
arXiv:2608.10499v1 Announce Type: new Abstract: Personalized Federated Reinforcement Learning (PFRL) takes a decentralized approach to storing and accessing information based on past experiences while keeping each…
arXiv:2608.09992v1 Announce Type: cross Abstract: Controllable generation guided by external knowledge is a key requirement in modern generative deep learning applications, enabling the synthesis of samples with…
arXiv:2604.20209v2 Announce Type: replace Abstract: LLM self-play algorithms are notable in that, in principle, nothing bounds their learning: a Conjecturer model creates problems for a Solver, and both improve…
arXiv:2505.21460v2 Announce Type: replace Abstract: We study online calibration of multi-dimensional forecasts over an arbitrary convex set $P \subset \mathbb{R}^d$ relative to an arbitrary norm $|\cdot|$. We connect…
arXiv:2608.10402v1 Announce Type: new Abstract: Reinforcement learning (RL) for large language models is moving toward multi-turn agentic workloads, where rollout tasks repeatedly pause for external environments, resume…
arXiv:2608.10195v1 Announce Type: cross Abstract: Human vision organizes what it sees into wholes: same-colored points group into series, similar marks cohere into categories, and shapes complete into recognizable…
arXiv:2608.11200v1 Announce Type: cross Abstract: Synthetic dialogue generation offers a way to study conversational dynamics in sensitive domains where real data are difficult to access, release, or annotate. The…
arXiv:2608.09938v1 Announce Type: cross Abstract: Hyperelastic deformations are highly sensitive to domain geometry and boundary conditions, making generalization across both a critical capability for neural operators…
arXiv:2606.02198v2 Announce Type: replace Abstract: Prediction tasks over individual futures, which are inherently noisy, often admit multiple similarly accurate models. When these models produce different predictions…
arXiv:2608.10738v1 Announce Type: new Abstract: We study the approximation of dynamical systems by semi-autonomous neural ordinary differential equations (SA-NODEs) over long time horizons. For a single network trained…
arXiv:2608.10182v1 Announce Type: new Abstract: Large-scale targeting and recommendation systems are typically built around predictive scores fed into heuristic or local allocation. When the business goal is incremental…
arXiv:2605.16411v3 Announce Type: replace-cross Abstract: Hallucination remains a fundamental challenge in vision-language models (VLMs), where autoregressive generation may produce linguistically plausible yet…
arXiv:2608.10131v1 Announce Type: cross Abstract: Vision foundation models are increasingly used as reusable encoders in medical image computing, yet their high-dimensional spatial embeddings are difficult to inspect…
arXiv:2608.10332v1 Announce Type: cross Abstract: Differentiable predictive control (DPC), a self-supervised learning approach for approximating explicit model predictive control (MPC) policies, offers significant…
arXiv:2607.11796v2 Announce Type: replace Abstract: Selective state-space models such as Mamba route information through a bank of first-order modes whose input coupling is set by a learned selection mechanism. We give…
arXiv:2604.07822v2 Announce Type: replace-cross Abstract: We study implicit reasoning, i.e. the ability to combine knowledge or rules within a single forward pass. While transformer-based large language models store…
arXiv:2604.07557v2 Announce Type: replace Abstract: Small longitudinal cohorts, common in maternal health, rare diseases, and early-phase trials, limit computational modeling because enrollment is slow and the data are…
arXiv:2509.05663v4 Announce Type: replace Abstract: Truly unsupervised approaches for time series anomaly detection are rare in the literature. Those that exist suffer from a poorly set threshold, which hampers…
arXiv:2608.10537v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have helped uncover mechanistic explanations for LLM behaviours such as reasoning, jailbreaking etc., via understanding the corresponding…
arXiv:2511.19436v2 Announce Type: replace-cross Abstract: Existing Video Detailed Captioning (VDC) methods predominantly rely on costly human annotations or distillation from powerful proprietary models, creating a…
arXiv:2608.10011v1 Announce Type: cross Abstract: Continuous hemodynamic monitoring guides treatment decisions in surgery and intensive care. However, gold-standard signals are only measured in severe cases due to risks…
arXiv:2608.10045v1 Announce Type: new Abstract: The problem of learning from pairwise comparisons has been widely studied across many domains such as recommendation systems, social choice, and more recently, fine-tuning…
arXiv:2604.08941v2 Announce Type: replace Abstract: Medical Vision-Language Models (VLMs) answering binary presence questions on chest radiographs can fail in two linked ways: they are confidently wrong, and they change…
arXiv:2607.26998v3 Announce Type: replace-cross Abstract: Large language model (LLM) agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools.…
arXiv:2608.10333v1 Announce Type: new Abstract: LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as…
arXiv:2605.08731v3 Announce Type: replace-cross Abstract: A JPEG decoder benchmark can combine worker counts, CPUs, and datasets in one large result matrix. We simplify that comparison by fixing a PyTorch DataLoader at…
arXiv:2310.15976v4 Announce Type: replace Abstract: signSGD is attractive in nonconvex optimization because it communicates sign-valued rather than full-precision gradients. Several standard analyses assume independent…
arXiv:2510.04399v3 Announce Type: replace-cross Abstract: We develop a learning-theoretic framework for analyzing self-improving agents by decomposing self-modification into five axes. Within this framework, we prove a…
arXiv:2604.09921v2 Announce Type: replace Abstract: Much work has been done on designing fast and accurate sampling for diffusion language models (dLLMs). However, these efforts have largely focused on the tradeoff…
arXiv:2608.10480v1 Announce Type: cross Abstract: Large language models (LLMs) are widely applied across chemical tasks, such as molecular property prediction, which underpins drug discovery. Molecular LLMs represent a…
arXiv:2505.05168v4 Announce Type: replace-cross Abstract: Under mild conditions, a least-squares local linear Fr\'echet curve predictor is derived for a response and a regressor evaluated in a separable Hilbert space.…
arXiv:2608.10709v1 Announce Type: new Abstract: Quantization-Aware Training (QAT) enables the deployment of quantized models with minimal accuracy degradation. However, in practical scenarios, training labels are often…
arXiv:2603.02462v2 Announce Type: replace Abstract: A key challenge in developing unified neural solvers for combinatorial optimization (CO) is the efficient generalization of models from a given set of tasks to new…
arXiv:2608.09996v1 Announce Type: cross Abstract: Recent advances in machine learning have greatly improved breast cancer detection, enabling more accurate and timely diagnosis. Deep learning (DL) models show strong…
arXiv:2412.09486v2 Announce Type: replace-cross Abstract: The literature reflects a mutually beneficial relationship between machine learning and quantum computing, where progress in one field frequently drives…
arXiv:2608.10398v1 Announce Type: new Abstract: Variational autoencoders generate samples from probabilistic latent representations but do not distinguish uncertainty about the latent location from variability around…
arXiv:2109.13445v3 Announce Type: replace-cross Abstract: The capability of Deep Neural Networks (DNNs) to recognize objects in orientations outside the distribution of the training data is not well understood. We…
arXiv:2602.02035v2 Announce Type: replace-cross Abstract: Multi-agent reinforcement learning systems deployed in real-world robotics applications face severe communication constraints that significantly impact…
arXiv:2603.10485v3 Announce Type: replace-cross Abstract: In this work, we study the convergence properties of the Dual Space Preconditioned Gradient Descent, encompassing optimizers such as Normalized Gradient Descent…
arXiv:2608.10291v1 Announce Type: cross Abstract: Large-scale multi-modal MRI datasets impose substantial storage and I/O costs, limiting the training of 3D generative models on commodity infrastructure. While lossy…
arXiv:2608.10837v1 Announce Type: new Abstract: The strong performance of foundation models for tabular tasks comes at substantial inference costs. Distilling models into task-specific architectures reduces model size…
arXiv:2608.10144v1 Announce Type: new Abstract: We consider federated parameter efficient fine-tuning of large neural networks with low-rank adaptation (LoRA,~Hu et al.\ 2022). Combining LoRA with federated PEFT…
arXiv:2608.10022v1 Announce Type: cross Abstract: The large-scale oceanic and atmospheric forecasts provided by global climate models typically lack sufficient resolution to accurately capture the response of the…
arXiv:2608.02829v2 Announce Type: replace Abstract: Model families are typically trained size by size, each from scratch. Can apretrained large model instead be converted into a smaller sibling? Wecharacterize the…
arXiv:2608.10897v1 Announce Type: new Abstract: Instant delivery platforms have become a critical component of urban logistics, increasingly relying on crowdsourced couriers to fulfill highly dynamic orders. In…
arXiv:2608.10506v1 Announce Type: cross Abstract: Accurate pre-deployment estimation of CNN inference cost--energy, latency, and peak memory--is increasingly critical as models are deployed on resource-constrained GPU…
arXiv:2507.00945v3 Announce Type: replace Abstract: Short-term forecasting of aggregated human mobility flows supports urban planning, intelligent transportation systems, and emergency response, yet existing models…
arXiv:2608.08730v2 Announce Type: replace Abstract: Large Language Models are deployed to multiple types of environments, from internet browsers to edge devices, and WebGPU serves as a modern cross-platform standard.…
arXiv:2506.00818v2 Announce Type: replace-cross Abstract: Offline reinforcement learning for longitudinal studies often faces two linked challenges: rewards may be binary or bounded, and reward observations may be…
arXiv:2608.10172v1 Announce Type: new Abstract: Mechanistic interpretability explains models by identifying circuits inside them, but has no way to tell whether a circuit is a property of the model or an artifact of the…
arXiv:2608.10196v1 Announce Type: new Abstract: Program evolution can measure whether a mutation helped, but it rarely controls how far the mutation moves in behavior space. Syntactic edit size is an unreliable proxy: a…
arXiv:2510.12947v3 Announce Type: replace-cross Abstract: Voice activity detection (VAD) serves as an early gate in voice-assistant pipelines for smart devices. Because conventional VADs respond to speech from any…
arXiv:2608.10042v1 Announce Type: new Abstract: Tool-use LLMs are increasingly asked to act on users' behalf, but existing benchmarks usually focus on profile recall, style imitation, generic tool use, or response-level…
arXiv:2607.10410v2 Announce Type: replace-cross Abstract: Reliable forecasting of several interrelated environmental variables - such as regional precipitation and temperature, or other correlated geophysical fields -…
arXiv:2605.17173v2 Announce Type: replace-cross Abstract: Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several…
arXiv:2510.01015v3 Announce Type: cross Abstract: Wasserstein metrics are increasingly adopted as similarity scores for images. We consider the sensitivity of Wasserstein metrics with respect to pixel-wise additive…
arXiv:2608.06896v2 Announce Type: replace Abstract: Deep learning has achieved great success in recent years thanks to the availability of high-quality, well-annotated training data. However, this requirement is often…
arXiv:2606.07718v2 Announce Type: replace-cross Abstract: Agentic AI offers a promising path to automating software development bottlenecks in scientific research pipelines, particularly for stages that take domain…
arXiv:2608.10905v1 Announce Type: new Abstract: On-policy distillation (OPD) applies token-level teacher supervision to student-generated trajectories, but this supervision is not always reliable. Existing methods use…
arXiv:2608.10289v1 Announce Type: cross Abstract: Deep neural networks are increasingly deployed in safety-critical domains as perception modules, where failures are often caused due to rare and under-represented…
arXiv:2608.10039v1 Announce Type: new Abstract: Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control…
arXiv:2603.24226v4 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have inspired a surge of scaling research in industrial search, advertising, and recommendation systems. However,…
arXiv:2608.10845v1 Announce Type: cross Abstract: Spectral clustering methods for network data are commonly based on a few matrix representations, such as the adjacency matrix and the symmetric Laplacian. We study a…
arXiv:2608.10046v1 Announce Type: new Abstract: Soft skills shape collaboration among ML engineers, data scientists, and software engineers building ML-enabled systems, yet what we know about them comes almost entirely…
arXiv:2608.10605v1 Announce Type: new Abstract: In large-scale pretraining, the algorithm, architecture, and systems decisions are conventionally made in disconnected stages. A scaling law stage selects an architecture…
arXiv:2608.00144v2 Announce Type: replace Abstract: Membership inference (MIA) on language models is usually summarised by aggregate ROC-AUC, but such evaluations are confounded: model-free blind baselines can separate…
arXiv:2608.10149v1 Announce Type: new Abstract: Due to the diversity of real-world time series, no single forecasting model consistently dominates across all samples. Ensemble learning addresses this by combining…
arXiv:2604.11827v2 Announce Type: replace-cross Abstract: Machine learning is revolutionizing chemistry. Beyond the value of predictive models accelerating virtual screening, generative AI aims at enabling inverse…
arXiv:2605.28626v2 Announce Type: replace Abstract: Hybrid interpretable models combine a transparent component with a black-box model by assigning some examples to the former and deferring the rest to the latter. While…
arXiv:2607.15606v2 Announce Type: replace Abstract: Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing and data-driven research, but evaluating their fidelity remains difficult…
arXiv:2608.10628v1 Announce Type: cross Abstract: Long-document understanding often requires reasoning over many visually rich pages, making inference costly and prone to context rot. In this work, we propose…
arXiv:2608.08363v2 Announce Type: replace-cross Abstract: Silicon carbide (SiC) power modules are increasingly deployed in automotive traction inverters, where condition monitoring is essential to prevent in-service…
arXiv:2112.07752v5 Announce Type: replace-cross Abstract: Researchers have formalized reinforcement learning (RL) in different ways. If an agent in one RL framework is to run within another RL framework's environments,…
arXiv:2608.06578v1 Announce Type: cross Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines. Whether these differences produce measurably different behaviors under…
arXiv:2608.09972v1 Announce Type: cross Abstract: First-generation AI weather models are often reported to underperform at extremes, mostly in reanalysis-based evaluations of deterministic regression systems. We verify…
arXiv:2608.10277v1 Announce Type: cross Abstract: We present a stochastic coupled emulator of E3SM version 3, built on the SamudrACE framework, which couples an atmosphere emulator (ACE2) with a full-depth ocean…
arXiv:2606.10959v2 Announce Type: replace Abstract: Spacecraft navigation often requires Bayesian inference from sparse nonlinear measurements that produce curved, multimodal, or geometrically constrained posterior…
arXiv:2509.23413v3 Announce Type: replace Abstract: Multi-task neural routing solvers have emerged as a promising paradigm for their ability to solve multiple vehicle routing problems (VRPs) using a single model.…
arXiv:2606.29243v2 Announce Type: replace Abstract: We introduce KrishokChat, an 85,979-instance Bengali agricultural benchmark built from 284 government publications, 13 institutions, and six regional dialects. The…
arXiv:2606.07271v3 Announce Type: replace Abstract: Understanding memorization in generative models remains challenging, with implications for copyright and privacy. Beyond verbatim reproduction, models can encode…
arXiv:2608.11197v1 Announce Type: new Abstract: Shani et al. (2026) show that LLM representations broadly recover human category boundaries, while failing to reflect fine-grained typicality structure. Their analysis…
arXiv:2607.27651v2 Announce Type: replace Abstract: Learned rules select samples for follow-up measurements in high-throughput experiments. Predicted value does not justify replacing a fixed plan. We introduce the…
arXiv:2608.10544v1 Announce Type: cross Abstract: Image restoration is fundamentally constrained by the tradeoff between distortion and perception: minimizing pixel-wise error yields over-smoothed results, whereas…
arXiv:2608.10414v1 Announce Type: cross Abstract: Large Language Models (LLMs) are typically evaluated on standard written Vietnamese, yet everyday communication frequently involves regional dialects that preserve…
arXiv:2608.10532v1 Announce Type: cross Abstract: Static load balancers cannot mitigate a backend that is degraded rather than down: round-robin and least-connections keep routing traffic to a server returning HTTP 500s…
arXiv:2608.10389v1 Announce Type: cross Abstract: In recent years, neural networks have significantly advanced numerical solutions of partial differential equations (PDEs). However, solving PDEs with discontinuous…
arXiv:2509.05624v3 Announce Type: replace-cross Abstract: How much information about an agent's underlying values can be recovered from its observable behavior? This question matters for any approach that infers agent…
arXiv:2608.11083v1 Announce Type: cross Abstract: Low Power Wide Area Networks like LoRa are increasingly deployed for smart city applications, requiring accurate path loss prediction for effective network planning.…
arXiv:2608.10969v1 Announce Type: new Abstract: Healthcare data, such as Intensive Care Unit (ICU) records, comprise heterogeneous multivariate time series sampled at irregular intervals with pervasive missingness.…
arXiv:2608.10374v1 Announce Type: new Abstract: Training neural networks to jointly predict mean and uncertainty estimates from noisy observations can be unstable, prompting a series of independent stabilization…
arXiv:2512.06227v3 Announce Type: replace-cross Abstract: Real-world indicators play an important role in many Natural Language Processing (NLP) applications, such as life events for mental health analysis and risky…
arXiv:2605.02937v2 Announce Type: replace Abstract: Deep learning in de novo protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize…
arXiv:2608.11019v1 Announce Type: new Abstract: Modeling spatiotemporal dynamical systems governed by partial differential equations (PDEs) poses two major challenges: it either requires expensive physics-based…
arXiv:2606.00135v2 Announce Type: replace Abstract: Tool-calling is a central component of modern large language model (LLM) agents, equipping them with skills beyond their parametric knowledge. This paper studies…
arXiv:2608.10634v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL), which learns environment dynamics to generate synthetic experience, is a promising approach to sample-efficient decision making.…
arXiv:2604.00523v2 Announce Type: replace Abstract: We study for the first time, stochastic dueling bandits over continuous action spaces with Lipschitz structure, where feedback is purely comparative. While dueling…
arXiv:2608.10792v1 Announce Type: cross Abstract: Autonomous chemistry increasingly depends on environments in which agents can repeatedly act, observe, and adapt.Physical laboratories provide essential real-material…
arXiv:2608.11162v1 Announce Type: new Abstract: The Naive Bayes (NB) classifier remains a standard choice for categorical data, yet its widely used smoothing rules, such as Laplace, Lidstone, Krichevsky-Trofimov, and…
arXiv:2608.10008v1 Announce Type: cross Abstract: LLM recommenders for top-$K$ item suggestion regularly emit titles outside the target catalog. Prior audits measure this as a binary out-of-domain rate; none ask whether…
arXiv:2608.11095v1 Announce Type: cross Abstract: Agentic coding READMEs like CLAUDE.md grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wholesale. We trace…
arXiv:2608.10384v1 Announce Type: new Abstract: This paper studies inverse sampling for L\'evy-driven generative models from the perspective of Markov generators. Unlike conventional diffusion models, L\'evy-driven…
arXiv:2605.22800v3 Announce Type: replace Abstract: Ordinary training optimises the task loss and then stops. It never pays for internal representation energy: Jacobians can stay large in directions that never helped…
arXiv:2608.10096v1 Announce Type: cross Abstract: Modern data science increasingly gives rise to hypothesis-testing problems that are not naturally formulated in terms of parameters within prespecified statistical…
arXiv:2608.10271v1 Announce Type: cross Abstract: Breast density classification is a critical component of breast cancer risk assessment, yet AI models often struggle to generalize across clinical sites due to…
arXiv:2601.21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability. Despite strong performance, these models are often…
arXiv:2512.01906v3 Announce Type: replace Abstract: Spiking neural networks (SNNs) are biologically inspired, event-driven models suited for temporal data processing and energy-efficient neuromorphic computing. In SNNs,…
arXiv:2608.07935v2 Announce Type: replace Abstract: On-policy self-distillation (OPSD) adapts a language model by distilling guidance from a frozen teacher on trajectories sampled from the student. Its effectiveness,…
arXiv:2608.09998v1 Announce Type: cross Abstract: Artificial Intelligence (AI) and Machine Learning (ML) have become powerful tools for supporting and automating complex human tasks. Despite their benefits, growing…
arXiv:2608.09948v1 Announce Type: cross Abstract: No single AI weather model excels at all variables, pressure levels, and lead times. Rather than building yet another architecture, we reframe the forecasting problem as…
arXiv:2602.20403v2 Announce Type: replace Abstract: We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from a…
arXiv:2608.10047v1 Announce Type: new Abstract: In modern industry, keeping complex systems reliable, safe, and efficient hinges on Prognostics and Health Management (PHM). Machine Learning (ML) has largely driven…
arXiv:2605.28803v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models unify perception, reasoning, and control in a single policy, but their multi-billion-parameter backbones and diffusion-based…
arXiv:2605.21600v3 Announce Type: replace Abstract: Computational antibody CDR design methods condition on antigen structure to generate binding loops. Yet, the existing architectures conflate two fundamentally distinct…
arXiv:2608.10268v1 Announce Type: new Abstract: Large language models (LLMs) increasingly mediate legal determinations over what human rights are realized, and how. Yet, no evaluation benchmark exists to assess whether…
arXiv:2606.12260v3 Announce Type: replace-cross Abstract: How can we design a market of human-generated content for use in training AI models that both enables technological progress and preserves individual incentives…
arXiv:2608.09942v1 Announce Type: cross Abstract: It is widely assumed that chain-of-thought (CoT) prompting universally improves LLM reasoning. We investigate this through the conceptual framework of the H_dp bandwidth…
arXiv:2608.11016v1 Announce Type: cross Abstract: Clustering is a fundamental class of data analysis techniques with the most important representatives being centroid-based methods like $k$-means. Such methods are…
arXiv:2608.10300v1 Announce Type: cross Abstract: Electronic health-record interoperability is a boundary problem: legacy systems, generative models, terminology services, identity systems, and human reviewers may each…
arXiv:2608.10240v1 Announce Type: cross Abstract: Multi-modal sequential recommenders assume every item carries every modality, but real product catalogs often miss images or text, and a model trained on complete data…
arXiv:2608.10621v1 Announce Type: new Abstract: Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs. Existing guardrails typically formulate safety…
arXiv:2608.11003v1 Announce Type: cross Abstract: In this work, we study the information bottleneck under perfect privacy, with particular emphasis on the active-rate regime, where the representation-rate constraint is…
arXiv:2505.02257v2 Announce Type: replace-cross Abstract: In regions lacking medically certified causes of death, verbal autopsy (VA) is a widely used tool to ascertain the cause of death through interviews with…
arXiv:2608.10344v1 Announce Type: cross Abstract: Thermo-mechanical compliant devices are commonly designed with small-strain linear elasticity and temperature-independent material properties, even though they might…
arXiv:2608.10562v1 Announce Type: new Abstract: Not all clicks are equal. Industrial ads ranking decouples conversion probability into click-through rate (CTR) and post-click conversion rate (CVR), yet treats every…
arXiv:2608.10599v1 Announce Type: new Abstract: In a $\beta$-VAE, increasing the regularization strength acts as a spectral cutoff by collapsing low-utility latent coordinates. In the linear Gaussian VAE, the collapse…
arXiv:2608.10050v1 Announce Type: new Abstract: Small and medium-sized businesses need timely financial guidance, yet historical accounting logs record self-selected and often co-occurring business changes rather than…
arXiv:2608.10235v1 Announce Type: new Abstract: Hamiltonian Neural Networks (HNNs) parameterize conservative dynamics through a learned scalar Hamiltonian, providing an architectural prior that is absent from generic…
arXiv:2608.10903v1 Announce Type: cross Abstract: Reliable clinical deployment of machine learning requires models that know when they are likely to fail, particularly for subgroups underrepresented in training data. A…
arXiv:2608.11061v1 Announce Type: new Abstract: Large-scale neural recommender systems are typically trained with a softmax cross-entropy objective over the full item vocabulary. For a typical large number of possible…
arXiv:2604.07126v3 Announce Type: replace-cross Abstract: Predicting traffic agent trajectories plays an important role in autonomous driving, traffic operations, transportation safety analysis, etc. Although many deep…
arXiv:2608.10694v1 Announce Type: new Abstract: Evolutionary optimization of LLM prompts and agentic programs (e.g., GEPA) is dominated by fitness evaluation: scoring each candidate runs an answering LLM over a…
arXiv:2608.11156v1 Announce Type: cross Abstract: Conditional Independence (CI) tests are the statistical engine of constraint-based causal discovery: in algorithms such as PC (Peter-Clark) and FCI (Fast Causal…
arXiv:2605.23146v3 Announce Type: replace Abstract: Classical reinforcement learning assumes the agent interacts with a fixed environment whose behavior does not depend on the agent's policy. This assumption breaks down…
arXiv:2608.11020v1 Announce Type: new Abstract: We systematically investigate finite-difference (FD) derivative computation in Physics-Informed Neural Networks (PINNs) as an alternative to automatic differentiation…
arXiv:2608.10835v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) achieve impressive visual reasoning and dialogue capabilities, yet frequently hallucinate content unsupported by the visual input.…
arXiv:2608.10386v1 Announce Type: new Abstract: Sample-efficient reinforcement learning for autonomous driving is often limited by the trade-off between data efficiency and model bias. While world models reduce the…
arXiv:2608.10441v1 Announce Type: new Abstract: Many pipelines can pay a per-example cost to acquire an auxiliary, model-derived observation -- an LLM's structured reasoning, a slow oracle, an expensive measurement --…
arXiv:2406.12659v3 Announce Type: replace-cross Abstract: We propose a scalable variational Bayes method for statistical inference for a single or pre-specified low-dimensional subset of the coordinates of a…
arXiv:2608.10703v1 Announce Type: new Abstract: Large language models (LLMs) increasingly act in interactive settings where their behavioral styles affect user experience, safety, and downstream decision making.…
arXiv:2509.19696v4 Announce Type: replace-cross Abstract: Learning-based methods excel at robot motion generation but remain limited in contact-rich physical interaction. Impedance control provides stable and safe…
arXiv:2608.10416v1 Announce Type: cross Abstract: We present a theoretical foundation for inverse-distance attention, from its Euclidean prototype (Resolver) to its non-Euclidean realization (Riemann GeoResolver). The…
arXiv:2608.11114v1 Announce Type: new Abstract: Probabilistic forecasting plays an essential role in risk-sensitive decision-making, particularly in long-horizon settings. However, existing approaches often face a…
arXiv:2608.10941v1 Announce Type: new Abstract: Industrial time-series signals, such as turbine temperature and rotational speed in aero-engines, are essential for monitoring the health and operational status of complex…
arXiv:2608.10517v1 Announce Type: cross Abstract: Accurate physical-layer modeling is increasingly essential for reliable ultra-wideband operation and capacity optimization, especially under the intensified…
arXiv:2607.03798v4 Announce Type: replace Abstract: Symmetry is everywhere in nature and society. Geometric deep learning builds architectures respecting group symmetries, whereas topological deep learning organizes…
arXiv:2608.08422v2 Announce Type: replace-cross Abstract: Ranking data arise in scientific and machine learning applications, including recommendation systems, information retrieval, voting, marketing, and AI preference…
arXiv:2602.01747v2 Announce Type: replace-cross Abstract: Automated Essay Scoring (AES) plays a crucial role in education by providing scalable and efficient assessment tools. However, in real-world settings, the…
arXiv:2608.10089v1 Announce Type: cross Abstract: Bias evaluations often move too quickly from evidence that a model encodes a social association to claims that the same association will alter consequential decisions.…
arXiv:2608.10126v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) aggregates heterogeneous preferences into a single reward model, assuming preference homogeneity. When preferences are…
arXiv:2608.11154v1 Announce Type: new Abstract: Detecting or attributing a supply-chain disruption is not the same as selecting the intervention that maximizes recoverable net value. We present CriticalSCM-Bench v1, a…
arXiv:2608.10090v1 Announce Type: cross Abstract: Large language models (LLMs) have advanced code generation, where executable feedback provides a more reliable learning signal than textual imitation alone. Hardware…
arXiv:2606.29484v2 Announce Type: replace-cross Abstract: In moderation, provenance, and verification pipelines a deepfake detector's output probability is read as a degree of trust, so its calibration matters as much…
arXiv:2608.11054v1 Announce Type: new Abstract: Deep learning models have emerged as the standard computational tool for a wide range of applications in genomics. Yet, uncertainty quantification (UQ) -- and more…
arXiv:2608.10316v1 Announce Type: cross Abstract: Multi-modal learning combining medical images and clinical text is promising for disease diagnosis. However, standard multi-modal training leads to shortcut learning:…
arXiv:2608.11181v1 Announce Type: cross Abstract: When a probabilistic predictor answers many conditional-probability queries, are its answers self-consistent, and can this be verified in polynomial time? This problem…
arXiv:2608.10007v1 Announce Type: new Abstract: The current state-of-the-art (SOTA) deep randomized neural networks, such as deep Random Vector Functional Link (dRVFL) and ensemble deep RVFL (edRVFL), treat all training…
arXiv:2511.00217v3 Announce Type: replace-cross Abstract: We introduce a novel way to combine gradient boosting with mixed effects models, whereby the mean and variance components are learned jointly as functions of…
arXiv:2608.08557v2 Announce Type: replace-cross Abstract: Visual tool use has emerged as a fundamental capability for multimodal agents to actively acquire evidence beyond a fixed image encoding. The prevailing recipe…
arXiv:2608.10433v1 Announce Type: new Abstract: Forecast accuracy does not tell us which past inputs produced a prediction. We separate three questions for time-series models with known delay structure: can the true…
arXiv:2511.00366v3 Announce Type: replace-cross Abstract: Digital twins are developed to model the behavior of a specific physical asset (or twin), and they can consist of high-fidelity physics-based models or…
arXiv:2607.04726v3 Announce Type: replace-cross Abstract: Chart-to-code generation is commonly trained with supervised fine-tuning on reference plotting scripts, implicitly treating the gold code as a fully observable…
arXiv:2502.02068v3 Announce Type: replace-cross Abstract: This paper introduces RoSeMary, the first-of-its-kind ML/Crypto codesign watermarking framework that regulates LLM-generated code to avoid intellectual property…
arXiv:2603.14846v4 Announce Type: replace Abstract: We define an information-complexity property for aggregation functions, capturing a vast range of practical aggregations, and prove that any Message-Passing Graph…
arXiv:2608.10528v1 Announce Type: cross Abstract: Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to recover cross-document context at pointwise cost. We study when this…
arXiv:2608.10867v1 Announce Type: new Abstract: Gradient-free post-training has emerged as a compelling alternative to gradient-based optimization for large language models (LLMs), but existing approaches remain costly.…
arXiv:2602.11410v2 Announce Type: replace Abstract: Click-through rate (CTR) prediction is fundamental to online advertising systems. While Deep Learning Recommendation Models (DLRMs) with explicit feature interactions…
arXiv:2307.03587v4 Announce Type: replace Abstract: In non-stationary linear contextual bandits, existing efficient algorithms typically rely on the Weighted Regularized Least-Squares (WRLS) estimator. Because WRLS only…
arXiv:2608.10430v1 Announce Type: new Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions to force a…
arXiv:2608.10351v1 Announce Type: new Abstract: In this work we present a method to accelerate the optimization of learning high dimensional functions using deep neural network (DNN). This optimization procedure…
arXiv:2608.10474v1 Announce Type: cross Abstract: Popularity bias in recommendation systems arises when a majority user class generates disproportionate interaction data, causing the system to increasingly favour it…
arXiv:2608.09967v1 Announce Type: cross Abstract: Deep reinforcement learning (DRL) agents achieve strong performance in complex environments, yet their decision-making processes remain difficult to interpret. We…
arXiv:2605.10775v2 Announce Type: replace-cross Abstract: A surprising phenomenon in the training of neural networks is the ability of gradient descent to find global minimizers of the training loss despite its…
arXiv:2608.10823v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training of large language models (LLMs) is computationally intensive and involves complex system pipelines with substantial debugging…
arXiv:2605.21610v2 Announce Type: replace Abstract: Antibody design methods condition on antigen structure to generate complementarity-determining regions (CDR), yet a systematic evaluation of baseline methods reveals…
arXiv:2506.11142v3 Announce Type: replace-cross Abstract: Semi-supervised semantic segmentation (SSSS) faces persistent challenges in effectively leveraging unlabeled data, such as ineffective utilization of…
arXiv:2608.09997v1 Announce Type: new Abstract: Transformers have had a profound impact on the world of language processing and computer vision. As efforts to answer the million-dollar question of ``How does a…
arXiv:2608.09385v2 Announce Type: replace Abstract: Generative AI models are primarily designed to imitate the data distribution, an objective that neither corrects diversity lost by a learned generator nor defines how…
arXiv:2606.00643v2 Announce Type: replace-cross Abstract: Physics-Informed Neural Networks (PINNs) often train slowly or fail to converge on challenging partial differential equations (PDEs), a behavior recently linked…
arXiv:2602.21436v2 Announce Type: replace-cross Abstract: In this paper, we study last-iterate convergence of learning algorithms in bilinear saddle-point problems, a preferable notion of convergence that captures the…
arXiv:2608.08574v2 Announce Type: replace Abstract: Crowdsourced Federated Learning (CrowdFL) extends traditional federated learning by enabling open and heterogeneous participation through a crowdsourcing paradigm. In…
arXiv:2608.10247v1 Announce Type: cross Abstract: Real-world recommendation platforms routinely collect explicit negative feedback such as 1-star reviews, hate-button clicks, distrust between users, and very-low…
arXiv:2608.09943v1 Announce Type: cross Abstract: Monitoring livestock behaviour under extensive conditions would provide valuable insights to assess animal adaption to environmental perturbations in agroecological…
arXiv:2608.11093v1 Announce Type: new Abstract: Cross-view feature matching aims to establish reliable correspondences across images with large viewpoint variations. Over the past decade, the field has evolved from…
arXiv:2608.10424v1 Announce Type: cross Abstract: A slew of recent works develop agents for solving research problems end-to-end, a paradigm increasingly referred to as autoresearch. Such agents have inspired large…
arXiv:2511.22331v4 Announce Type: replace-cross Abstract: Bilevel optimization minimizes an objective function, defined by an upper-level problem whose feasible region is the solution of a lower-level problem. We study…
arXiv:2608.10137v1 Announce Type: cross Abstract: Grammar Constrained Decoding (GCD) forces Language Models (LMs) to produce syntactically valid outputs by masking out non-conforming tokens at each step. However, rigid…
arXiv:2509.13211v4 Announce Type: replace Abstract: The ability to learn continuously over time remains a major challenge for modern machine learning systems, even in the era of Foundation Models. While the rich…
arXiv:2608.10232v1 Announce Type: cross Abstract: Recent world-action models (WAMs) show that co-training policies with future prediction can provide physical priors for action generation. Building on the…
arXiv:2608.10037v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rely on external tools to accomplish complex real-world tasks, making tool documentation a critical grounding resource for LLM…
arXiv:2608.10473v1 Announce Type: new Abstract: Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction. However, directly…
arXiv:2608.10056v1 Announce Type: cross Abstract: Following a target human in crowded environments involves an inherent conflict between staying close to the target and navigating safely among surrounding pedestrians…
arXiv:2509.10600v5 Announce Type: replace-cross Abstract: Collegiate cross country teams often build their season schedules on intuition rather than evidence, partly because large-scale performance datasets were not…
arXiv:2608.10470v1 Announce Type: new Abstract: Fair representation learning with a continuous sensitive attribute $S$ requires a representation $Z$ that is statistically independent of $S$. Existing criteria, including…
arXiv:2608.09417v2 Announce Type: replace Abstract: Deep decoder-only Transformers often replace the original Post-Norm architecture with Pre-Norm variants because Post-Norm training is highly sensitive to warmup and…
arXiv:2604.12036v3 Announce Type: replace-cross Abstract: We study a well-known task of constructing a decision tree identifying an unknown hypothesis from a given ground set of hypotheses under both the average- and…
arXiv:2608.11047v1 Announce Type: cross Abstract: While existing benchmarks have made substantial progress in evaluating LLMs across STEM domains, financial reasoning over structured data remains comparatively less…
arXiv:2608.10587v1 Announce Type: new Abstract: Artificial Intelligence (AI)-based prospective anomaly detection methods are increasingly deployed in high-dimensional and nonlinear settings. Among these approaches,…
arXiv:2606.00671v2 Announce Type: replace-cross Abstract: We present AXIOM, a trust-first neuro-symbolic architecture for natural-language mathematical reasoning. Its language model is strictly a canonicalizer: it…
arXiv:2608.10600v1 Announce Type: cross Abstract: Skill abstraction---the process of learning reusable and temporally extended behaviors---has emerged as a key paradigm for improving sample efficiency and generalization…
arXiv:2605.09273v3 Announce Type: replace Abstract: We study online multicalibration beyond the worst-case. We give a single, efficient algorithm which dynamically interpolates between benign and worst-case sequences by…
arXiv:2607.22286v2 Announce Type: replace Abstract: Anomaly detection is inherently characterised by severe class imbalance, making the interpretation of evaluation metrics challenging. Although metrics such as AUROC,…
arXiv:2605.31249v2 Announce Type: replace Abstract: Electrocardiography (ECG) is a cornerstone of cardiac assessment, making the learning of informative ECG representations fundamental to tasks ranging from disease…
arXiv:2501.11655v3 Announce Type: replace-cross Abstract: This paper proposes a novel learning approach for designing Kazantzis-Kravaris or nonlinear Luenberger (KKL) observers for autonomous nonlinear systems. The…
arXiv:2608.09959v1 Announce Type: cross Abstract: AI weather models are in the process of revolutionising weather forecasting. While these models have been shown to achieve superior performance to physics-based NWP in…
arXiv:2608.06690v2 Announce Type: replace-cross Abstract: Most language-model access controls regulate behavior while leaving the same computation available to every request. We study a different systems question: can…
arXiv:2607.18281v3 Announce Type: replace-cross Abstract: Finding exact solutions to the quantum many-body problem is computationally intractable (QMA-hard). Traditional approximations for electrons in an atom or…
arXiv:2608.10357v1 Announce Type: new Abstract: Long-horizon tool-using agents must reason over user goals, domain policies, tool calls, simulator state, and delayed verifiable rewards. Reinforcement learning (RL) is a…
arXiv:2608.10657v1 Announce Type: cross Abstract: Leukemia cell image classification is challenged by real-world domain shifts from acquisition, staining, illumination, and site protocols, causing single-dataset models…
arXiv:2608.10145v1 Announce Type: new Abstract: LeWorldModel trains a latent world model with a prediction loss and a single anti-collapse regulariser, and reports approximately 87% of goals reached on TwoRoom, its…
arXiv:2505.22839v2 Announce Type: replace Abstract: Recent studies suggest that diffusion models significantly improve the empirical adversarial robustness of deep neural network models. While intuitive explanations…
arXiv:2604.22416v3 Announce Type: replace Abstract: Latent variables pose a fundamental obstacle to both causal discovery and inference. Local approaches exploiting direct neighborhood relations provide little beyond…
arXiv:2512.06244v4 Announce Type: replace Abstract: The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and…
arXiv:2602.13136v2 Announce Type: replace Abstract: Template-free retrosynthesis methods treat the task as black-box sequence generation, limiting learning efficiency, while semi-template approaches rely on rigid…
arXiv:2608.10896v1 Announce Type: cross Abstract: Constant-stepsize temporal-difference (TD) learning is attractive for policy evaluation, but inference from a single Markov trajectory must account for serial dependence…
arXiv:2608.10619v1 Announce Type: new Abstract: Message-passing neural networks (MPNNs) often struggle when task-relevant information is distributed across distant regions of a graph, since local propagation must…
arXiv:2508.13831v4 Announce Type: replace-cross Abstract: Functional data, i.e., random functions observed over a continuous domain, are increasingly available in areas such as biomedical research, health informatics,…
arXiv:2604.06336v2 Announce Type: replace Abstract: Fragment-level representations provide a natural way to capture recurring molecular substructures and reuse their learned representations across molecules. However, a…
arXiv:2601.05280v3 Announce Type: replace-cross Abstract: On the one hand, the question of whether large language models (LLMs) are Solomonoff induction estimators has become an explicit question at the intersection of…
arXiv:2608.10256v1 Announce Type: new Abstract: Accurate vessel trajectory prediction is critical for maritime safety and anomaly detection, yet existing models often struggle with geographic bias and navigational…
arXiv:2608.08365v2 Announce Type: replace-cross Abstract: Data-driven health-state estimators for SiC (Silica-Carbide) power modules typically report their performance on a single accelerated-aging campaign, and how…
arXiv:2608.10245v1 Announce Type: cross Abstract: Inventory and distribution planning in Physical Internet networks requires coordinating factory-hub assignments, factory supply, lateral transshipment among…
arXiv:2608.10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining. An ideal calibrator should correct nonlinear…
arXiv:2608.11143v1 Announce Type: new Abstract: This paper develops a method for sensor-subset selection for tracking. Prior work showed that low-cost acoustic Received Signal Strength Indicator (RSSI) measurements can…
arXiv:2608.10400v1 Announce Type: new Abstract: What if judges already behave like algorithms? As artificial intelligence and algorithms are deployed in many settings, including the judicial system, many have debated…
arXiv:2608.10804v1 Announce Type: cross Abstract: Deep neural networks excel in various tasks but struggle to generalize across evolving data distributions, leading to significant performance degradation under domain…
arXiv:2603.25251v2 Announce Type: replace-cross Abstract: Explainable AI (XAI) methods are commonly evaluated using functional correctness metrics, sometimes termed faithfulness or fidelity, which estimate how closely…
arXiv:2608.10936v1 Announce Type: cross Abstract: We study a Restart POMDP (Partially Observable Markov Decision Process) on a general Borel state space, where the controller either lets the hidden state evolve…
arXiv:2604.18245v3 Announce Type: replace Abstract: Large language models operate in protocols containing multiple calls, yet added calls are usually evaluated only by their net effect. That summary cannot distinguish…
arXiv:2603.12231v3 Announce Type: replace Abstract: Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are…
arXiv:2608.11034v1 Announce Type: cross Abstract: In LLM pre-training, synchronization propagates rank-local stalls, slowdowns, and numerical errors into job-wide symptoms, obscuring their origin. Existing diagnosis…
arXiv:2606.15237v1 Announce Type: cross Abstract: Ensemble classifiers are predictive models that combine the results of simpler base models, often by majority vote. A classic example is random forests, which combine…
arXiv:2608.10529v1 Announce Type: new Abstract: The multi-armed bandit problem is a central framework in sequential decision-making, extensively studied under sub-Gaussian reward assumptions. However, real-world…
arXiv:2608.10251v1 Announce Type: cross Abstract: A transformer's answer lives on one axis: the direction its unembedding reads. Its intermediate states largely do not, and that off-axis position is usually treated as…
arXiv:2608.11123v1 Announce Type: cross Abstract: Augmentation can corrupt a training example when an image and its annotations receive different random changes. A crop must use the same coordinates for the image, mask,…
arXiv:2608.10418v1 Announce Type: cross Abstract: Recent work has shown that, for smooth convex optimization, plain gradient descent can be accelerated from its textbook convergence rate of $O(T^{-1})$ (where $T$…
arXiv:2608.10891v1 Announce Type: new Abstract: Time series forecasting in privacy-sensitive domains often requires training models on released data rather than original observations. Synthetic time series generation…
arXiv:2607.13205v2 Announce Type: replace-cross Abstract: Attention-based KV cache eviction (H2O and its descendants) compresses the memory-constrained state of a long-context model by ranking tokens on accumulated…
arXiv:2604.02621v2 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) substantially improves the reasoning capabilities of language models, but most existing RL fine-tuning approaches rely entirely on…
arXiv:2608.10204v1 Announce Type: new Abstract: Safe reinforcement learning maximizes reward subject to safety constraints. For Constrained Markov Decision Processes, the linear-programming view over occupancy measures…
arXiv:2605.05629v4 Announce Type: replace-cross Abstract: We study the problem of learning generative models for discrete sequences in a continuous embedding space. Whereas prior approaches typically operate in…
arXiv:2602.15159v2 Announce Type: replace Abstract: Electronic health records (EHR) arrive masked. Clinicians order measurements selectively, and any patient table thus contains only a subset of the values that…
arXiv:2608.10392v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts. Shared-expert designs preserve reusable knowledge, fine-grained…
arXiv:2608.10777v1 Announce Type: new Abstract: Linear Quadratic Stochastic Optimal Control (LQ-SOC) establishes a fundamental framework for steering noisy dynamical systems and has recently gained renewed interest in…
arXiv:2608.10869v1 Announce Type: new Abstract: Worst-case multiclass bounds do not become smaller when the best classifier is already nearly correct: what is missing is an optimistic rate, a guarantee whose fluctuation…
arXiv:2608.10523v1 Announce Type: new Abstract: \texttt{TensorSketch} by~\cite{pham2013fast,kar2012random} provides efficient sketching algorithms for high-dimensional polynomial kernels $\vec{x}^{\otimes p} \in…
arXiv:2608.10674v1 Announce Type: cross Abstract: The Uhlmann fidelity ${\rm F}(\rho_0,\rho_1) = {\rm tr}|\sqrt{\rho_0}\sqrt{\rho_1}|$ is one of the most fundamental quantities in quantum information theory for…
arXiv:2608.10147v1 Announce Type: new Abstract: We study the best separable state problem (BSS), which asks for the maximum acceptance probability of a quantum measurement over unentangled states. In classical terms,…
arXiv:2608.11163v1 Announce Type: new Abstract: We show that a simple extension of the randomized greedy maximal independent set algorithm yields a constant approximation for the maximum matching problem. The algorithm…
arXiv:2608.11038v1 Announce Type: new Abstract: We study the graphic $s$-$t$ path TSP on subcubic graphs (maximum degree 3): given two vertices $s,t$, find a shortest walk from $s$ to $t$ that visits every vertex. Our…
arXiv:2504.21601v3 Announce Type: replace-cross Abstract: Discrete Forman-Ricci curvature (FRC) is an efficient tool that characterizes essential geometrical features and associated transitions of real-world networks,…
arXiv:2608.10326v1 Announce Type: cross Abstract: We study envy elimination by adding goods (EEAG) when the additional pool has bounded supply and no separate budget bound. We establish a sharp type-count dichotomy for…
arXiv:2607.13284v2 Announce Type: replace Abstract: The minimum spanning tree (MST) problem is one of the most basic optimization problems on metric spaces and graphs. We study the problem of computing a…
arXiv:2608.10184v1 Announce Type: cross Abstract: Let $x_1,\ldots,x_n$ be independent standard Gaussian vectors in $\mathbb{R}^d$. An \emph{ellipsoid fit} is a matrix $S \succeq 0$ such that $x_i^\top S x_i =d$ for…
arXiv:2608.10193v1 Announce Type: cross Abstract: We prove a necessary and sufficient Hall condition for a family $A=(A_e)_{e\in E(G)}$ of hypergraphs, possibly with loops, indexed by the edges of a forest $G$. We also…
arXiv:2608.11158v1 Announce Type: cross Abstract: We establish new bounds on the Grothendieck constant $K_G$: \[ \frac{6\pi}{11} \le K_G \le \frac{\pi}{2\log(1+\sqrt2)} - 10^{-4}. \] Methodologically, our lower bound…
arXiv:2608.10040v1 Announce Type: new Abstract: We study online discrepancy minimization: vectors $v_1,\ldots,v_T\in\mathbb{R}^n$ arrive sequentially, and each must immediately be assigned a sign $x_t\in\{\pm1\}$, with…
arXiv:2608.10848v1 Announce Type: new Abstract: We study the problem of connectivity augmentation of a planar graph, while preserving planarity. This problem is motivated by many real-world settings such as…
arXiv:2608.10135v1 Announce Type: new Abstract: A number of fundamental graph problems admit simple algorithms based on iterative peeling: repeatedly remove all vertices whose current degree is below a fixed threshold.…
arXiv:2608.10376v1 Announce Type: new Abstract: A set of intervals $I = \{ I_1, I_2, \dots, I_n \}$ forms a simple chain if, for every $2\leq i \leq n-1$, interval $I_i$ overlaps only with $I_{i-1}$ and $I_{i+1}$. We…
arXiv:2608.11057v1 Announce Type: new Abstract: We study the minimum-weight mixed dominating set problem on threshold graphs. In this problem, vertices and edges have weights, and the goal is to find a mixed set of…
arXiv:2603.12894v3 Announce Type: replace Abstract: The BEST theorem, due to de Bruijn, van Aardenne-Ehrenfest, Smith, and Tutte, is a classical tool from graph theory that links the Eulerian trails in a directed graph…
arXiv:2608.10753v1 Announce Type: new Abstract: Having simple algorithms is important for the practical adoption of new algorithms. However, simplifying existing algorithms is a field that does not usually receive a lot…
arXiv:2608.10421v1 Announce Type: new Abstract: In this paper, we present a stable mergesort variant, "directional mergesort", that to sort an array of $n$ elements makes no more than $nH+3n$ comparisons and…
arXiv:2506.16021v2 Announce Type: replace-cross Abstract: The problem of locally routing on geometric networks using limited memory is extensively studied in computational geometry. We consider one particular graph, the…
arXiv:2309.09359v3 Announce Type: replace-cross Abstract: Skiplists are used in a variety of applications for storing data subject to order criteria. In this article we discuss the design, analysis and performance of a…
arXiv:2608.11094v1 Announce Type: new Abstract: In the undirected \emph{Densest Subgraph Problem (DSG)} the goal is to output a subset $S$ of vertices of a given graph $G$ that maximizes the quantity $|E(S)|/|S|$, where…
arXiv:2608.10380v1 Announce Type: new Abstract: A connectivity function on a finite set $E$ is a function $f\colon 2^E\to\mathbb Z$ that is submodular and symmetric, with $f(\varnothing)=0$. Given a connectivity…
arXiv:2608.10617v1 Announce Type: new Abstract: For a connected graph $G = (V, E)$, a set $D \subseteq V$ is a co-secure dominating set if $D$ is a dominating set of $G$ and for each vertex $u \in D$ there exists a…
arXiv:2507.18776v2 Announce Type: replace-cross Abstract: We address the problem proposed by Chartrand, Erd\H{o}s and Oellermann (1988) about the existence of regular $K_3$-irregular graphs. We first establish bounds on…
arXiv:2009.09674v2 Announce Type: replace-cross Abstract: Let $\mathcal G$ be a hypergraph whose edges are colored. An {\it $(\alpha,n)$-detachment} of $\mathcal G$ is a hypergraph obtained by splitting a vertex…
arXiv:2311.13523v3 Announce Type: replace-cross Abstract: We study the problem of gradually representing a complex graph as a sequence of drawings of small subgraphs whose union is the complex graph. The sequence of…
arXiv:2510.13705v3 Announce Type: replace-cross Abstract: We prove a support--shattering uncertainty principle for functions on the Boolean cube. Let $\mathbb{F}$ be any field and let $f:\{0,1\}^n\to\mathbb{F}$ be…
arXiv:2608.10874v1 Announce Type: new Abstract: A proper conflict-free (PCF) $k$-coloring of a graph $G$ is a proper $k$-coloring such that there exists a color that appears exactly once in the neighborhood of every…
arXiv:2608.10315v1 Announce Type: new Abstract: Large language models (LLMs) are powerful black-box systems, making it difficult to discern whether their answers reflect stable internal beliefs or superficial pattern…
arXiv:2608.10109v1 Announce Type: new Abstract: Social media has become a major venue for multilingual communication, where users frequently mix multiple languages within a single utterance. Although code-mixed corpora…
arXiv:2608.10949v1 Announce Type: cross Abstract: Streaming video understanding requires multimodal large language models (MLLMs) to preserve relevant evidence from continuously evolving streams under strict causality…
arXiv:2608.10216v1 Announce Type: new Abstract: Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff. Deduplication filters, semantic caches, drift…
arXiv:2509.25143v2 Announce Type: replace-cross Abstract: Existing medical reasoning benchmarks for vision-language models primarily focus on analyzing a patient's condition based on an image from a single visit.…
arXiv:2608.10636v1 Announce Type: cross Abstract: Visual document retrieval (VDR) is dominated by multi-billion-parameter models that are slow to index at full corpus scale and expensive to serve. Prior compression…
arXiv:2604.08849v3 Announce Type: replace Abstract: Many real-world retrieval and matching problems require more than topical relevance: a candidate must satisfy the specific constraints of one profile among many, not…
arXiv:2608.10688v1 Announce Type: new Abstract: Purpose: Keyphrases are statistically and semantically important textual units that can also attract readers' attention during comprehension. However, existing keyphrase…
arXiv:2608.11138v1 Announce Type: new Abstract: We propose that a model's uncertainty about a token is reflected not only in the breadth of its output distribution but also in whether a confident prediction is…
arXiv:2608.10715v1 Announce Type: new Abstract: Over the past several years, LLM-powered chatbots and agents have become widely used as a tool for academic writing. LLM-assisted writing can be valuable by removing…
arXiv:2607.21412v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) excel at natural language understanding and generation but remain unreliable for multi-step logical reasoning, especially in…
arXiv:2601.17387v3 Announce Type: replace Abstract: Multilingual speech-text models rely on cross-modal language alignment to transfer knowledge between speech and text, but it remains unclear whether this reflects…
arXiv:2608.11171v1 Announce Type: new Abstract: The Workshop on Trustworthy Natural Language Processing (TrustNLP), co-located with major ACL conferences since 2021, has grown from 8 proceedings papers to 41 over six…
arXiv:2608.09936v1 Announce Type: new Abstract: Do French news headlines frame left- and right-populist challengers as symmetric ``extremes,'' or as fundamentally different political adversaries? We examine 28,592…
arXiv:2608.10698v1 Announce Type: new Abstract: The rapid development of large language models (LLMs) has increased the need for reliable detection of LLM-generated text, especially in realistic Chinese scenarios…
arXiv:2606.08348v2 Announce Type: replace Abstract: LLM agents increasingly rely on prompts, tools, memory, SOPs, skills, and harness feedback, yet current self-evolution pipelines often update these assets through…
arXiv:2608.10878v1 Announce Type: new Abstract: Accurate and responsive turn-taking is essential for spoken dialogue systems, which must distinguish in real time between user interruptions, backchannels that should be…
arXiv:2606.11470v2 Announce Type: replace Abstract: Reasoning has become central to how Large Language Models (LLMs) are evaluated and interpreted, spanning Chain-of-Thought (CoT), mathematical problem-solving,…
arXiv:2608.10503v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. The NLP community…
arXiv:2608.10206v1 Announce Type: cross Abstract: Detecting phonemes from children's speech has historically been difficult due to the scarcity of training data, and unique characteristics of children's speech. During a…
arXiv:2608.10337v1 Announce Type: cross Abstract: We introduce narrative keyframing, an interaction technique for AI-assisted creative writing that lets writers specify different types of narrative constraints at…
arXiv:2608.10218v1 Announce Type: cross Abstract: AI agents are becoming more autonomous and increasingly interconnected, exposing them to new emergent risks arising from agent-to-agent interaction. One such risk is the…
arXiv:2606.07943v2 Announce Type: replace-cross Abstract: Agent skills extend general-purpose agents, but their open format enables skill poisoning: a tampered skill can make an agent run an attacker's command while…
arXiv:2606.06960v2 Announce Type: replace Abstract: Experience-based self-evolution enables language-model agents to improve their behavior by accumulating and updating experience at test time, yet existing evaluations…
arXiv:2608.10812v1 Announce Type: new Abstract: We study reference-free post-training for multilingual machine translation with open large language models. Starting from the supervised-finetuned MiLMMT-46-v0.1 models,…
arXiv:2608.10690v1 Announce Type: new Abstract: Pretraining corpus composition shapes LLM capabilities, but it often remains hidden even when model weights are released. Prior work has inferred corpus mixtures or traced…
arXiv:2608.10996v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has been especially effective in mathematics and coding, where answers can be checked automatically. Many open-ended medical…
arXiv:2608.06869v2 Announce Type: replace-cross Abstract: We describe DAEP, team BIGC's submission to NLPCC 2026 Shared Task 1 Track 3: Difficulty-Aware Temporal Answer Grounding in Video Corpus (DA-TAGVC). The task…
arXiv:2608.11044v1 Announce Type: new Abstract: Hierarchical Text Classification (HTC), as a critical text mining task, faces challenges such as complex label hierarchies and class imbalance. Existing methods based on…
arXiv:2608.10154v1 Announce Type: new Abstract: We present results from reconstructing multiple-choice model (MCM) and three-parameter logistic (3PL) model curves using a fine-tuned multimodal large language model (LLM)…
arXiv:2608.08775v2 Announce Type: replace Abstract: Agentic benchmarks aim to measure how well AI agents plan, search, execute, and recover within realistic multi-tool environments, but they are almost exclusively in…
arXiv:2508.08636v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly expected to act as generalist agents capable of solving complex real-world problems. Training such agents, however,…
arXiv:2608.11036v1 Announce Type: new Abstract: Although Whisper models benefit from large-scale multilingual pre-training, their performance on Burmese medical speech remains limited. This work presents a Burmese…
arXiv:2604.25374v2 Announce Type: replace Abstract: Background: Dutch medical corpora are scarce, limiting NLP development. Methods: We translated English datasets, identified medical text in generic corpora, and…
arXiv:2608.10810v1 Announce Type: new Abstract: Emotion understanding in discourse requires reasoning beyond surface sentiment because speakers often convey affect through indirect, implicit, polite, ironic, or…
arXiv:2608.10679v1 Announce Type: cross Abstract: Enterprise question answering is framed as retrieving internal documents and generating grounded answers. Routine enterprise records, however, are work by-products in…
arXiv:2608.10606v1 Announce Type: new Abstract: ASR-roundtrip evaluation is widely used as a scalable proxy for text-to-speech (TTS) intelligibility, but it can produce false negatives for reading errors perceived by…
arXiv:2608.10359v1 Announce Type: cross Abstract: As information increasingly traverses linguistic boundaries, users require concise cross-lingual representations of long-form content. Nevertheless, long-document…
arXiv:2608.09548v2 Announce Type: replace Abstract: Large language models are increasingly deployed in education as tutors, teaching assistants, and content generators. These roles place demands that ordinary question…
arXiv:2608.10908v1 Announce Type: cross Abstract: As generative multimedia evolves from static image synthesis to complex, interleaved visual narratives, a foundational bottleneck has emerged: the judgment crisis. While…
arXiv:2608.10731v1 Announce Type: cross Abstract: Whether an additional general dimension is necessary beyond correlated first-order factors is a property of the population covariance matrix, not of any estimator or…
arXiv:2608.10444v1 Announce Type: new Abstract: Large language models (LLMs) have made substantial progress on reasoning tasks that require increasingly long and complex inferential chains. This progress primarily…
arXiv:2608.10273v1 Announce Type: new Abstract: Deploying large language models (LLMs) for decision support in emergency departments (EDs) faces two major challenges: privacy risks of transmitting patient data to…
arXiv:2608.05353v2 Announce Type: replace Abstract: LLM judges are often asked to extract criteria and evidence before choosing between candidate answers. This workflow assumes that the intermediate record preserves the…
arXiv:2608.07968v2 Announce Type: replace Abstract: Reasoning language models increasingly use test-time compute to improve performance, but existing evaluations typically study this compute one question at a time. Yet…
arXiv:2606.03793v2 Announce Type: replace Abstract: Multimodal Large Language Models integrate visual perception into language reasoning, introducing a continuous attack surface susceptible to adversarial attacks. Prior…
arXiv:2608.10672v1 Announce Type: cross Abstract: Social interaction has become one of the most common uses of LLMs, yet research on emotional bonds with AI has focused largely on how users experience these systems,…
arXiv:2608.11008v1 Announce Type: new Abstract: Political stance detection in LLMs has long been dominated by closed-ended, multiple-choice political survey questions---originally designed for humans, and thus lacks the…
arXiv:2608.10626v1 Announce Type: new Abstract: Large language models have demonstrated conversational capabilities, yet empathetic competence remains challenging. Empathetic support is inherently multi-turn and…
arXiv:2602.05307v3 Announce Type: replace Abstract: Large reasoning models (LRMs) have demonstrated impressive reasoning capabilities, but their solutions are often verbose and computationally expensive, and taxing for…
arXiv:2608.10743v1 Announce Type: new Abstract: Recent research empowers Large Language Models (LLMs) as multi-turn search agents to iteratively retrieve and generate outputs until complex tasks are solved. However, the…
arXiv:2608.11025v1 Announce Type: new Abstract: Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leading mechanistic…
arXiv:2607.28707v2 Announce Type: replace Abstract: Entropy-based pruning has been proposed as an effective method for compressing Chain-of-Thought (CoT) reasoning with negligible accuracy loss. We test the robustness…
arXiv:2608.10615v1 Announce Type: new Abstract: Discrete diffusion models for categorical generation are defined by a corruption kernel, which determines the intermediate state space and the associated reverse…
arXiv:2608.09934v1 Announce Type: new Abstract: Large language model (LLM) agents improve task performance by decomposing problems into role-specialized behaviors. However, their practical deployment is often limited by…
arXiv:2608.09937v1 Announce Type: new Abstract: Recent work in NLP has probed large language models for their understanding of cultural norms across countries. However, this work typically considers distributional…
arXiv:2503.05061v3 Announce Type: replace Abstract: Reliable evaluation of large language models (LLMs) is critical as their deployment rapidly expands, particularly in high-stakes domains such as business and finance.…
arXiv:2604.05192v2 Announce Type: replace Abstract: Byte Pair Encoding (BPE) is a widely used tokenization algorithm, whose tokens cannot extend across pre-tokenization boundaries, functionally limiting it to…
arXiv:2608.10258v1 Announce Type: new Abstract: Large language models (LLMs) increasingly provide conversational health information that may influence treatment decisions, yet existing benchmarks do not isolate whether…
arXiv:2608.10279v1 Announce Type: cross Abstract: Streaming language-model output creates a release-timing problem: complete-response moderation acts after streamed text has escaped, whereas repeated semantic…
arXiv:2608.10986v1 Announce Type: new Abstract: A growing class of methods probes a language model by feeding it its own output: self-consistency, iterated refinement, agentic loops. We ask what such a probe measures,…
arXiv:2608.10459v1 Announce Type: new Abstract: As LLM-generated content becomes more sophisticated, detection systems for distinguishing those texts from human-written text must operate at scale while handling diverse…
arXiv:2509.23102v4 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) has emerged as the standard paradigm for aligning large language models with human preferences. However,…
arXiv:2604.01418v2 Announce Type: replace Abstract: Thousands of diverse benchmarks have been developed to measure the quality of large language models (LLMs). Yet prior work has demonstrated that LLM performance is…
arXiv:2608.10916v1 Announce Type: new Abstract: Autoformalisation (AF) systems map natural language reasoning steps into formal statements in a proof assistant such as Lean. We consider how to assess the faithfulness of…
arXiv:2608.10875v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mostly use short, self-contained requests in static…
arXiv:2604.16382v2 Announce Type: replace Abstract: Longitudinal NLP tasks such as mental health monitoring and stance evolution require modeling temporally ordered text to track persistence and detect change. Such…
arXiv:2608.10296v1 Announce Type: new Abstract: One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that this is not the case…
arXiv:2608.10692v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as mobile assistants, where a key challenge is leveraging personal information scattered across multiple…
arXiv:2608.10299v1 Announce Type: new Abstract: Agentic systems are increasingly expected to improve after deployment, yet single-entity self-evolution is often bounded by a static learning context, such as fixed tasks…
arXiv:2608.09988v1 Announce Type: cross Abstract: Large language models are increasingly used to read markets, assess risk, and allocate capital. However, reported results for LLM trading agents can be inflated by…
arXiv:2608.10021v1 Announce Type: new Abstract: Self-attention models content-dependent interactions between tokens but does not by itself encode token order. Position encoding addresses this limitation by introducing…
arXiv:2608.10366v1 Announce Type: cross Abstract: Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coordinated use of…
arXiv:2605.02815v2 Announce Type: replace Abstract: Text-to-SQL over large analytical databases requires navigating complex schemas, resolving ambiguous queries, and grounding decisions in actual data. Most current…
arXiv:2608.08868v2 Announce Type: replace Abstract: Many modern AI systems analyze conversational traces to infer aspects of human interaction and state, implicitly assuming that such information is recoverable from…
arXiv:2608.10408v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown strong capabilities in generating visualization code from textual or visual specifications. However, real-world visualization…
arXiv:2607.16057v5 Announce Type: replace Abstract: Large language models (LLMs) are improving rapidly as reflected in benchmark scores, yet these AI benchmarks largely test capabilities such as factual recall, narrow…
arXiv:2608.10716v1 Announce Type: cross Abstract: Speech-to-speech (S2S) voice agents are increasingly being incorporated into enterprise for customer care and as daily companions for consumers owing to the ease of the…
arXiv:2605.11533v3 Announce Type: replace Abstract: Routine clinical check-up reports combine laboratory measurements, physiological assessments, imaging findings and visually structured information, but rarely tell…
arXiv:2608.10670v1 Announce Type: new Abstract: At corpus sizes typical of low-resource dialects, single-run comparisons can yield gains that do not replicate. We show this for Garhwali, an under-resourced Indo-Aryan…
arXiv:2608.10484v1 Announce Type: cross Abstract: Action verbs describe not only the physical outcomes of actions, but also how those actions are performed. Yet action representations in vision-language-action models…
arXiv:2604.13201v2 Announce Type: replace Abstract: Large language models are emerging as scientific assistants, but evaluating their ability to reason from empirical data remains challenging. Benchmarks derived from…
arXiv:2608.11146v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. However, this…
arXiv:2604.23733v2 Announce Type: replace Abstract: Discourse comprehension in complex documents often involves continuously posing and resolving Questions Under Discussion (QUDs). While QUD frameworks have so far…
arXiv:2608.09096v2 Announce Type: replace Abstract: Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is…
arXiv:2604.16706v2 Announce Type: replace-cross Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human…
arXiv:2608.10720v1 Announce Type: cross Abstract: Omni-modal dialogue models can understand multimodal inputs and synthesize spoken replies, yet their responses remain visually disembodied. We introduce…
arXiv:2608.10963v1 Announce Type: new Abstract: We present the REAP system for the AKBC Shared Task 2026 on constructing knowledge bases from language models in a closed-book setting, subject to a budget of at most 32B…
arXiv:2608.10893v1 Announce Type: new Abstract: Certified selective predictors attain whatever coverage they attain; operators impose an automation floor: answer at least a $\beta$-fraction of shifted target traffic…
arXiv:2608.10939v1 Announce Type: new Abstract: Multilingual short-text classification supports operational systems such as content moderation, customer support routing, and intent recognition, yet aggregate evaluation…
arXiv:2608.11030v1 Announce Type: cross Abstract: Patent retrieval and matching based on large language models (LLMs) play a vital role in intellectual property protection. However, due to the complex structure of…
arXiv:2608.10974v1 Announce Type: new Abstract: Scientific papers contain fine-grained records of problem solving: authors mention technical obstacles and methods that were used to address them, often along with…
arXiv:2510.09887v3 Announce Type: replace Abstract: Vision and language models frequently ignore semantically critical input edits, defaulting to pretraining priors. For example, models will confidently assert a…
arXiv:2608.11002v1 Announce Type: new Abstract: Text-to-image (T2I) generation has achieved remarkable progress in recent years. However, existing research has largely focused on English-only settings, leaving…
arXiv:2607.26598v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because…
arXiv:2604.07095v2 Announce Type: replace Abstract: Do multilingual embedding models encode a language-general representation of proficiency? We investigate this by training linear and non-linear probes on hidden-state…
arXiv:2506.03922v4 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains. However, current benchmarks for evaluating MLLMs…
arXiv:2608.10678v1 Announce Type: new Abstract: Chinese web pollution has surfaced in LLMs, motivating audits of upstream Chinese corpora. However, auditing such corpora faces three challenges: (1) their web-scale size…
arXiv:2604.26148v3 Announce Type: replace-cross Abstract: AI agents operating on user interfaces must understand how interfaces communicate state and feedback to act reliably. As a core communicative modality,…
arXiv:2608.10329v1 Announce Type: cross Abstract: Notice-and-comment rulemaking gives any affected party the same formal right to influence federal regulation, but formal access is not substantive capacity to shape rule…
arXiv:2608.10505v1 Announce Type: cross Abstract: Automated radiology report generation is advancing rapidly in response to the shortage of radiologists, yet unlike a perception model, existing generation models offer…
arXiv:2603.20907v5 Announce Type: replace Abstract: As users increasingly turn to LLMs for practical and personal advice, they become vulnerable to subtle steering toward hidden incentives misaligned with their own…
arXiv:2602.24287v2 Announce Type: replace Abstract: In multi-turn conversations, large language models typically condition on the full conversation history: both past user prompts and assistant responses. We revisit…
arXiv:2509.23452v2 Announce Type: replace-cross Abstract: Current text-to-image generation models, even state-of-the-art models, exhibit a significant performance gap when spatial expressions are described from…
arXiv:2604.18401v5 Announce Type: replace Abstract: Reinforcement learning (RL) has become a key technique for improving the agentic capabilities of large language models (LLMs). Although critic-free methods such as…
arXiv:2608.11110v1 Announce Type: new Abstract: When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compares final answers…
arXiv:2604.09874v2 Announce Type: replace Abstract: Simulating how organized groups (e.g., corporations) make decisions (e.g., responding to a competitor's move) is essential for understanding real-world dynamics and…
arXiv:2608.02673v2 Announce Type: replace-cross Abstract: Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a…
arXiv:2608.09941v1 Announce Type: new Abstract: While 4-bit weight quantization is critical for deploying Small Language Models (SLMs) on edge devices, evaluations of the resulting performance degradation-the…
arXiv:2608.06926v1 Announce Type: cross Abstract: Designing autonomous agents that effectively assist human teams hinges on understanding team dynamics, often without task specific knowledge. We present TRIBE, a domain…
arXiv:2607.19364v2 Announce Type: replace-cross Abstract: Activation steering adds a residual-stream direction at inference time, providing lightweight behavioral control without fine-tuning. Sparse autoencoders (SAEs)…
arXiv:2608.10462v1 Announce Type: new Abstract: Large language models (LLMs) are trained on massive and largely undisclosed corpora that may contain copyrighted or privacy-sensitive content. Data contamination detection…
arXiv:2608.08086v2 Announce Type: replace Abstract: Diffusion language models (DLMs) iteratively refine a sequence, allowing earlier predictions to be revised as context evolves. This rollback capability distinguishes…
arXiv:2608.10475v1 Announce Type: cross Abstract: The emergence of language-based AI agents promises to transform the scope of machine economic activity. Instead of just proposing bids or following hard-coded protocols,…
arXiv:2604.26355v5 Announce Type: replace Abstract: Reasoning in Large Language Models incurs significant inference-time compute, yet the token-level information structure of reasoning traces remains underexplored. We…
arXiv:2608.10970v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have demonstrated strong capabilities in generating semantically relevant concepts and relations, making them promising…
arXiv:2608.11191v1 Announce Type: cross Abstract: GUI Visual Grounding is a fundamental capability for GUI agents. Existing models typically freeze their parameters after deployment, limiting their ability to adapt to…
arXiv:2604.02319v3 Announce Type: replace Abstract: When posed with prompts that permit a large number of valid answers, comprehensively generating them is the first step towards satisfying a wide range of users. In…
arXiv:2604.19001v2 Announce Type: replace Abstract: Large reasoning models (LRMs) produce complex, multi-step reasoning traces, yet safety evaluation remains focused on final outputs, overlooking how harm emerges during…
arXiv:2608.11049v1 Announce Type: new Abstract: The rapid growth of social media has created vast amounts of political discourse, which provides valuable opportunities to analyze public opinions and identify different…
arXiv:2608.06110v2 Announce Type: replace-cross Abstract: This paper presents ECHO (Enhanced Care & Health Observer), a locally-deployable conversational health assistant for long-term chronic care management. ECHO…
arXiv:2607.29168v2 Announce Type: replace Abstract: Authorship Verification (AV) represents an important subfield of digital text forensics and addresses the fundamental question of whether two texts were written by the…
arXiv:2606.31087v3 Announce Type: replace Abstract: Few-shot selection typically assumes that reranking retrieved examples always improves performance. We challenge this view by identifying that the expensive reranking…
arXiv:2608.10627v1 Announce Type: new Abstract: Decompose-then-verify pipelines, including FActScore-style fact-checkers and long-form factuality evaluators, first split a passage into atomic claims before checking each…
arXiv:2607.25589v2 Announce Type: replace-cross Abstract: Medical-imaging AI benchmarks combine datasets, DICOM rendering, prompts, provider APIs, automated labels, statistical code, manuscripts, and repository…
arXiv:2608.10806v1 Announce Type: new Abstract: Reliability estimation of large language models is in many cases as crucial as their accuracy, as reliable models are more trustworthy, robust, and suitable for practical…
arXiv:2608.10689v1 Announce Type: cross Abstract: Terminal interfaces to conversational agents report rich internal state (listening, thinking, executing tools, awaiting input, failing) almost entirely through text,…
arXiv:2608.11066v1 Announce Type: cross Abstract: We prove inference-time quantum coordination advantages for specified AI state-tracking tasks. A solver compresses semantic history into a future-accessible boundary…
arXiv:2608.10179v1 Announce Type: new Abstract: A tensor has border rank at most $r$ if it can be written as $T=\lim_{\varepsilon \rightarrow 0} T(\varepsilon)$ where $T(\varepsilon)$ has rank at most $r$ for all…
arXiv:2608.11195v1 Announce Type: cross Abstract: AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how AI…
arXiv:2608.10696v1 Announce Type: new Abstract: Shellsort's best general lower and classical upper bounds differ by an iterated-logarithmic factor. Lower bounds use signed, order-free cancellation, whereas upper bounds…
arXiv:2608.03031v2 Announce Type: replace Abstract: Time series forecasting is fundamental to decision-making in complex systems, where future dynamics are influenced not only by historical observations but also by…
arXiv:2506.13058v2 Announce Type: replace-cross Abstract: Diffusion probabilistic models (DPMs) have demonstrated remarkable success in visual generation. However, their iterative sampling mechanism results in slow…
arXiv:2608.08521v2 Announce Type: replace-cross Abstract: Face recognition systems face two distinct, commonly-separated failure modes: spoofing, where an impostor presents a photograph or video of an authorized user,…
arXiv:2504.11500v3 Announce Type: replace-cross Abstract: Transit Origin-Destination (OD) data are fundamental for optimizing public transit services, yet current collection methods, such as manual surveys,…
arXiv:2607.17188v2 Announce Type: replace Abstract: While test-time scaling improves the problem-solving ability of large reasoning models (LRMs) through additional inference-time computation, it can also exacerbate…
arXiv:2608.11050v1 Announce Type: cross Abstract: Deep learning systems perform mainly within the 2D for a single image domain and take the face as a single-dimension representation, losing sight of the 3D anatomy of…
arXiv:2605.19748v2 Announce Type: replace Abstract: Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation methods based…
arXiv:2608.07440v2 Announce Type: replace Abstract: Agentic coding faces growing problems of affordability and wasted tokens. We introduce Blast Radius, a predictive memory management layer that estimates an incoming…
arXiv:2608.08605v2 Announce Type: replace Abstract: Multi-agent systems (MAS) built on Large Language Models (LLMs) are proliferating rapidly, but their heterogeneous execution traces provide no common basis for…
arXiv:2608.11017v1 Announce Type: cross Abstract: Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state,…
arXiv:2608.10915v1 Announce Type: new Abstract: After an older adult misses a medication dose, a software agent can send another reminder and an embodied agent can bring the medication. Yet neither explains whether the…
arXiv:2608.10471v1 Announce Type: new Abstract: Prompt optimizers automate the search for prompts that improve language-model performance, but existing methods rely on a predefined optimization procedure: the algorithm…
arXiv:2608.10004v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) provide an interpretable framework by grounding predictions in human-understandable concepts, enabling semantic inspection and test-time…
arXiv:2606.00078v2 Announce Type: replace-cross Abstract: Numerous modern applications in signal processing and medical imaging necessitate acquiring high-dimensional signals under tight resource constraints.…
arXiv:2602.13319v2 Announce Type: replace Abstract: Perspective-aware AI requires modeling evolving internal states---goals, emotions, contexts---not merely preferences. Progress is limited by a data bottleneck: digital…
arXiv:2608.10669v1 Announce Type: new Abstract: Large language model (LLM) agents combine language-based reasoning with external tools to perform complex tasks. Adversarial inputs can exploit interactions between the…
arXiv:2608.09696v2 Announce Type: replace Abstract: Predicting the answer to interventional ``what if'' questions --- the outcome of an action never taken --- requires a \emph{mechanistic}, causal model, not a curve…
arXiv:2606.16465v2 Announce Type: replace Abstract: AI agents can now take irreversible actions in operational systems, but agent-caused losses are still not clearly assigned, priced, or transferred. Providers often…
arXiv:2608.10765v1 Announce Type: new Abstract: Recognizing human behavior across levels of abstraction, from atomic actions to long-horizon intentions, requires data annotated along a semantic hierarchy. Large corpora…
arXiv:2608.11080v1 Announce Type: new Abstract: Rail transit systems play a vital role in urban mobility and economic development. As key components of such systems, rail transit stations function as critical transport…
arXiv:2608.10524v1 Announce Type: cross Abstract: Driven by the rapid advancement of vision-language representation learning, Text-based Image Retrieval (TBIR) has made notable progress. However, existing benchmarks are…
arXiv:2608.10932v1 Announce Type: cross Abstract: Understanding camera motion is fundamental to video perception, with applications in spatial intelligence and controllable video generation. Multimodal large language…
arXiv:2608.10676v1 Announce Type: new Abstract: Large language model (LLM)-based search agents answer questions through multi-step interactions with external environments. However, providing complete execution…
arXiv:2603.29418v2 Announce Type: replace-cross Abstract: Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them…
arXiv:2608.10403v1 Announce Type: new Abstract: Reinforcement learning (RL) has shown promising performance in autonomous driving, yet ensuring the safety of online RL policies remains challenging due to insufficient…
arXiv:2608.03699v2 Announce Type: replace Abstract: Persistent memory helps long-term agents retain knowledge, yet a single update error can repeatedly distort future retrieval and reasoning. Most existing systems…
arXiv:2608.10668v1 Announce Type: new Abstract: Temporal knowledge graphs are central to many uses of the Semantic Web, but existing completion methods assume the entities, relation names, and timestamps to be reasoned…
arXiv:2608.10522v1 Announce Type: cross Abstract: While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured…
arXiv:2608.03025v2 Announce Type: replace Abstract: Multimodal named entity recognition (MNER) determines whether each candidate span and entity-type hypothesis is supported by joint textual and visual evidence.…
arXiv:2608.10323v1 Announce Type: new Abstract: Competitive artificial-life systems can rank trained controllers differently under training and ecological evaluation. We present Neuroevolution Arena, a GPU-accelerated…
arXiv:2608.10214v1 Announce Type: new Abstract: Do large language models contain domain-specific parametric shells: concentrated, causally necessary neuron populations whose removal selectively degrades a target domain…
arXiv:2608.10650v1 Announce Type: new Abstract: Reducing the number of focal elements of a mass function is classically driven by an intrinsic distance, such as Jaccard or Jousselme, that keeps the approximation close…
arXiv:2608.10492v1 Announce Type: new Abstract: Large Language Model (LLM)-based simulators often reproduce observable actions but fail to capture the underlying reasoning behind them. In education, where student…
arXiv:2608.07917v2 Announce Type: replace Abstract: Chinese historical documents preserve valuable cultural heritage, but many collections remain accessible only as scanned page images, preventing full-text retrieval,…
arXiv:2602.17162v3 Announce Type: replace Abstract: Genomic Foundation Models (GFMs) typically rely on Masked Language Modeling (MLM) or Next-Token Prediction (NTP) to learn the "Laws of Nature". While effective at…
arXiv:2608.10330v1 Announce Type: new Abstract: AI agents are increasingly being developed to assist humans in various applications, and Large Language Models and other deep network architectures are considered to be…
arXiv:2608.10538v1 Announce Type: new Abstract: Agent skills represent a standardized format for packaging procedural knowledge and domain expertise, serving within agent harness systems as an essential mechanism to…
arXiv:2608.10740v1 Announce Type: new Abstract: Effective research ideation requires moving beyond a static understanding of prior work to trace how research problems and solutions evolve across the literature. Existing…
arXiv:2608.10983v1 Announce Type: cross Abstract: Multi-modal recommenders fuse collaborative signals with item modalities such as text, images, and audio, but the usefulness of each drifts over time and at different…
arXiv:2608.10549v1 Announce Type: new Abstract: Achieving high accuracy in laser-based cutting of optical films requires careful tuning of parameters such as focal length and laser power beam, adjusted according to the…
arXiv:2508.07617v2 Announce Type: replace-cross Abstract: AI has the potential to augment human decision making. However, even high-performing models can produce inaccurate predictions when deployed. These inaccuracies,…
arXiv:2608.09939v1 Announce Type: cross Abstract: Production teams deploying LLM chat agents face a specific quality assurance gap: existing evaluation tools test individual responses or simulate social interactions,…
arXiv:2608.10393v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong capabilities in controlling robots across diverse manipulation tasks. However, their adversarial robustness remains…
arXiv:2608.10153v1 Announce Type: new Abstract: Enterprises are deploying autonomous AI agents faster than they can govern them, and prevailing approaches stretch a single discipline, typically DevSecOps built for…
arXiv:2608.10319v1 Announce Type: cross Abstract: Large language model (LLM)-powered agents have rapidly evolved from code-completion tools into solvers of complex software engineering tasks. As developers collaborate…
arXiv:2608.11006v1 Announce Type: cross Abstract: Governments worldwide have responded to the rapid expansion of AI by publishing national and regional AI strategies. Comparing national and regional AI strategies to…
arXiv:2608.10504v1 Announce Type: new Abstract: As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that systematically…
arXiv:2608.10601v1 Announce Type: cross Abstract: Two instruments of EU digital law place inference at their centre and mean different things by it. Article 3(1) of the AI Act uses the capability to infer…
arXiv:2608.07299v2 Announce Type: replace-cross Abstract: Radiology reports describe clinical observations but do not specify executable segmentation targets. They may contain present, negated, prior,uncertain, or…
arXiv:2605.09089v2 Announce Type: replace-cross Abstract: Digital onboarding and eKYC systems used by banks, fintech platforms, telecom providers, and other third-party services commonly verify users by comparing an…
arXiv:2608.10881v1 Announce Type: new Abstract: The Traveling Salesperson Problem (TSP) is one of the best-known problems in computer science and arises in many engineering applications, such as smart vehicles and…
arXiv:2608.10589v1 Announce Type: cross Abstract: This paper presents $\pi$-SUB, a physics-informed framework for generating synthetic underwater benchmark datasets that bridges the synthetic-to-real gap for Underwater…
arXiv:2605.20173v2 Announce Type: replace Abstract: Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a first-class…
arXiv:2608.10346v1 Announce Type: cross Abstract: Although advancements in face landmark detection (FLD) methods continue to push performance boundaries, they overlook two major functional limitations: (1) different…
arXiv:2608.10579v1 Announce Type: new Abstract: Although existing instruction data selection methods have introduced various metrics, the inherent complexity of real-world datasets makes it impractical for any single…
arXiv:2608.10483v1 Announce Type: new Abstract: Double perovskites (DPs) offer broad compositional tunability, but predicting the space groups (SGs) of stable structures remains difficult because available datasets are…
arXiv:2608.09949v1 Announce Type: new Abstract: This study evaluates the application of Large Language Models (LLMs) in complex biological systems, evolving from data analysis to autonomous, AI-guided experimentation.…
arXiv:2608.10434v1 Announce Type: new Abstract: Machine learning-based Intrusion Detection Systems (IDS) have demonstrated superior performance in securing Unmanned Aerial Vehicle (UAV) networks. However, the…
arXiv:2608.10714v1 Announce Type: cross Abstract: The Organic 6G vision of a network of networks spanning an edge-cloud continuum complemented by non-terrestrial resources requires, to realize its promise, service…
arXiv:2606.12826v2 Announce Type: replace-cross Abstract: Moving instance segmentation (MIS) attracts increasing attention due to its broad applications in traffic surveillance, autonomous driving, and animal tracking.…
arXiv:2608.10171v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has facilitated their ubiquitous integration into various domains, leading to widespread adoption. However, this…
arXiv:2608.10920v1 Announce Type: new Abstract: We introduce IO Factory, an AI-driven framework for simulating information and influence campaigns as fully integrated, traceable processes. The threat of digital…
arXiv:2607.23116v2 Announce Type: replace-cross Abstract: Time-dependent routing recognizes that the same journey can take a different time depending on when it begins. Under duration minimization, even the departure…
arXiv:2605.06772v2 Announce Type: replace Abstract: As large language models (LLMs) show increasing promise on research-level physics reasoning tasks and agentic AI becomes more common, a practical question emerges: How…
arXiv:2608.10448v1 Announce Type: new Abstract: Multimodal emotion recognition in conversation (MERC) requires understanding complex interactions between verbal and non-verbal cues. However, most existing approaches…
arXiv:2608.10382v1 Announce Type: cross Abstract: Universal approximation in reservoir computing is typically associated with a class of reservoirs. We show that universality can be associated with a single reservoir,…
arXiv:2608.11064v1 Announce Type: cross Abstract: Artificial intelligence (AI) has become a powerful approach to solving complex problems in critical domains. Many concerns arise regarding the decision-making process of…
arXiv:2608.10450v1 Announce Type: cross Abstract: Complex software systems develop over timescales that exceed the lifespan of any individual coding agent. Most agentic software systems preserve continuity through…
arXiv:2608.11136v1 Announce Type: new Abstract: Logic Tensor Networks (LTN) provide a neurosymbolic framework in which first-order logic is interpreted through tensor operations, enabling logical constraints to be…
arXiv:2605.27944v2 Announce Type: replace Abstract: With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepfake detection…
arXiv:2602.16481v2 Announce Type: replace Abstract: Causal discovery seeks to uncover causal relations from data, typically represented as causal graphs, and is essential for predicting the effects of interventions.…
arXiv:2505.11146v4 Announce Type: replace-cross Abstract: Fine-grained facial expression transfer from humans to humanoid agents presents a unique pattern recognition challenge due to the significant domain gap between…
arXiv:2608.11022v1 Announce Type: cross Abstract: Model Cards and Data Cards have demonstrated the value of structured, human-readable documentation for machine learning artifacts, capturing their context, parameters,…
arXiv:2608.10327v1 Announce Type: new Abstract: Can AI systems be aligned to human values? The popularization of large language models (LLMs) and multi-modal foundation models has seen a rise in harms spanning from…
arXiv:2605.15850v3 Announce Type: replace-cross Abstract: In recent years, generative AI (GenAI) in educational settings has become ubiquitous in university students' daily lives, despite its potential to induce…
arXiv:2607.04872v2 Announce Type: replace-cross Abstract: Reasoning temporal localization (RTL) requires a model to generate an answer that itself contains the time interval supporting it, coupling high-level reasoning…
arXiv:2512.08240v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) rely on hundreds of visual tokens, leading to high computational and memory costs. Existing compression methods face a trade-off:…
arXiv:2608.11204v1 Announce Type: cross Abstract: Learning reliable surgical manipulation policies is bottlenecked by the scarcity of action-labeled demonstrations: teleoperated surgical robot (e.g., dVRK) trajectories…
arXiv:2608.10339v1 Announce Type: cross Abstract: Hospital quality improvement (QI) programs routinely face multiple candidate interventions to optimize hospital flow, but existing methods struggle to estimate and rank…
arXiv:2608.10525v1 Announce Type: cross Abstract: Historical context integration presents a fundamental challenge for Vision-Language Models (VLMs) in sequential decision-making tasks. Current VLMs process visual inputs…
arXiv:2604.07042v3 Announce Type: replace Abstract: Most research in planning focuses on generating a plan to achieve a desired set of goals. However, a goal specification can also be used to encode a property that…
arXiv:2608.10588v1 Announce Type: cross Abstract: Purpose: Fine-grained handshape recognition supports computational sign-language transcription, recognition, and translation, but broad, phonetically defined visual…
arXiv:2506.01982v5 Announce Type: replace-cross Abstract: This study investigates emotional expression and perception in music performance using computational and neurophysiological methods. The influence of different…
arXiv:2608.10030v1 Announce Type: new Abstract: As AI agents are increasingly deployed in complex environments, understanding their behaviors becomes critical. Yet behavioral scientific research on AI agents remains…
arXiv:2608.10584v1 Announce Type: new Abstract: Scholar assessment plays a fundamental role in faculty recruitment, funding allocation, academic promotion, and talent discovery. Existing scholar assessment methods…
arXiv:2608.10207v1 Announce Type: new Abstract: Bus bunching degrades service regularity and increases passenger waiting in high-frequency transit. Existing reinforcement-learning-based holding controllers primarily…
arXiv:2608.10729v1 Announce Type: cross Abstract: Foundation models can improve their outputs through a self-refinement process driven by external feedback. In this process, the model is embedded in an iterative loop…
arXiv:2608.10513v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) remain vulnerable to jailbreak attacks that exploit visual inputs to bypass safety alignment inherited from their language…
arXiv:2608.10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors durable: a poisoned, stale, or misattributed record can alter…
arXiv:2608.10494v1 Announce Type: new Abstract: Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence. This is challenging because EO…
arXiv:2608.10644v1 Announce Type: new Abstract: Extraction produces candidate entities and relationships; writing them into a graph is where identity is decided, and identity decisions are destructive in a way…
arXiv:2608.08326v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective approach for improving multimodal reasoning. However, most existing methods evaluate…
arXiv:2608.09946v1 Announce Type: cross Abstract: Social service navigation requires connecting help-seeking individuals to resources that satisfy their needs and specific constraints. Although LLM agents offer a…
arXiv:2608.00422v2 Announce Type: replace Abstract: Large language models (LLMs) can generate fluent reasoning traces that nevertheless lead to incorrect answers, making response-level uncertainty estimation important…
arXiv:2608.10790v1 Announce Type: cross Abstract: Deploying modern video trackers at scale is bottlenecked by the computational cost of RGB-based object detectors. To this end, we present MVTrack, an ultrafast tracker…
arXiv:2504.00035v4 Announce Type: replace-cross Abstract: Large language models (LLMs) enable powerful knowledge injection through approaches such as in-context learning and fine-tuning, but they also introduce new…
arXiv:2608.10976v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models can connect scene understanding, semantic reasoning, and trajectory generation for autonomous driving. However, verbose…
arXiv:2608.09971v1 Announce Type: cross Abstract: Over the past few years, the rapid development of machine learning (ML) models for weather forecasting has produced deterministic models whose medium-range skill matches…
arXiv:2608.10295v1 Announce Type: cross Abstract: Frozen foundation-model (FM) embeddings are increasingly used as off-the-shelf brain-MRI representations, on the assumption that they capture anatomy. We audit what they…
arXiv:2608.08311v2 Announce Type: replace-cross Abstract: We present Ouroboros, a self-developing agent harness whose tools, prompts, context assembly, and core implementation improve through reviewed commits that…
arXiv:2608.10545v1 Announce Type: cross Abstract: Edge LLMs must preserve inference continuity when a user hands over between edge nodes, requiring key-value (KV) cache transfer to the target node. However, simultaneous…
arXiv:2608.07556v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) decompose long-horizon tasks across supervisors and subagents, but delegated goals do not necessarily carry their original…
arXiv:2607.21106v3 Announce Type: replace Abstract: Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging. A memory-construction policy decides what information to extract,…
arXiv:2601.10129v2 Announce Type: replace-cross Abstract: Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamics. In this work, we…
arXiv:2208.11582v2 Announce Type: replace-cross Abstract: The wide spread of false information online, including misinformation and disinformation, has become a major problem for our highly digitised and globalised…
arXiv:2608.10928v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning. However, recent studies…
arXiv:2510.09859v5 Announce Type: replace-cross Abstract: A provider sells a \emph{dynamic information service}---a real-time, capacity-constrained process that resolves a customer's uncertainty---to customers who…
arXiv:2608.10237v1 Announce Type: new Abstract: Contrastive learning and Siamese embedding models have become the foundation of modern verification systems, where decisions are governed not by discrete classification…
arXiv:2608.10595v1 Announce Type: cross Abstract: Proteolysis-targeting chimeras (PROTACs) induce protein degradation by recruiting a target protein to an E3 ubiquitin ligase, making degradation a joint outcome of the…
arXiv:2608.10730v1 Announce Type: cross Abstract: The pursuit of artificial general intelligence (AGI) rests on a seemingly self-evident premise: that general intelligence, the kind of flexible, domain-general cognitive…
arXiv:2608.10260v1 Announce Type: new Abstract: Lens methods interpret large language models (LLMs) by mapping intermediate activations to the output vocabulary, revealing how next-token predictions develop through the…
arXiv:2608.10224v1 Announce Type: new Abstract: Enterprise support agents operate in rapidly changing environments where policies, product capabilities, and knowledge bases evolve continuously, making static assistants…
arXiv:2608.10795v1 Announce Type: new Abstract: Successful mutation strategies in evolutionary code search may contain reusable knowledge that is useful beyond a single run, and in some cases may transfer across related…
arXiv:2608.10954v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) demonstrate impressive performance in benign scenarios, their cognitive reliability deteriorates significantly in complex…
arXiv:2608.10427v1 Announce Type: cross Abstract: Scattering matrices are the standard experimental and computational description of photonic and electromagnetic devices. Passivity is explicit in the conventional…
arXiv:2608.10929v1 Announce Type: new Abstract: Cross-domain recommendation (CDR) transfers preference knowledge across related domains, but federated deployment makes cross-domain alignment difficult because the…
arXiv:2608.10773v1 Announce Type: cross Abstract: The increasing use of Generative Artificial Intelligence (GenAI) in journalism raises concerns about possible detrimental effects both on journalism and its democratic…
arXiv:2608.10438v1 Announce Type: new Abstract: Large language models increasingly rely on external tools to access up-to-date information, perform computation, and interact with the outside world. For autoregressive…
arXiv:2608.08020v2 Announce Type: replace Abstract: Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the…
arXiv:2608.10186v1 Announce Type: cross Abstract: LLMs are increasingly deployed in settings that require collective reasoning on complex, value-laden problems. Confidence in these deployments rests largely on…
arXiv:2604.01039v3 Announce Type: replace-cross Abstract: System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational…
arXiv:2608.05224v3 Announce Type: replace Abstract: Large language models fine-tuned on human behavioural data have emerged as general-purpose cognitive proxies, but the scale this requires, and whether these models…
arXiv:2508.03611v3 Announce Type: replace-cross Abstract: This paper presents Astrolabe, a randomized prediction-guided scheduler for one-shot request dispatch in multi-instance large language model (LLM) serving.…
arXiv:2608.10363v1 Announce Type: new Abstract: AI agents can accelerate nutrition research, but their analyses inherit the identity, semantic, and release ambiguities of the underlying data. We present Nutrition Data…
arXiv:2606.17441v2 Announce Type: replace-cross Abstract: Simulating realistic patient interactions is a key requirement to testing clinical applications of LLMs at scale without time-consuming and expensive user…
arXiv:2608.10405v1 Announce Type: cross Abstract: Many studies have shown that specially crafted inputs can induce large language models (LLMs) to generate excessively long outputs, resulting in significant…
arXiv:2608.10836v1 Announce Type: cross Abstract: The signal ambiguity of whispered speech drives ASR systems toward two opposing failure modes: failing to capture whispered speech or hallucinatory transcription of…
arXiv:2606.24112v2 Announce Type: replace Abstract: Multimodal misinformation detection is increasingly important because viral posts now combine long multilingual narratives, several images, mixed provenance, and…
arXiv:2608.10665v1 Announce Type: new Abstract: Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approaches have notable…
arXiv:2608.11079v1 Announce Type: new Abstract: Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated in several…
arXiv:2608.10775v1 Announce Type: new Abstract: Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual controls without…
arXiv:2605.11611v3 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for training agentic retrieval-augmented generation (RAG) systems from…
arXiv:2505.11635v2 Announce Type: cross Abstract: Many real-world tasks, from associative memory to symbolic reasoning, benefit from discrete, structured representations that standard continuous latent models can…
arXiv:2608.10530v1 Announce Type: cross Abstract: Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code…
arXiv:2607.21421v2 Announce Type: replace Abstract: Data-driven generative models can extend partially observed simulation trajectories into ensembles of alternative future scenarios. However, consistency with a learned…
arXiv:2608.10108v1 Announce Type: new Abstract: Long-horizon agents accumulate trajectories spanning hundreds of interleaved reasoning, action, and observation steps, where answering a query may depend on evidence…
arXiv:2608.00961v2 Announce Type: replace-cross Abstract: AI anthropomorphism is typically treated as a problem of user misperception requiring institutional correction. Users who engage in sustained or relational…
arXiv:2608.10375v1 Announce Type: cross Abstract: Volatility control converts risk estimates into portfolio exposure, yet existing approaches often rely on a fixed volatility estimator or a pre-defined control rule that…
arXiv:2608.09944v1 Announce Type: cross Abstract: Modern web interfaces are increasingly difficult to use with screen readers, particularly when pages update dynamically or hide important structure behind visual layout.…
arXiv:2606.09942v3 Announce Type: replace-cross Abstract: Microservice systems are widely used to build cloud applications, yet their complexity makes failures inevitable, degrading user experience and causing economic…
arXiv:2608.10233v1 Announce Type: cross Abstract: Groundwater variability in Ghana remains poorly characterized due to limited long-term in-situ observations. This study investigates groundwater storage anomalies using…
arXiv:2608.10760v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) has become the de-facto interface for connecting LLM agents to enterprise tools, and adoption has been explosive: within a year, large…
arXiv:2608.08594v2 Announce Type: replace Abstract: Diffusion bridge models leverage Doob's \(h\)-transform to construct stochastic transports between arbitrary endpoint distributions, and have shown strong potential in…
arXiv:2608.09273v2 Announce Type: replace Abstract: LLMs have demonstrated strong capabilities in code generation and automated program repair, but migrating an entire repository rarely produces a runnable application…
arXiv:2608.06929v2 Announce Type: replace-cross Abstract: Regional image editing has attracted considerable attention for its spatial controllability. Although instruction-based and mask-reference-based editing methods…
arXiv:2607.23955v3 Announce Type: replace Abstract: Reinforcement learning enables Agentic RAG systems to learn multi-turn search from verifiable outcome rewards, but all- zero rollout groups provide no comparative…
arXiv:2608.10843v1 Announce Type: new Abstract: First-order concept synthesis asks a system to infer one formula that classifies labeled objects consistently across several finite relational structures. Every candidate…
arXiv:2608.10101v1 Announce Type: cross Abstract: Code review is credited with substantially changing a patch's code between its first submission and the version that eventually lands. However, prior work typically…
arXiv:2508.00129v2 Announce Type: replace Abstract: Rank Reversal, where the relative order of alternatives changes in ways that violate axioms of rational decision-making, is a well-documented threat to the reliability…
arXiv:2608.09964v1 Announce Type: cross Abstract: The Brazilian Conference on Intelligent Systems (BRACIS) is the main national venue for Artificial Intelligence research in Brazil, hosted by the Brazilian Computer…
arXiv:2608.10431v1 Announce Type: cross Abstract: Responsible AI (RAI) has become a central concern for technology companies, regulators, and the public. How industry practitioners interpret, implement, and sustain RAI…
arXiv:2603.20990v4 Announce Type: replace-cross Abstract: Hard-negative source selection for dense retrieval is usually decided only after fine-tuning and downstream evaluation. We propose ECIsem, a validity-weighted…
arXiv:2604.01687v3 Announce Type: replace Abstract: Anthropic proposes the concept of skills for LLM agents to tackle multi-step professional tasks that simple tool invocations cannot address. A tool is a single,…
arXiv:2608.11053v1 Announce Type: cross Abstract: The application of computer vision in agriculture has shown significant potential for improving crop monitoring and precision farming. However, many existing approaches…
arXiv:2608.10176v1 Announce Type: new Abstract: Public service chatbots are expected to deliver recommendations from an underlying public service directory, while also making sure that the recommendations respect…
arXiv:2608.10290v1 Announce Type: cross Abstract: Comprendia is an Eclipse plugin that integrates structural dependency visualization with LLM-powered code explanation on a shared interactive graph for Java program…
arXiv:2608.10635v1 Announce Type: cross Abstract: Medical Vision-Language Models (Med-VLMs) excel at verbalizing visual content, yet precise visual perception, segmentation, and grounding remain challenging. Existing…
arXiv:2608.09790v2 Announce Type: replace Abstract: Online credit card discussions provide a natural setting for studying how consumers communicate about financial products. Simulating these discussions requires more…
arXiv:2601.18579v2 Announce Type: replace-cross Abstract: Graph RAG on corpus graphs enhances retrieval by leveraging intermediate node content as contextual clues to uncover unretrieved oracle nodes. However, existing…
arXiv:2608.10239v1 Announce Type: new Abstract: Generative AI makes social-engineering attacks more fluent, adaptive, and scalable, increasing the need for LLM-based de- fenders that can protect users during ongoing…
arXiv:2608.10660v1 Announce Type: cross Abstract: Continuous and reliable localization is essential for autonomous driving. Cross-view visual localization matches ground images with satellite maps, providing…
arXiv:2608.10509v1 Announce Type: new Abstract: Shared memory helps language-model agents reuse information across long workflows, yet relevant evidence may not be admissible for a particular agent or action. Because…
arXiv:2608.09968v1 Announce Type: cross Abstract: Current AI systems are optimized for answering questions; the scientific enterprise is bottlenecked earlier, at discovering the questions worth investigating. We present…
arXiv:2608.10198v1 Announce Type: new Abstract: Latent-space communication allows heterogeneous vision-language model agents to exchange continuous representations without serializing visual and reasoning states into…
arXiv:2608.10166v1 Announce Type: cross Abstract: Digital watermarking has emerged as a critical technique for provenance and copyright attribution in AI-generated imagery, yet its robustness against realistic,…
arXiv:2606.14498v2 Announce Type: replace-cross Abstract: Predicting the Kohn-Sham Hamiltonian with machine learning can accelerate density functional theory while retaining access to molecular orbitals, energy levels,…
arXiv:2607.08970v3 Announce Type: replace-cross Abstract: Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across…
arXiv:2405.03728v3 Announce Type: replace-cross Abstract: Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or with minimal…
arXiv:2607.13738v5 Announce Type: replace-cross Abstract: Attribution maps for echocardiographic ejection-fraction models are evaluated by their overlap with an expert left-ventricular annotation, compared against a…
arXiv:2608.10964v1 Announce Type: cross Abstract: Reinforcement Fine-Tuning (RFT) has enabled medical Multimodal Large Language Models (MLLMs) to produce Chain-of-Thought (CoT) reasoning for visual question answering,…
arXiv:2507.06849v3 Announce Type: replace-cross Abstract: Neural network (NN)-based Digital Predistortion (DPD) improves linearization for wideband radio frequency (RF) power amplifiers (PAs) but often increases the…
arXiv:2509.04009v2 Announce Type: replace-cross Abstract: Due to their powerful feature association capabilities, neural network-based computer vision models have the ability to detect and exploit unintended patterns…
arXiv:2608.10360v1 Announce Type: cross Abstract: Arabic maqam music microtonal, modal, and built on ornamented call and response is among the traditions most underserved by generative music models, whose training…
arXiv:2608.09138v2 Announce Type: replace-cross Abstract: While learned robotic policies hold promise for advancing generalizable manipulation, their practical deployment is often hindered by suboptimal execution…
arXiv:2608.10442v1 Announce Type: cross Abstract: Automatic stress detection from facial video offers a practical path to non-intrusive affect monitoring, yet existing video-based approaches commonly decompose full…
arXiv:2505.23399v2 Announce Type: replace Abstract: We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent…
arXiv:2608.10103v1 Announce Type: cross Abstract: High-performance Tensor Core kernels rely on a low-level PTX pipeline built from asynchronous data movement with cp.async, warp-level matrix loads with ldmatrix, and…
arXiv:2608.10664v1 Announce Type: new Abstract: The Relativity of Causal Knowledge (RCK) explains how a network of agents with different structural causal models can exchange causal knowledge through a shared…
arXiv:2608.10420v1 Announce Type: new Abstract: Reasoning shortcuts are solutions of a neurosymbolic system's rules that produce correct predictions through unintended concepts. A recent framework of Takemura, Inoue,…
arXiv:2608.10807v1 Announce Type: cross Abstract: Age-related Macular Degeneration (AMD) is the major cause of blindness in the Western world. Its late dry phase is characterised by irreversible atrophic areas, namely…
arXiv:2608.06128v3 Announce Type: replace Abstract: Search agents extend large language models beyond static parametric memory by enabling them to acquire and use external evidence during multi-step reasoning. For…
arXiv:2608.10567v1 Announce Type: new Abstract: Analytic dashboards combine coordinated views and interactions for data exploration and decision-making. Recent models can generate them from data and natural-language…
arXiv:2509.03140v2 Announce Type: replace-cross Abstract: We demonstrate that local sensing is sufficient for effective global reconfiguration of homogeneous pivoting cube modular robots in two dimensions. While cube…
arXiv:2604.08991v3 Announce Type: replace-cross Abstract: Reliable embodied interaction in indoor environments requires agents to precisely localize small everyday objects from visual observations. Yet this fundamental…
arXiv:2608.10385v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as relevance assessors in information retrieval (IR) evaluation, raising questions about how assessor framing affects…
arXiv:2608.10989v1 Announce Type: cross Abstract: Token-pruning policies are usually designed for a single recognition pipeline, but pretrained Vision Transformers are reused across tasks with different spatial demands.…
arXiv:2608.10157v1 Announce Type: new Abstract: Self-improving agents seek to reduce the human engineering effort behind AI systems by enabling them to evolve and self-improve their performance over time. Recently,…
arXiv:2608.10827v1 Announce Type: cross Abstract: Medical visual agents can use tools to inspect images and retrieve external knowledge, but indiscriminate tool use may introduce noisy or misleading evidence. Reliable…
arXiv:2608.10805v1 Announce Type: cross Abstract: Wavelet convolution (WTConv) has emerged as an increasingly popular drop-in replacement for standard convolutions, expanding a network's receptive field exponentially…
arXiv:2608.10906v1 Announce Type: cross Abstract: An agent skill is a folder containing a SKILL.md file with instructions for a language-model agent, optionally accompanied by scripts and reference files. The agent…
arXiv:2607.28646v2 Announce Type: cross Abstract: This article analyses narrative mechanisms that are common in dialogues with LLM chatbots. In combination, these mechanisms produce an interactional strategy for…
arXiv:2607.10309v2 Announce Type: replace Abstract: Reinforcement learning (RL) is commonly employed to enhance the performance of autonomous systems, including the Autonomous Internet of Things (AIoT). However, the…
arXiv:2601.03888v5 Announce Type: replace-cross Abstract: In prior work, we introduced IndexTTS 2, a zero-shot neural text-to-speech foundation model comprising two core components: a transformer-based Text-to-Semantic…
arXiv:2608.10447v1 Announce Type: cross Abstract: Large language model-based recommender systems are increasingly adopting slow-thinking models that generate step-by-step reasoning before making predictions, often…
arXiv:2608.09248v2 Announce Type: replace Abstract: Skill-based LLM agents select reusable procedures from an external library to solve complex tasks, yet their routing decisions rely entirely on text-level signals such…
arXiv:2608.10209v1 Announce Type: new Abstract: Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and…
arXiv:2608.10362v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to speculate multiple tokens, reducing expensive…
OpenRouter is the only API you need for AI. Every model, the best uptime and no subscription. Try it free: https://openrouter.ai/?utm_source=fireship&utm_medium=video&utm_campaign=2026-08_dev-sponsorships&utm_content=des…
Hacker News discussion (218 points, 77 comments)
Hacker News discussion (70 points, 63 comments)
MINISFORUM Elite Mini M2 Air-304 is a barebone mini PC powered by an Intel Core 3 304 Wildcat Lake penta-core processor with a DDR5 SO-DIMM slot and an M.2 PCIe Gen4 x4 socket for NVMe SSD storage. There’s currently a…
Regulator hopes for greater financial inclusion, without extra risk or blaming models for bad decisions
Hacker News discussion (251 points, 242 comments)
Hacker News discussion (76 points, 71 comments)
PostgreSQL 17 introduced read streams that combine adjacent disk blocks into larger I/O requests.
Hacker News discussion (84 points, 13 comments)
Hacker News discussion (67 points, 47 comments)
Hacker News discussion (56 points, 75 comments)
FBI Atlanta confirms it's looking into the incident, no arrests made.
Hacker News discussion (574 points, 202 comments)
#661 — August 12, 2026 Web Version 🏖️ We're taking a summer break next week, so the next issue will be on August 26. __ Your editor, Peter Cooper Postgres Weekly Introducing sqlfmt: An SQL gofmt-Style Formatter —…
🗓️ A brief scheduling note: We're taking a summer break next week, so will be back in your inbox on August 26. Catch you then! __ Your editor, Chris Brandrick 🚀 Frontend Focus #754 — August 12, 2026 | Read on the web…
Hacker News discussion (289 points, 296 comments)
https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B-FP8
In this clip from our fireside chat, Dave Morin reflects on evaluating over a thousand companies and explains why OpenClaw stood out. He compares current AI developments to 1997, when the web was first taking off,…
Hacker News discussion (66 points, 80 comments)
Hacker News discussion (70 points, 25 comments)
Hacker News discussion (467 points, 292 comments)
Hacker News discussion (633 points, 102 comments)
Hacker News discussion (187 points, 26 comments)
Hacker News discussion (190 points, 123 comments)
Hacker News discussion (208 points, 45 comments)
Hacker News discussion (609 points, 495 comments)
Hacker News discussion (108 points, 29 comments)
Hacker News discussion (438 points, 117 comments)
Hacker News discussion (189 points, 286 comments)
Woxi is an interpreter for the Wolfram Language written in Rust. It comes with Woxi Studio, a Mathematica-like GUI built with iced, but you can also use Woxi through a CLI, Jupyter kernel, Python package, npm package,…
Hacker News discussion (220 points, 120 comments)
