CORS Chat
Tool: CORS Chat I built this today (with GPT-5.6-Sol xhigh) to help test Qwen 3.8 27B running in LM Studio on both my M5 MacBook Pro and an NVIDIA DGX Spark. It provides a web UI for exercising an…
Daily edition
The daily ledger
TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.
pytorch/pytorch: viable/strict/1786818422: ci: align FlashAttention and CuTeDSL dependencies (#193646)
Human Note split up big ghstack rebase pr into the smaller chunk that rebases quack so we can get ci in better spot Agent note FlashAttention 4 b17 leaves its QuACK and CuTeDSL dependencies open-ended. The B200 setup…
Introducing public preview runtimes on AWS Lambda, starting with Node.js 26 and Python 3.15
AWS Lambda introduces public preview runtimes, a new way to try upcoming language versions before GA. Start using Node.js 26 and Python 3.15 today, provide feedback, and help shape runtime quality before general…
replyfast 0.4.0 is available
Yesterday I released replyfast version 0.4.0, which is a Python module to receive and send messages on Signal You can install it via python3 -m pip install replyfast or uv pip install replyfast I have a script to help…
pytorch/pytorch: viable/strict/1786787633: [CP] Fix FlexCP + load balancing enabled + aot_fx_trace issue (#188766)
Without the fix, TorchTitan graph_trainer + FlexCP with load balancing will trigger the following errors: Without squeeze(0) fix: RuntimeError: Attempting to use FunctionalTensor on its own. Instead, please use it with…
pytorch/pytorch: trunk/53126a784b3327da0a681a42d1613420967af2a2: [CP] Fix FlexCP + load balancing enabled + aot_fx_trace issue (#188766)
Without the fix, TorchTitan graph_trainer + FlexCP with load balancing will trigger the following errors: Without squeeze(0) fix: RuntimeError: Attempting to use FunctionalTensor on its own. Instead, please use it with…
pytorch/pytorch: viable/strict/1786786000: [vllm hash update] update the pinned vllm hash (#193642)
This PR is auto-generated nightly by this action. Update the pinned vllm hash. Pull Request resolved: #193642 Approved by: https://github.com/pytorchbot
pytorch/pytorch: trunk/77b2f6092b1254dc9bbbf5e827c881063907ee42: [vllm hash update] update the pinned vllm hash (#193642)
This PR is auto-generated nightly by this action. Update the pinned vllm hash. Pull Request resolved: #193642 Approved by: https://github.com/pytorchbot
pytorch/pytorch: trunk/8b3301a10f1d99a79717f93dd4a9a6d080f360c1: [MPS] Fix MPSProfiler `stream` arg backward compatibility (#193611)
PR #192525 introduced a BC-breaking change to MPSProfiler functions by adding a new stream argument that is not optional. So other libraries that use those functions, like torchvision, fail to build…
pytorch/pytorch: trunk/9d4b247751531438d45ca34f6a994268a51d8bce: Add merge rule for the Greenlight review bot (#191884)
Impact: PR merge automation / CI only Risk: low What Adds a new Greenlight Review Bot entry to .github/merge_rules.yaml that lets pytorchgreenlight[bot] approve any PR (*), gated on the standard mandatory checks…
pytorch/pytorch: viable/strict/1786784177: Add merge rule for the Greenlight review bot (#191884)
Impact: PR merge automation / CI only Risk: low What Adds a new Greenlight Review Bot entry to .github/merge_rules.yaml that lets pytorchgreenlight[bot] approve any PR (*), gated on the standard mandatory checks…
pytorch/pytorch: trunk/159a07dd4b7e3b234926fb6aaee8a0784b63bc67: Fix typo in LibTorch stable ABI documentation (#193579)
Fixes #193364 Pull Request resolved: #193579 Approved by: https://github.com/malfet
pytorch/pytorch: viable/strict/1786782419: Fix typo in LibTorch stable ABI documentation (#193579)
Fixes #193364 Pull Request resolved: #193579 Approved by: https://github.com/malfet
Northern Gannet
Northern Gannet, in Pillar Point Harbor, CA, US This is Morris. Morris is a local celebrity: the only known Northern Gannet (Morus bassanus) in the entire Pacific Ocean. They showed up in the Farallon Islands off the…
pytorch/pytorch: trunk/2773fe021c50d2a6c0e45376ba23f9538ff5e10e
Revert "[Inductor] Query DeviceInterface for device identity and capa…
pytorch/pytorch: viable/strict/1786777314
Revert "[Inductor] Query DeviceInterface for device identity and capa…
pytorch/pytorch: trunk/31e32c171df8fdca1a8db1d56b5c7e2726252209: flex_gemm: support contiguous transposed reduction outputs (#192661)
Human Note This lets users indicate the stride ordering of the output; this is baically the way to communciate C.T.C . I am going to add this in since its minimilish code and extends the output layout but I might revist…
pytorch/pytorch: viable/strict/1786769835: Add more ops support for functional all_reduce (#190942)
This PR adds premul_sum support for functional all_reduce forward (& backward) by making the reduce_op argument Any in the schema so that we can pass ReduceOp object directly with factor supplement. adds min and max's…
pytorch/pytorch: trunk/83296c3e43ed02cef6184ba879f6a7f08886338f: Add more ops support for functional all_reduce (#190942)
This PR adds premul_sum support for functional all_reduce forward (& backward) by making the reduce_op argument Any in the schema so that we can pass ReduceOp object directly with factor supplement. adds min and max's…
pytorch/pytorch: ciflow/rocm-mi355/193291: [ROCm] Comment cleanup in jiterator reduction acquire fence
Remove empty comment line; fix possessive.
pytorch/pytorch: ciflow/trunk/193291: [ROCm] Comment cleanup in jiterator reduction acquire fence
Remove empty comment line; fix possessive.
pytorch/pytorch: ciflow/rocm-mi350/193291: [ROCm] Comment cleanup in jiterator reduction acquire fence
Remove empty comment line; fix possessive.
pytorch/pytorch: ciflow/trunk/193645
[AI Codemod][PerfAICT-General] Speed up ATen CPU sort by packing (val…
pytorch/pytorch: ciflow/trunk/193644
update vision commit hash
pytorch/pytorch: ciflow/trunk/193643
update torchcomms commit hash
pytorch/pytorch: ciflow/torchtitan/193244
update torchtitan commit hash
pytorch/pytorch: ciflow/trunk/193642
update vllm commit hash
pytorch/pytorch: trunk/55dfacc69b3a9156f68cfe07b61553e4bdc7de29: Auto-label ciflow/b200 on CuTeDSL and DLPack paths (#193605)
CuTeDSL receives its tensors through the DLPack interface, and ciflow/b200 is the only job that runs CuTeDSL. Its label paths are matmul/blas-only, so DLPack and DSL changes get no CuTeDSL coverage pre-merge: #182924…
Episode 66 “JSON API, Valhalla Progress, LTS ❤️ PQC” [IJN]
Work on values progresses, JSON API incubation proposed to target 28, PQC in LTS, and more
Dasturlash tillari: qanday tanlash va afzalliklari
Dasturlash tillari: tanlov va afzalliklar Dasturlash tillari zamonaviy texnologiyalar dunyosida muhim ahamiyatga ega. Har bir dasturlash tili o'ziga xos xususiyatlar, afzalliklar va kamchiliklarga ega bo'lib, turli…
Next.js Image Optimization in 2026: `next/image` v4, AVIF by Default, and the Config Changes Teams Miss
Next.js Image Optimization in 2026: next/image v4, AVIF by Default, and the Config Changes Teams Miss This article was written with the assistance of AI, under human supervision and review. Most Next.js image…
Tự Host LLM Bằng Open WebUI + Docker: Rẻ Hơn ChatGPT Plus?
Originally published on NextFuture Mỗi tháng bạn trả 20 đô cho ChatGPT Plus hoặc Claude Pro, tức khoảng 240 đô một năm — mà vẫn dính rate limit vào giờ cao điểm, dữ liệu prompt bị bên thứ ba giữ lại, và không hề có…
Peeling Fruit with the Power of Steam
Steam power is a staple of the steampunk aesthetic, thermodynamics, and a checkpoint for the budding mechanical engineer studying heat cycles. But because food is largely made of water, steam …read more
Kiến Trúc AI Agent Sống Sót Ở Production: 6 Pattern Cốt Lõi
Originally published on NextFuture Agent bạn build chạy mượt trong 5 lần demo, planning rõ ràng, gọi tool đúng thứ tự. Rồi lên production, nó lặp lại một action lỗi suốt 40 phút, hoặc "nhiệt tình" gửi email cho khách…
Now Karma Bandhana is Adhomukhi and Aatma breath pulse with white glow.
MOKSHA Development Log — 2026-08-15 Repository: weirdcodesofficial/MOKSHA Project Description: An HTML5 browser game based on Sanatan Shastras and Karmic philosophy Language Composition: JavaScript: 89.4% CSS: 6.3%…
Build a Markdown Heading Linter on the AST, Not With Regex
A heading linter sounds like a one-line regex: /^#{1,6}\s+(.+)$/gm It works until a documentation page contains a fenced example: # Real heading ```md ## This is code, not navigation ``` The regex finds two headings. A…
I'm Done Paying for Beautiful.ai — Here's My Free Alternative
I'm Done Paying for Beautiful.ai — Here's My Free Alternative You know the drill. You're prepping for a investor meeting, a pitch competition, or just need to present your startup idea. You open Beautiful.ai, stare at…
Retry budgets by language: Python, Go, and JavaScript
Originally published on Loop & Retry — field notes on building LLM agents that survive production. The retry-budget argument is language-independent: your retry multiplier is set by how you recover, not by how often you…
JWT Authentication in Express That You Can Actually Revoke
Access tokens, refresh token rotation, and theft detection: the parts most Node.js tutorials leave out. A friend messaged me about his side project a few months ago: "Someone else is logged into my account. I changed my…
How I Built a WhatsApp AI Bot That Runs for $0/Month on Windows
I wanted a simple WhatsApp AI bot without paying every month for cloud hosting or an AI API. So I built one that runs on a Windows PC I already have running 24/7. The result: WhatsApp integration with Node.js Optional…
Woman claims her stepfather used Grok to transform childhood photo into explicit imagery
The woman claimed that AI tools are "taking everyday life and turning it into child sexual abuse."
VisionQuest trailer kicks off Disney's D23 fan event
Also: Ahsoka S2 teaser, Doomsday trailer, news about MCU's X-Men and Star Wars: Starfighter.
Payal Singh: The agent is not the system. Postgres is.
The numbers here come from my own audit and design records as of 2026-08-15. Everything described as a redesign is a plan I have started building and have not proven yet. Since June I have been building Looper, an…
Scanning for Lifesigns with ESP32 and Raspberry Pi
It’s a sci-fi trope that you can ‘scan for life signs’ and detect if there are humans — or suspiciously human-shaped aliens — present, but in real life it’s harder …read more
Anthropic shares more details about how Claude’s new watermarks will work
How will the watermarking actually work? Can it be hidden with editing? And how does this affect code?
I Built a Cloud Storage with E2E Encryption — Here Is Why
I Built a Cloud Storage with E2E Encryption — Here Is Why The Problem Every time you upload a file to Google Drive, Dropbox, or OneDrive, your data sits unencrypted on their servers. They can read it, scan it, and use…
Email to Slack: threading, Block Kit limits, and the duplicate-post trap
Start from the mismatch, because every bug in this integration comes out of it. Email hands you a MIME tree, an SMTP envelope, and a Message-ID chain that defines the conversation. Slack hands you a channel, a message…
Top 12 Sites to Buy LinkedIn Accounts with Sales …
Top 12 Sites to Buy LinkedIn Accounts with Sales … We’re available 24/7 to assist you through any channel you prefer: ✅✅✅📩 Email: Smmusapva@gmail.com ✅✅✅💬 Telegram: @Smmusapva ✅✅✅📱 WhatsApp: +1(209)419-4976 LinkedIn…
Storage ByAFR: Cloud Storage Indonesia dengan End-to-End Encryption
Storage ByAFR: Cloud Storage Indonesia dengan E2E Encryption Masalahnya Cloud storage di Indonesia didominasi oleh pemain global seperti Google Drive dan Dropbox. Tapi ada gap: belum ada solusi lokal yang menggabungkan…
The Future of Frontend Development: Building Better Web Experiences
Frontend development has evolved far beyond creating simple web pages. Today, frontend developers are responsible for building fast, accessible, and interactive experiences that connect users with digital products.…
Wagyu Mack & Cheese
This is a submission for Frontend Challenge - Comfort Food Edition, Perfect Landing What I Built I created a comfort food landing page designed to feel warm, welcoming, and personal. The core concept revolves around a…
🍲 Annapurna's Kitchen — Every tiffin has Home's Flavour (Perfect Landing)
This is a submission for Frontend Challenge - Comfort Food Edition, Perfect Landing Tagline: अन्नपूर्णा की रसोई — every tiffin has Home's Flavour 🏠✨ 💡 Inspiration The Challenge asks for a polished, functional landing…
Top 10 Sites for Purchasing Aged Gmail Accounts Safely
Buy Old Gmail Account Management Services – Secure Setup & 2FA | USA Digital Hub 🌟💬 24/7 Premium Support — Always Here for You! 🤝✨ 📱💎 WhatsApp: +1 (506) 541-7768 ✈️🚀 Telegram: @usadigitalhub 🎮🔥 Discord: usadigitalhub 📩💌…
The download button that silently did nothing on mobile
For about a year, the save button in my collage editor did nothing on phones. Not "threw an error." Not "downloaded a corrupted file." Nothing at all. You tapped it, the button got its little active state, and then the…
The Goroutine Awakens: Channeling Your Inner Jedi
The Quest Begins (The “Why”) I still remember the first time I tried to make a Go program do two things at once. I had a web scraper that needed to fetch a dozen URLs, parse the HTML, and stash the results in a…
I pasted a production JWT into a random website. Then I read their privacy policy.
I'd like to tell you this was a one-time lapse. It wasn't. I do it constantly. A JWT to check what's in the payload. A chunk of JSON to pretty-print because the API response came back on one line. A cron expression I…
I Built a Free NDA & Contract Generator for Freelancers (Because Rocket Lawyer Charges $150+/Year)
I Built a Free NDA & Contract Generator for Freelancers (Because Rocket Lawyer Charges $150+/Year) Stop uploading sensitive business information to the cloud just to generate a non-disclosure agreement or freelance…
Radio Shack Toy Returns to Life
[The Modern Rogue] found an old childhood friend in a closet: a Radio Shack 200-in-1 electronic kit. Along with [Josh Nass], he put it through its paces and made a …read more
SpaceX officially closes its Cursor acquisition
AI coding startup Cursor is now officially a part of SpaceX.
How to tell if your AI platforms’ accounts have been hacked
A guide on how to check if hackers have broken into your accounts on the most popular AI platforms.
Ukraine strikes major Russian rocket factory with cruise missiles
"Flamingo missiles were used. A good achievement."
Radim Marek: The curious case of Google's AlloyDB
Google launched AlloyDB in 2022. They claimed it is fully compatible with PostgreSQL. Can be up to 100 times faster for analytical queries than vanilla Postgres. Four years later, I haven't personally seen it gain…
EP222: What is Google’s TPU?
A TPU (Tensor Processing Unit) is Google’s custom AI chip, designed from scratch for the giant matrix multiplications that modern models live on. GPUs were built for graphics first.
Fully Characterized Systems
A friend from my old hackerspace was in grad school for electrical engineering. He had a professor who would ask, when something went wrong with a student project, “Have you …read more
Per-developer environments were the goal. Agents moved the goalposts.
Multi-tenancy has moved in one direction for 60 years: the tenant keeps getting smaller. Mainframe time-sharing carved a single machine The post Per-developer environments were the goal. Agents moved the goalposts.…
Every fusion startup that has raised over $100M
Fusion startups have raised $7.1 billion to date, with the majority of it going to a handful of companies.
DailyJobs - FedEx Jobs - (US) HOT
__https://sites.google.com/view/alislamk/home
If you render user HTML, you have an SSRF problem. Here is the code that fixes it.
Every HTML-to-PDF service has the same shape. Someone hands you markup, you open it in headless Chromium, you print to PDF. If you want Mermaid diagrams or KaTeX math to work, that markup has to be allowed to run…
temporalio/temporal: v1.32.0-162.0-rc.20260815113011
temporalio/temporal version 1.32.0
200+ 5th Grade Trivia Questions and Answers to Test Your Knowledge (And Build a Quiz App)
Are you building a full-stack quiz application, a trivia Discord bot, or a flashcard app? Every quiz engine needs structured data. In this post, we provide a preview of a dataset containing 200+ 5th Grade Trivia…
How to Build an Accessible Toast Notification Component
Most toast components pass a quick visual review and fail every screen reader test, because the accessibility layer usually gets bolted on after the animation and styling are already done. Here's a walkthrough of…
Why ARIA Live Regions Are the Most Skipped Accessibility Feature in Frontend Dev
Run an accessibility audit on almost any dynamic web app and you'll find the same gap: keyboard navigation works, alt text is present, focus states are visible, and then a toast notification fires and nothing happens…
I built an image vectorizer that grades its own homework — and it kept catching me lying
Every image-to-SVG converter I've ever used makes the same promise on its landing page: 100% accuracy. None of them can define what that means, let alone measure it. So I built one that does. It's called Vecline, it's…
So much solar: Digging into the list of every US power plant that went online this year
Utility-scale solar leads by a mile, followed by batteries. Fossil fuels, not so much.
ESP32 Music Sequencer is Clearly Nailing the Y2K Aesthetic
Do you remember back when electronics came in clear cases? Back around the turn of the millennium, when translucency was chic. [3DSage] sure does, which is why he went to …read more
I Built a Free, Dependency-Free Gematria Calculator with Vanilla JS
What is Gematria? Gematria is the ancient practice of assigning numerical values to letters — used for centuries to uncover hidden meanings and connections between words. Every Hebrew letter carries a number (Aleph = 1,…
Presentation: From Models to Agents: Building Context-Aware Consumer AI at Scale at DoorDash
Sudeep Das shares how DoorDash shifts from legacy one-shot predictions to an agentic recommendation platform. He discusses leveraging language-native consumer memory, RQ-VAE semantic IDs for catalog representation, and…
I Built a Free Freelancer Invoice Generator (Because FreshBooks Charges $15-30/Month)
I Built a Free Freelancer Invoice Generator (Because FreshBooks Charges $15-30/Month) Stop paying $15-30/month just to generate invoices. I was tired of FreshBooks' subscription model — another recurring cost for what…
Cloudflare Adds Agent Tracing, with Truncation Limits and Uneven Payload Defaults
Cloudflare launched agent tracing, adding spans for agent invocations, model calls, tool runs, and approvals to existing Workers traces. Sessions replay turn by turn, though the docs warn traces are not lossless and…
Flexible PCB Assembly and Reliability: A Complete Guide to Component Integration, Testing, Failure Analysis, and Long-Term Performance
Introduction Flexible printed circuit boards have become an essential technology in modern electronics. Their ability to bend, fold, and adapt to compact spaces allows manufacturers to create products that are smaller,…
How to handle Lemon Squeezy webhooks in Next.js 16 (the right way)
Lemon Squeezy webhooks look simple until the first payment lands and the upgrade never happens. Or worse, it happens twice. The docs show you the happy path; production shows you the four things the happy path leaves…
Building a High-Performance, Client-Side JSON Diff Checker Using Dynamic Programming (LCS)
Comparing nested JSON configuration files across builds or API revisions is a constant necessity in backend development. While standard text diffing utilities exist, semantic JSON comparison requires robust syntax…
ChainDrop worm crawls into npm supply chain, evades standard defenses
Shai-Hulud variant poisons 444 packages, spreads via tarballs and dev-tool hooks
Java Weekly, Issue 659
Equality in Java is evolving. The post Java Weekly, Issue 659 first appeared on Baeldung.
Gravy Theory: three chickens, one base
This is a submission for Frontend Challenge - Comfort Food Edition Perfect Landing. What I Built Gravy Theory is an interactive field guide to North Indian gravy, built around a single claim: Butter chicken and chicken…
GEEKOM IT13 Max Review – Part 3: Ubuntu 26.04 on an Intel Core Ultra 9 185H mini computer
We’ve already checked out the hardware with an unboxing and a teardown of the GEEKOM IT13 Max in the first part of the review, before testing the Intel Core Ultra 9 185H mini PC with Windows 11, so it’s now time to test…
Lego's supersized Hubble deserves a little more shine
Excellent internal detail cannot entirely disguise some penny-pinching choices
A Tape Deck Gets a Service
If there’s an engineer’s equivalent to those YouTube ASMR videos, then perhaps it comes in a good repair or servicing journey filmed without edits at the bench. Relaxing to watch, …read more
Cloudflare Introduces Cache Response Rules for Post-Origin Cache Control
Cloudflare recently introduced Cache Response Rules, a rules engine that operates after an origin server responds but before content is written to Cloudflare's cache. Previously, Cache Rules operated only on request…
How do you regression-test a ReDoS fix without hanging CI?
A known-bad regex is useful evidence, but putting it directly in the test process can hang the runner before the timeout assertion fires. The boundary I am using: run each adversarial case in a fresh worker thread or…
Your Agent's First Call Has a Byte Problem: UTF-8-Safe OpenAI-Compatible Requests
An AI Agent can pass every local test and still fail on its first real multilingual ticket. The Python client reads café and 上海 correctly, JavaScript returns a slightly different answer, and a PowerShell request…
"Yonaka — A Midnight Ramen Counter"
What I Built Yonaka is a landing page for a midnight ramen counter — an imaginary 12-seat spot that opens after dark. The whole page is built around one idea: a fixed background video that scrubs frame-by-frame as you…
How to Use Cloudflare Workers for Free Hosting
How to Use Cloudflare Workers for Free Hosting tags: javascript, cloudflare, hosting, free tags: javascript, cloudflare, hosting, free tags: javascript, cloudflare, hosting, free tags: javascript, cloudflare, hosting,…
Spicing Up the Web: Building "Angaar", an Immersive Indian Comfort Food Experience
This is a submission for Frontend Challenge - Comfort Food Edition, Perfect Landing What I Built I built Angaar (अंगार) — an immersive, cinematic landing page for a fictional high-end Indian comfort food restaurant.…
JSX - 0 to Hero
key takeaways: Definition: JSX stands for JavaScript XML. It is a syntax extension that allows you to write HTML-like code directly within JavaScript. Role of XML: The "XML" in JSX refers to the ability to define custom…
INAB Eatery
This is a submission for Frontend Challenge - Comfort Food Edition, Perfect Landing What I Built Demo Journey
Twin Guitar-Playing Robots Will Work for Tab
Remember Animusic? They were these incredible animated music videos with original tunes being played by computer-generated robots. Well, the MegCell Pulse might be the coolest robots-playing-music thing we’ve seen since…
I'm Building Free AI on a VM That Barely Qualifies as a Computer
How I am using small models, BM25, RRF, response contracts, relationship validation, recovery loops, and a brutally measured free compute budget to build Scout. I am building an AI system on a budget best described as…
I built 59 free browser-based dev tools in vanilla JS — here's what I learned
I've been quietly building Antigravity Tools — a collection of 59 free, browser-based developer utilities — and today I'm sharing everything I built and learned. Why vanilla JS? No React, no build step. The main…
"Image Optimization: The Complete 2026 Checklist for Faster Websites"
Images are the single biggest performance lever on almost every website. They average over 1MB of every 2MB page — and cutting them down is the fastest way to improve Core Web Vitals and SEO rankings. I've spent the…
Polish Medical Visual Question Answering: Vision-Language Models Underutilize Visual Evidence
arXiv:2608.12928v1 Announce Type: new Abstract: We introduce a Polish-language medical visual question answering (VQA) benchmark, built from Polish Board Certification Examination questions for licensed physicians and…
ReflectFact: Self-Reflective Agents for Improving Comprehension and Reasoning in Multi-Hop Fact Verification
arXiv:2608.12877v1 Announce Type: new Abstract: Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social media yet remains…
Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence
arXiv:2608.12743v1 Announce Type: new Abstract: Spatial intelligence is becoming a foundation for embodied agents, robotic planning, and multimodal assistants. To improve the spatial reasoning ability of VLM agents,…
Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition
arXiv:2608.12327v1 Announce Type: cross Abstract: Multilingual pretrained models nominally support Nepali, yet no controlled benchmark has compared them under a single fine-tuning protocol. We fine-tune six pretrained…
TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes
arXiv:2608.13057v1 Announce Type: cross Abstract: In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU. Dispatchers balance token counts (EPLB, LPLB, UltraEP) or activated-expert counts…
Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds
arXiv:2608.13069v1 Announce Type: new Abstract: Large language models (LLMs) are predominantly aligned to function as passive, sycophantic assistants. We challenge this default paradigm by empirically evaluating the…
Mimicry without understanding: the origins of decision bias in large language models
arXiv:2608.12339v1 Announce Type: cross Abstract: Large Language models (LLMs) were found to be susceptible to a host of social, affective, and cognitive biases. We examined two mechanisms through which such biases can…
Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance
arXiv:2605.18793v3 Announce Type: replace-cross Abstract: Accurate spatiotemporal pattern analysis is critical in fields such as urban traffic, meteorology, and public health monitoring. However, existing methods face…
Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation
arXiv:2608.12880v1 Announce Type: cross Abstract: Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution rows to 180…
Dual Spatial-Temporal Attribution: Architecture-Aligned Post-Hoc Explainability for Recurrent Graph Anomaly Detection
arXiv:2608.12441v1 Announce Type: cross Abstract: Deep learning detectors for anomalies in dynamic graphs have reached strong accuracy, yet they remain opaque: when an edge is flagged, the analyst receives a score but…
AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models
arXiv:2608.13472v1 Announce Type: cross Abstract: Analog circuit design is a time-consuming, iterative process in a nonlinear and high-dimensional design space that relies heavily on expert intuition. Among recent…
Mr3D-VL: A generalist vision language foundation model for Multiparametric 3D Magnetic Resonance Imaging
arXiv:2608.12689v1 Announce Type: cross Abstract: Multi-parametric magnetic resonance imaging (mpMRI) is a cornerstone for brain tumor diagnosis and treatment, yet current AI models face critical limitations: their lack…
TopoIntent: Compiling Security Intent into Executable, Compliance-Checked Network Topologies
arXiv:2608.13389v1 Announce Type: new Abstract: Enterprise security topology design requires translating business intent, regulatory requirements, and risk assumptions into zones, boundary devices, inter-zone paths, and…
A Compositional Theory of Curvature in Probabilistic Circuits
arXiv:2608.12869v1 Announce Type: cross Abstract: Probabilistic Circuits (PCs) are generative models that support exact inference and, unlike deep neural networks, admit an exact and tractable measure of loss-surface…
AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
arXiv:2605.08756v2 Announce Type: replace Abstract: Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs). Recent works show that large…
Trie Automata for Constrained Decoding over Large Finite Sets
arXiv:2608.12574v1 Announce Type: new Abstract: Large language models increasingly need to generate structured outputs that conform to predefined schemas, with one common constraint being selection from a finite set of…
Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs
arXiv:2608.12675v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries. Existing privacy research on RAG…
OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
arXiv:2608.13558v1 Announce Type: new Abstract: Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to…
Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models
arXiv:2608.13258v1 Announce Type: cross Abstract: Self-referential prompting has been shown to reliably induce large language models to produce first-person reports resembling subjective experience, but no prior work…
EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory
arXiv:2608.12627v1 Announce Type: cross Abstract: Long-horizon egocentric memory transforms continuous first-person video and audio into a searchable record of past experiences. We demonstrate two bottlenecks in…
Into the ORBIT for Time Series: Training Regimes for Foundation Models
arXiv:2608.13262v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain…
LipCache: A Local Inference Proxy with Certified Caching for Edge Image Classification Service
arXiv:2608.13144v1 Announce Type: cross Abstract: As edge-side vision services continue to expand toward low-latency, high-throughput scenarios, reducing the inference cost of vision models without sacrificing…
Jointly Predicting Courses and Grades Using a Transformer-Based Model
arXiv:2608.13409v1 Announce Type: new Abstract: Existing predictive models in learning analytics often treat student academic history as a simple sequence, overlooking the concurrent nature of courses taken within a…
Robust Dempster-Shafer Evidence Fusion with Chaos-Conflict Measurement and Historical-Experience Weighting
arXiv:2608.13108v1 Announce Type: new Abstract: Multi-source evidence fusion under Dempster-Shafer theory faces two persistent challenges: existing conflict measures assess inter-evidence inconsistency and…
LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
arXiv:2608.13136v1 Announce Type: cross Abstract: With the rapid advancement of large language models (LLMs), research idea generation has attracted increasing attention. Existing approaches enable LLMs to retrieve…
MindMemOS: A Portable and Self-Evolving Memory Operating Layer for AI Agents
arXiv:2608.12428v1 Announce Type: new Abstract: Memory is a core component of AI agents, enabling them to accumulate experience, maintain personalization, and adapt over long-term interactions. However, existing memory…
Early Warning Signals for OpenVLA Failure under Visual Distribution Shift
arXiv:2606.29699v2 Announce Type: replace-cross Abstract: Visual shifts can cause a vision-language-action policy to fail after initially plausible behavior. We ask whether OpenVLA's internal activations contain signals…
GEM: A Generative Embedding Model Bridging Reasoning and Retrieval
arXiv:2608.13200v1 Announce Type: cross Abstract: Modern LLMs excel at reasoning and instruction following, enabling users to express complex and diverse information needs. However, conventional retrievers largely rely…
Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance
arXiv:2608.12323v1 Announce Type: cross Abstract: Specifying a penalty can paradoxically convert a legal obligation into a cost-benefit calculation that favors violation. We demonstrate that this enforcement information…
EGRL: Edge generation-guided relation-aware learning for RNA-protein interaction prediction
arXiv:2608.12906v1 Announce Type: cross Abstract: RNA-Protein Interactions (RPIs) are critical for regulating cellular functions. While traditional wet-lab experiments for RPI detection are costly and time-consuming,…
Concept Drift Detection and Adaptive Retraining of Malware Classification Models
arXiv:2608.13465v1 Announce Type: cross Abstract: Concept drift refers to changes over time in the statistical properties of data, as compared to the data that was used to train a learning model. Machine learning models…
ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs
arXiv:2608.12788v1 Announce Type: new Abstract: The rapid advancement of Auto-Research has surfaced a fundamental evaluation challenge: how can we measure the alignment, logical coherence, and evolutionary completeness…
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark
arXiv:2608.13555v1 Announce Type: cross Abstract: Humanoid motion tracking is central to teleoperation and whole-body imitation, yet evaluation often disagrees with what people perceive in videos. Kinematic errors…
TsuGO: Probing Search Efficiency in LLM Reasoning via Go Life-and-Death Problems
arXiv:2608.13221v1 Announce Type: new Abstract: The evaluation of LLM reasoning is moving from final-answer accuracy to process-level assessment, yet existing methods still fail to capture how models plan reasoning…
Constitutional On-Policy Safe Distillation
arXiv:2606.03089v3 Announce Type: replace-cross Abstract: On-policy self-distillation (OPSD) has emerged as an efficient post-training paradigm by using a teacher conditioned on privileged information to provide dense…
DiffImaginE: Imagine to Verify Entity Types with Diffusion
arXiv:2608.03025v3 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.…
DAPD: Dual-Anchored Policy Distillation
arXiv:2608.01735v2 Announce Type: replace Abstract: On-policy (self) distillation (OPSD) is increasingly adopted for language-model post-training. It strengthens the teacher with privileged information but can induce a…
The AI Accountability Ecosystem in the Era of Language Models
arXiv:2608.12320v1 Announce Type: cross Abstract: This article reviews and updates the framework for accountability in AI based on account- ability ecosystems. We update the framework in light of the latest developments…
PseudoMapLabeler: Confidence-Aware Pseudo-Label Generation for Semi-Supervised Online Mapping
arXiv:2608.12600v1 Announce Type: cross Abstract: A critical challenge in deploying online HD map construction systems to real-world scenarios is the scarcity of labeled training data, which limits model generalization…
EU-ETS under attack? The impact of carbon price suppression on the decarbonization of the power sector
arXiv:2608.12363v1 Announce Type: cross Abstract: European countries are debating policies to mitigate the increased energy costs caused by renewed geopolitical tensions, while pursuing decarbonization and…
General Probabilities of Causation with Causal Knowledge
arXiv:2608.12657v1 Announce Type: new Abstract: Probabilities of causation (PoCs) characterize individual causal responses that cannot be directly observed and therefore generally require partial identification. Tian…
SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models
arXiv:2605.17985v2 Announce Type: replace-cross Abstract: We propose a new method for compressing physics foundation models (PFMs) which is a new trend in AI for Science. While model compression is essential for…
Sign Language Video Synthesis via Loss-Guided Multi-Expert GANs
arXiv:2608.13368v1 Announce Type: cross Abstract: This preliminary technical report presents a framework for sign language video synthesis using a loss-guided multi-expert Generative Adversarial Network (GAN) to enhance…
DiffGRM: Diffusion-based Generative Recommendation Model
arXiv:2510.21805v2 Announce Type: replace-cross Abstract: Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by…
Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples
arXiv:2608.13341v1 Announce Type: cross Abstract: Infrared (IR) spectroscopy is widely used for chemical sensing, but extracting reliable chemical information from spectra remains challenging. Conventional…
FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation
arXiv:2608.12845v1 Announce Type: cross Abstract: Semantic ID (SID)-based generative recommendation has recently achieved remarkable success. However, existing methods suffer from a previously overlooked fairness issue,…
CEON: Circular Economy Ontology Network
arXiv:2606.02253v2 Announce Type: replace Abstract: Increasing the circularity of resource use in our society has been recognized as a path to sustainability, i.e., transitioning into a more circular economy. There are…
Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review
arXiv:2608.12440v1 Announce Type: cross Abstract: This paper reports a single, fully instrumented case study of a large-scale architectural refactoring by an AI coding agent under a specification-first protocol, with no…
VALG: An Agentic System for ML Theory Research
arXiv:2608.13060v1 Announce Type: new Abstract: Machine learning theory studies learning procedures through mathematical setups in which the data model, training protocol, oracle access, loss, metric, and randomness…
INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification
arXiv:2605.20088v2 Announce Type: replace-cross Abstract: Discovering shapelets -- i.e., discriminative temporal patterns within time series -- has been widely studied to address the inherent complexity of time-series…
Uniform Herding: Exemplar Replay with Representation Refresh
arXiv:2608.13061v1 Announce Type: new Abstract: As the feature representation changes, replay must preserve the earlier classes. However, only a bounded active exemplar set can be replayed. We propose Uniform Herding,…
SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation
arXiv:2606.16454v2 Announce Type: replace-cross Abstract: Low-Rank Adaptation (LoRA) enables efficient adaptation of large pretrained models to downstream tasks by parameterizing weight updates with low-rank matrices.…
What Makes a Peer? Valuation-Anchored Similarity in Private Markets
arXiv:2608.12594v1 Announce Type: cross Abstract: As more investors contemplate private markets and contend with limited transparency, sparse disclosures, and infrequent transactions, identifying economically meaningful…
Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of Gait Detection with Egocentric Vision
arXiv:2608.13283v1 Announce Type: new Abstract: Understanding motion in daily living requires context beyond kinematics, because similar inertial patterns during activities of daily living (ADLs) can reflect intentional…
Training AI Scientists to Replicate Research
arXiv:2608.13331v1 Announce Type: cross Abstract: The replicability of papers is a cornerstone of scientific knowledge, ensuring the reliability of existing results and providing a base for further experiments. The act…
RAIL: An Automatic Classifier of the Artificial Intelligence Readiness Level
arXiv:2608.13428v1 Announce Type: new Abstract: Assessing the maturity of artificial intelligence technologies is essential for investment decisions, project management, and policy monitoring, yet the available…
AI and Consumer Rights in India Working Paper
arXiv:2608.12863v1 Announce Type: new Abstract: As AI systems proliferate in consumer facing applications, questions about liability for AI related harms remain unresolved. This working paper examines whether India's…
Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge
arXiv:2608.12218v2 Announce Type: replace-cross Abstract: Large language models are increasingly trained and deployed with long contexts that span documents, code repositories, and interaction histories. This scaling…
Agent Behavioral Contracts II: Certifying Compositional Reliability Without Assuming Independence
arXiv:2608.12895v1 Announce Type: new Abstract: Compositional reliability bounds for multi-agent systems multiply component reliabilities, a step licensed by a conditional-independence assumption that is routinely…
Unlearning at Scale: State-Exact Trace-Preserving Deletion in Billion-Parameter Language Models
arXiv:2508.12220v2 Announce Type: replace-cross Abstract: Can a prospectively instrumented training continuation reproduce a deletion counterfactual exactly after selected examples leave its replay dataset? We study a…
CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives
arXiv:2608.12779v1 Announce Type: cross Abstract: Understanding the temporal progression of symptoms in clinical narratives is critical for disease monitoring, safety surveillance, and causality assessment. Clinical…
BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving
arXiv:2608.12854v1 Announce Type: cross Abstract: Autonomous driving requires planning under both semantic constraints and predictive dynamics. Existing end-to-end driving approaches, however, typically emphasize only…
Are you Talking Logic to Me? Assessing Language Models Syllogistic Reasoning Capabilities
arXiv:2608.12374v1 Announce Type: cross Abstract: Language models (LMs) struggle with logical tasks like reasoning on syllogisms. It has been shown that Knowledge Representation (KR) plays a crucial role in expressing…
Rules or Character? Scaling Laws for AI Safety Design
arXiv:2608.13345v1 Announce Type: new Abstract: Artificial Intelligence (AI) safety systems combine character shaping (e.g., Reinforcement Learning from Human Feedback [RLHF], Constitutional AI), which modifies…
Sovereign by necessity? Frontier AI export controls, cyber security, and the limits of national AI capability
arXiv:2608.13272v1 Announce Type: new Abstract: A small number of firms based in two states produce the most capable frontier AI models. The governments of those states have shown both the legal power and the political…
Explanatory Engagement Under Rare Anomalous Failure: Asymptotic Rarity in Model Behavior (or: The Asymptotic AI)
arXiv:2608.13063v1 Announce Type: new Abstract: Prior work on LLM behavior under anomalous conditions asks whether a model notices anomalies. We ask a narrower question: once a model sits in a workflow with a low,…
Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories
arXiv:2608.12847v1 Announce Type: new Abstract: Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or…
Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test
arXiv:2608.13228v1 Announce Type: new Abstract: Agent harnesses combine retrieval, routing, state, provenance, and verification, but locally successful components may disagree on shared state. We model this failure with…
Vero: Can AI Agents Build Formally Verified Software Repositories?
arXiv:2608.13522v1 Announce Type: cross Abstract: AI agents are increasingly used for programming, but do not provide any guarantee on the correctness of generated code. Verified code generation, in which an agent…
TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability
arXiv:2608.09538v2 Announce Type: replace-cross Abstract: We introduce TCS-Bench, a benchmark for evaluating Large Language Models (LLMs) on research-level Theoretical Computer Science (TCS) proof generation. TCS-Bench…
Sampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Neural Combinatorial Optimization
arXiv:2608.13087v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) solvers report the best of many sampled solutions per instance, and the sample count is, by convention, identical for every…
Can Generalist Vision Language Models (VLMs) Rival Specialist Medical VLMs? Benchmarking and Strategic Insights
arXiv:2506.17337v5 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown promise in automating image diagnosis and interpretation in clinical settings. However, developing specialist medical…
Learning to Adapt Cross-Domain Preferences via Meta-LoRA for LLM Personalization
arXiv:2608.12389v1 Announce Type: new Abstract: Cross-domain zero- or few-shot personalization aims to generate user-preferred responses in unseen conversational domains from only a handful of target-domain…
H-VAEP and H-xT: Valuing Offensive On-the-Ball Actions in Handball by Estimating Probabilities
arXiv:2608.12926v1 Announce Type: cross Abstract: Traditional player evaluation in professional handball relies on basic box-score metrics or heuristic indices, which fail to credit the multi-player build-up chain.…
Multi-Layer Context Camouflaging: A Semantic Superposition and Contextual Lamination Framework for Malpractice-Resilient Online Assessment
arXiv:2608.13100v1 Announce Type: new Abstract: Contemporary online assessment systems rely primarily on browser lockdown, webcam monitoring, and behavioural analytics, yet remain vulnerable to attacks that extract the…
Keep the Future, Drop the Rollout: RIFT for World Action Models
arXiv:2608.11521v2 Announce Type: replace-cross Abstract: World action models (WAMs) condition robot actions on predicted futures, but iterative video rollout increases deployment latency. We ask whether action…
Annealed Softmax Greedy in Many-Armed Bayesian Bandits
arXiv:2605.31034v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) and group-based policy optimization methods such as GRPO update a stochastic policy by sampling multiple…
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
arXiv:2608.13517v1 Announce Type: cross Abstract: Current large language model development relies on massive, often non-permissible datasets, creating a high barrier for researchers committed to open-source and…
MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
arXiv:2608.13476v1 Announce Type: new Abstract: We present Multi-Agent Reasoning and Coordination (MARC), an open-source framework that replaces monolithic LLM prompting with deterministic multi-agent orchestration for…
Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval
arXiv:2608.12843v1 Announce Type: cross Abstract: Text-based person anomaly retrieval aims to retrieve pedestrians exhibiting anomalous behaviors from a large image gallery using natural language descriptions. Compared…
Measuring Curriculum-Labor Market Alignment at the Scale of a Program Portfolio
arXiv:2608.12356v1 Announce Type: cross Abstract: A college offering several overlapping computing degrees implicitly assumes that its programs are differentiated in line with how the labor market segments computing…
Thought-Aware KV Cache Compaction for Reasoning via Adaptive Attention Matching
arXiv:2608.12331v1 Announce Type: cross Abstract: Reasoning language models generate lengthy chain-of-thought (CoT) sequences whose key-value (KV) cache grows linearly and becomes a memory bottleneck during decoding.…
Time-Series Forecasting in Safety-Critical Environments: An Open-Source Package for EU-AI-Act-Compliant Development / Zeitreihenprognose in sicherheitskritischen Umgebungen: Ein Open-Source-Paket f\"ur die KI-VO-konforme Entwicklung
arXiv:2604.23859v3 Announce Type: replace Abstract: With spotforecast2-safe we present an integrated Compliance-by-Design approach to Python-based point forecasting of time series in safety-critical environments. A…
How Significant Are the Real Performance Gains? An Unbiased Evaluation Framework for GraphRAG
arXiv:2506.06331v2 Announce Type: replace-cross Abstract: By retrieving contexts from knowledge graphs, graph-based retrieval-augmented generation (GraphRAG) enhances large language models (LLMs) to generate quality…
Steering the Language Axis: From Linear Decodability to Causal Control
arXiv:2608.12334v1 Announce Type: cross Abstract: Despite the impressive multilingual capabilities of Large Language Models, the latent dynamics dictating language selection remain poorly understood. In this work, we…
Enhancing Virtual Agents through SLMs and Edge-Computing: An Exploratory Evaluation of Think and Memory Processes
arXiv:2608.13420v1 Announce Type: new Abstract: Embodied intelligent virtual agents are expected to operate as persistent, adaptive, and context-aware entities within complex virtual and Metaverse worlds. However,…
Nutrition Data Infrastructure for the AI Era: Operationalizing FAIR for Agent-Mediated Research
arXiv:2608.10363v2 Announce Type: replace Abstract: AI agents can accelerate nutrition research, but their analyses inherit the identity, semantic, and release ambiguities of the underlying data. We present Nutrition…
DMDIntel: Interpreting Large Language Models via Dynamic Mode Decomposition
arXiv:2608.13048v1 Announce Type: new Abstract: In this work, we introduce DMDIntel which uses dynamic mode decomposition (DMD) to make the predictions made by LLMs in a classification task interpretable. It develops an…
Vision-Language Models are Fragile Multilingual Associators
arXiv:2608.12333v1 Announce Type: cross Abstract: Vision-language models must associate visual entities with textual attributes. Whether these associations or concept bindings remain stable when the language of the…
CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language
arXiv:2603.14501v2 Announce Type: replace-cross Abstract: Large Language Models excel in high-resource programming languages but struggle with low-resource ones. Existing research related to low-resource programming…
Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
arXiv:2608.13160v1 Announce Type: cross Abstract: Multilingual retrieval-augmented generation (mRAG) equips large language models with access to globally distributed external knowledge for complex multilingual question…
Fast and Memory-Efficient Wavelet Convolutions via I/O-Aware Reformulation
arXiv:2608.10805v2 Announce Type: replace-cross Abstract: Wavelet convolution (WTConv) has emerged as an increasingly popular drop-in replacement for standard convolutions, expanding a network's receptive field…
Recursive Synthesis for Long-Horizon Terminal Tasks
arXiv:2608.05466v3 Announce Type: replace Abstract: High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must…
MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification
arXiv:2608.13463v1 Announce Type: cross Abstract: Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty levels. We propose…
Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction
arXiv:2608.12426v1 Announce Type: new Abstract: Large language models are increasingly deployed in settings that require simultaneous adherence to multiple explicit constraints - reasoning structure, safety boundaries,…
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents
arXiv:2608.12977v1 Announce Type: cross Abstract: The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective…
BoardroomAI: Dependency-Aware Human-Steerable Multi-Agent Deliberation through Evolving Decision Graphs
arXiv:2608.13046v1 Announce Type: new Abstract: Organizational decisions are co-created while evidence, constraints, and human priorities continue to evolve. In conventional transcript-based multi-agent systems, humans…
SteerBench-Work: A Benchmark for Agent Steering at Action Boundaries
arXiv:2608.12654v1 Announce Type: new Abstract: Long-running LLM agents act through tools, and a single step can send an email, merge a pull request, or wire a payment. The steering decision is the pre-commit choice at…
Yes, Q-learning Helps Offline In-Context RL
arXiv:2502.17666v5 Announce Type: replace-cross Abstract: Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have…
Unmasking Conversational Bias in AI Multiagent Systems
arXiv:2501.14844v3 Announce Type: replace-cross Abstract: Detecting biases in the outputs produced by generative models is essential to reduce the potential risks associated with their application in critical settings.…
LongEarth-R1: Benchmarking and Aligning Vision-Language Models for Long-Horizon Earth Observation Reasoning
arXiv:2608.13344v1 Announce Type: new Abstract: Long-horizon Earth observation reasoning requires models to organize multi-stage geographic evolution, localize spatial changes, detect temporal anomalies, and infer…
DiG-bench: Discovery in Games
arXiv:2608.12593v1 Announce Type: new Abstract: Discovery---formulating novel generalizations---is a central part of the scientific process. Despite its importance, there is a gap in the current AI benchmark landscape,…
Interpretable Causal Discovery via Causal-Effect Constraints
arXiv:2608.12640v1 Announce Type: cross Abstract: Causal discovery aims to uncover the underlying causal relationships given data generated from a system. The goal, however, is not merely to predict causal edges given…
Not All Nudges Land: Behavioral Controllability and Elaboration Quality in AI-Supported Journaling
arXiv:2608.12582v1 Announce Type: cross Abstract: AI journaling tools can tailor prompts to a person's own sensed behavior, but it is unclear which behaviors respond to them. We analyzed 369 journal entries from an…
LOB-ID: Evaluating Synthetic Market Data by Inception Distances
arXiv:2608.13082v1 Announce Type: cross Abstract: Generative models of limit orderbook (LOB) data have advanced rapidly, but their evaluation often focuses on stylised facts and selected market statistics. These…
Novels generated by language models show compressed formal variation
arXiv:2608.12630v1 Announce Type: cross Abstract: While large language models can generate entire novels, there is little information about the level of formal variation in their output over many generations. Rather…
SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
arXiv:2511.07820v4 Announce Type: replace-cross Abstract: Despite the rise of billion-parameter foundation models trained across thousands of graphical processing units (GPUs), similar scaling gains have not been shown…
Demand Transfer Estimation at Scale via Restricted Logit Modeling
arXiv:2608.12680v1 Announce Type: cross Abstract: Item demand forecasting is an integral component of store assortment optimization. Existing literature focuses on learning a suitable customer choice model and using…
CAPRI: Contract-Aware Proof Repair for Isabelle
arXiv:2608.13459v1 Announce Type: cross Abstract: We address the use of large language models (LLMs) to help discover Isabelle proofs. An Isabelle build establishes that the submitted theory is accepted, but not that an…
Certifiable Semantic Agreement Among LLM Agents: What the Admissibility Instrument Decides
arXiv:2606.07316v2 Announce Type: replace-cross Abstract: Can a committee of LLM agents reach agreement that is certifiable at the level of meaning, not only at the level of a label? We build a protocol to find out.…
Private Etymology: Designing Relational Reuse of Shared Symbols in Long-Term Human-AI Interaction
arXiv:2608.08443v2 Announce Type: replace-cross Abstract: Previous studies have shown that people can develop shared symbols, partner-specific expressions, personal idioms, inside jokes, and other parts of a relational…
Algebraic Decomposition Theory for Transformer Length Generalization
arXiv:2608.13433v1 Announce Type: cross Abstract: Transformer-based language models are known to sometimes generalize to sequences longer than seen during training, but we lack a precise characterization of which tasks…
What Drives LLM Self-Reflection? A Controlled Ablation of Uncertainty Routing in Armed Conflict Forecasting
arXiv:2608.12322v1 Announce Type: cross Abstract: Self-reflection is widely assumed to improve LLM reasoning, yet which component drives the gain remains poorly understood. We present a controlled six-condition ablation…
Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity
arXiv:2608.13484v1 Announce Type: cross Abstract: When asked about entities outside their knowledge boundary, LLMs routinely fabricate plausible-sounding details rather than backing off to safer, more general claims. We…
A Q-learning-based QoS-aware multipath routing protocol in IoMT-based wireless body area network
arXiv:2604.15489v2 Announce Type: replace-cross Abstract: The Internet of Medical Things (IoMT) enables intelligent healthcare services but faces challenges such as dynamic topology, energy constraints, and diverse QoS…
ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
arXiv:2608.12720v1 Announce Type: cross Abstract: While Large Language Model (LLM) agents increasingly rely on long-term memory for persistent interactions, the retrieval mechanisms governing this memory are rarely…
Correct Is Not Governed: Provenance Integrity in Agentic Workflows
arXiv:2608.12761v1 Announce Type: new Abstract: Agentic workflows are commonly evaluated by whether they reach the correct outcome. That is insufficient in institutional settings, where a correct action may rely on the…
Why AI Governance Frameworks Are Hard to Adopt: A Role-Based Stress Test of the NIST AI RMF
arXiv:2608.12352v1 Announce Type: cross Abstract: AI governance frameworks can be known, used, and implemented in form without becoming governance in practice. This paper examines that problem through a role-based…
Architecture Before the Formula: Individuating Neural Architecture Beyond the Composite Map
arXiv:2601.11618v3 Announce Type: replace-cross Abstract: Neural architecture is often identified by module syntax, computation graphs, or the composite functions they realize. These descriptions answer different…
Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks
arXiv:2608.07335v2 Announce Type: replace-cross Abstract: Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms. Notably, the Parallelized Q-Network (PQN)…
PhysMaster: Building an Autonomous AI Physicist for Theoretical and Computational Physics Research
arXiv:2512.19799v2 Announce Type: replace Abstract: Advances in LLM reasoning and tool use have enabled agentic science, yet frontier theoretical and computational physics remains challenging because research requires…
Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing
arXiv:2608.12371v1 Announce Type: new Abstract: Stream-processing systems increasingly operate across heterogeneous mobile edge--cloud infrastructures, where workload volatility, resource contention, and stringent…
TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
arXiv:2608.13167v1 Announce Type: cross Abstract: When visual evidence is occluded or chaotic, models should abstain. In this paper, we show that Vision-Language Models (VLMs) can internally distinguish when abstention…
Do LLMs Know Their Vulnerable Scenarios?
arXiv:2607.23496v2 Announce Type: replace Abstract: Safety-aligned large language models are trained to refuse harmful requests, yet embedding the same requests in particular scenarios can bypass their safeguards.…
REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Models
arXiv:2508.14390v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often express verbal confidence that is poorly aligned with actual correctness, limiting their reliability in safety-critical…
Decomposition of Evidence, Contradiction, and Fragility in Perturbation Responses
arXiv:2608.12935v1 Announce Type: new Abstract: Perturbation methods explain model decisions by measuring prediction changes under altered inputs, but response magnitude tells us only how much a model reacts, not what…
HybridSB-MoE: Dual-Domain Schr\"odinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement
arXiv:2608.12715v1 Announce Type: cross Abstract: Generative speech enhancement faces three gaps: spectral models capture harmonic structure but often disrupt phase, waveform models preserve phase but miss harmonics,…
Learning Latency-Aware Orchestration for Multi-Agent Systems
arXiv:2601.10560v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflows, gaining reasoning power but incurring high inference latency from…
AI Guardrail Survival under Single-Cycle Agentic Self-Summarization
arXiv:2608.11392v2 Announce Type: replace-cross Abstract: Long-running agents periodically compact their context, replacing the transcript with a model-generated summary. Recent work shows that dropping a standing…
Scaling Time Series Classification via XAI-Driven Data Reduction
arXiv:2607.15774v3 Announce Type: replace-cross Abstract: Explainable AI (XAI) for time series has seen significant algorithmic growth, but its utility in providing measurable performance gains for downstream tasks…
CAS: A Causal Attribution Score for Local and Global Explainable Artificial Intelligence
arXiv:2608.12555v1 Announce Type: new Abstract: Predictive explanation methods attribute a model output; they do not, by themselves, attribute an intervention effect on the real-world outcome. We introduce the Causal…
Personalized Scorer Modeling: A Learning-Based Framework for Deriving Robust Sleep Stage Labels from Multiple Experts
arXiv:2608.12446v1 Announce Type: cross Abstract: Sleep stage classification is important for the diagnosis and management of sleep disorders, yet most automatic staging studies evaluate models against a single…
Coordinated incentives in AI-generated misinformation governance
arXiv:2608.07070v2 Announce Type: replace-cross Abstract: With the rapid diffusion of AI-generated content, AI-driven misinformation is becoming increasingly pervasive and difficult to govern, undermining information…
Designing AI Pipelines for Decision-Ready ITSM Intelligence
arXiv:2608.12670v1 Announce Type: new Abstract: IT service management (ITSM) systems accumulate large volumes of heterogeneous ticket data that are difficult for sales and executive stakeholders to convert into…
AgenticCANN: Automated Ascend C Operator Generation via Knowledge-Augmented Agentic Evolution
arXiv:2607.26661v3 Announce Type: replace Abstract: Ascend C operator optimization is critical for NPU (Neural Processing Unit) inference performance but requires deep hardware expertise. While large language models…
Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents
arXiv:2608.13179v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) offers a verifier-bounded performance ceiling for training multi-turn tool-use agents, yet its trajectory-level…
Hamilton-Zero: A Neural Tensor-Network Foundation Model for Ground States of Arbitrary Quadratic Qubit Hamiltonians
arXiv:2608.11911v2 Announce Type: replace-cross Abstract: A central promise of useful quantum advantage is the ability to compute ground states of Hamiltonian systems beyond the reach of classical simulation methods.…
CityRiSE: Reasoning Urban Socio-Economic Status in Large Vision-Language Models via Reinforcement Learning
arXiv:2510.22282v2 Announce Type: replace-cross Abstract: Urban socio-economic sensing plays a vital role in advancing global sustainable development goals. With the advent of Large Vision-Language Models (LVLMs), new…
Alipay-PIBench: A Realistic Payment Integration Benchmark for Coding Agents
arXiv:2607.14573v4 Announce Type: replace Abstract: Payment integration is a demanding repository-level software task: agents must select a suitable product, implement coordinated client-server flows, verify payment…
Position: The Alignment Community is Unintentionally Building a Censor's Toolkit
arXiv:2608.12346v1 Announce Type: new Abstract: This position paper argues that modern AI alignment methods - originally designed to prevent harmful output - are dual-use technologies that may easily be misused by…
Position: Reasoning is a Learnable Rule-Based Process
arXiv:2608.12325v1 Announce Type: new Abstract: Autonomous reasoning is among the most scientifically and economically motivating topics in AI today. Historically the purview of symbolic AI, recent advances have mainly…
In-context superposition: human-like working memory interference in large language models
arXiv:2604.09670v3 Announce Type: replace-cross Abstract: Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments. This capacity, known as working memory, is…
EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory
arXiv:2608.13113v1 Announce Type: cross Abstract: Recent advances in Multimodal Large Language Models (MLLMs) have led to substantial progress in video understanding, accompanied by a growing number of long video…
Dual-Flow Transformers: Decoupling the Primary Prefill Path from Additional Decode Computation
arXiv:2608.12385v1 Announce Type: new Abstract: As large language models serve more requests, cumulative inference cost is becoming increasingly important relative to one-time training cost. The two inference phases…
SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference
arXiv:2608.13076v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable success in natural language understanding and generation, but their deployment is constrained by high computational…
Assessment Design in the GenAI Era: The X1-X2-X3 Assessment Pattern for Testing Students' AI Literacy, Learning Outcomes, and Reflection
arXiv:2608.12351v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI) has challenged the validity of unsupervised online assessment, especially in technical subjects where plausible answers can be…
StateBridge: Training-free Hidden-state Alignment for Latent Communication in LLM Multi-Agent Systems
arXiv:2608.13317v1 Announce Type: new Abstract: Large language model based multi-agent systems usually communicate in text, i.e., using discrete tokens. However, text introduces a discrete bottleneck. Converting the…
Humans are Missing from AI Coding Agent Research
arXiv:2608.12355v1 Announce Type: cross Abstract: Recent progress in AI coding agent research has led to rapid improvements in agents' ability to autonomously perform complex software engineering tasks, from editing…
Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
arXiv:2608.13430v1 Announce Type: cross Abstract: Instruction-tuned language models achieve strong performance across a range of generation tasks, but have also recently been shown to exhibit verbalized overconfidence.…
Lines and Ladders: A Context-Aware Multi-Agent Framework for Large-Scale Retail Price Taxonomy
arXiv:2608.12674v1 Announce Type: new Abstract: Maintaining price consistency and executing an Every Day Low Price strategy is critical for global retailers. However, with catalogs spanning millions of active items,…
SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization
arXiv:2608.12751v1 Announce Type: cross Abstract: Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning…
ContactGuard: Pre-Contact Execution Monitoring with Action-Conditioned Latent World Models
arXiv:2608.13438v1 Announce Type: cross Abstract: Contact-rich manipulation failures are often detected only after the robot has committed to contact. This is especially limiting in wrist-camera setups: close…
QuoteBench: How Matched Scores Can Hide Command-Path Failures
arXiv:2608.13547v1 Announce Type: new Abstract: LLM coding agents issue Bash commands through interfaces that may serialize, wrap, and reparse model output. Matched execution scores alone cannot distinguish…
CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport
arXiv:2608.13226v1 Announce Type: cross Abstract: While 3D Vision-Language Models (3D VLMs) have demonstrated remarkable spatial reasoning capabilities, they suffer from massive visual token counts that create severe…
Jagged Judges: Epistemic Stability Under Silence, Pressure, and Persistence
arXiv:2608.12645v1 Announce Type: new Abstract: LLM judges have become central infrastructure for model evaluations, online grading, and reward modeling. Judges are typically validated by accuracy on golden data, but…
How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures
arXiv:2608.13267v1 Announce Type: cross Abstract: Existing vision-language model (VLM) benchmarks emphasize perception and reasoning accuracy (how well VLMs describe and reason about what they see in an image), with…
Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings
arXiv:2608.13410v1 Announce Type: new Abstract: Parliamentary proceedings are a primary record of democratic deliberation, yet their volume and fragmentation make multi-perspective access difficult for citizens,…
RadarGen: Automotive Radar Point Cloud Generation from Cameras
arXiv:2512.17897v2 Announce Type: replace-cross Abstract: We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient…
Automated Design Optimization via Strategic Search with Large Language Models
arXiv:2511.22651v2 Announce Type: replace-cross Abstract: Optimization methods have long advanced many fields, yet they struggle when faced with design problems where the search space and design parameters are difficult…
AnchorSIPS: A Synthetic Dataset and Evaluation Resource for Evidence-Supported Psychosis-Risk Symptom Measurement
arXiv:2608.12329v1 Announce Type: cross Abstract: Progress on AI for psychosis-risk assessment is limited by a data-access bottleneck. Real clinical interviews are difficult to share because of privacy, governance, and…
Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists
arXiv:2608.12345v1 Announce Type: new Abstract: Language models are increasingly deployed as co-scientists, yet their ability to uphold research integrity under institutional pressure remains unmeasured. We introduce…
Mixture of Training: Recombining Small-Scale Scaffolded Pretraining Runs into a Larger Language Model
arXiv:2608.13277v1 Announce Type: cross Abstract: We ask whether language-model pre-training can be decomposed into smaller, independently trainable jobs that can later be recomposed into a coherent larger model. We…
PatientAct: Theory-Grounded Mental Health Client Simulation
arXiv:2608.12750v1 Announce Type: cross Abstract: LLM-based simulated clients are increasingly used to train novice counselors, evaluate LLM therapists, and generate synthetic data. However, current simulators produce…
Zoom In, Reason Out: Efficient Far-field Anomaly Detection in Expressway Surveillance Videos via Focused VLM Reasoning Guided by Bayesian Inference
arXiv:2604.23724v4 Announce Type: replace-cross Abstract: Expressway video anomaly detection is important for traffic safety, but remains challenging across diverse scenes, particularly for far-field vehicles with…
Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information
arXiv:2608.10766v2 Announce Type: replace Abstract: Explainable Artificial Intelligence (XAI) seeks to explain how an Artificial Intelligence (AI) system arrived at a particular decision. We propose ''Rule of Thumb''…
LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure
arXiv:2608.13545v1 Announce Type: cross Abstract: Modern language models are trained on heterogeneous web-scale text corpora. Consequently, studying knowledge and skill acquisition is difficult, as prior exposure to…
Exploiting Symbolic Heuristics for the Synthesis of Domain-Specific Temporal Planning Guidance using Reinforcement Learning
arXiv:2505.13372v2 Announce Type: replace Abstract: Recent work investigated the use of Reinforcement Learning (RL) for the synthesis of heuristic guidance to improve the performance of temporal planners when a domain…
Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training
arXiv:2607.19058v2 Announce Type: replace-cross Abstract: Optimizer state is the largest single line item in the memory budget of mixture-of-experts (MoE) training. On a 6.78B-parameter MoE language model AdamW keeps…
Identification of Probabilities of Causation: from Recursive to Closed-Form Bounds
arXiv:2505.15274v4 Announce Type: replace Abstract: Probabilities of causation (PoCs) are fundamental quantities for counterfactual analysis and personalized decision making. However, existing analytical results are…
Auditable Agents
arXiv:2604.05485v2 Announce Type: replace Abstract: LLM agents call tools, query databases, delegate tasks, and trigger external side effects. Once an agent system can act in the world, the question is no longer only…
Automatic Termination Strategy of Inelastic Neutron-scattering Measurement Using Bayesian Optimization for Bin-width Selection
arXiv:2603.16946v2 Announce Type: replace-cross Abstract: Currently, an excessive amount of event data is being obtained in four-dimensional inelastic neutron-scattering experiments. A method for automatic bin-width…
Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision
arXiv:2505.12532v3 Announce Type: replace-cross Abstract: Efficiently adapting large pretrained models is critical under tight compute and memory budgets. While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA…
Falsehood and Impossibility Are Different Directions in an AI's Representation of Language
arXiv:2608.12852v1 Announce Type: cross Abstract: Language can describe states of affairs that are false and states of affairs that could not be the case at all. Whether an AI model internally distinguishes these…
Research Assistant: AstraZeneca's Agentic System for R&D
arXiv:2608.12395v1 Announce Type: new Abstract: We describe Research Assistant, an internal LLM-based system developed at AstraZeneca to help scientists and clinicians explore biomedical questions across a broad range…
GeoCache: Training-Free Acceleration of Multi-View Texture Diffusion via Geometric Delta Transport
arXiv:2608.13255v1 Announce Type: cross Abstract: Geometry-conditioned multi-view diffusion enables high-quality 3D texture generation, but its repeated per-view denoiser evaluations introduce substantial computational…
Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement
arXiv:2608.13129v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong results on mathematical reasoning benchmarks yet remain unreliable on elementary numerical tasks, including magnitude…
NAS-Driven Hardware Accelerator Exploration for Edge AI and Quantization Effects on the Pareto Space
arXiv:2608.13293v1 Announce Type: new Abstract: Edge AI deployment demands neural architectures that are simultaneously accurate, computationally efficient, and hardware-deployable - a challenge addressed by…
Governed Persistent Memory: Source-Bound State Semantics and Fail-Closed Release for Long-Horizon Agents
arXiv:2608.12476v1 Announce Type: new Abstract: Long-term agent memory is usually treated as select--store--retrieve, but retrieval does not decide whether contradictory, superseded, retracted, deleted, or stale records…
Interaction Readiness: A Framework for Building and Evaluating AI Agents in Human Roles
arXiv:2608.12358v1 Announce Type: cross Abstract: Product and engineering teams building role-bearing AI agents face an evaluation gap: an agent can produce accurate, safe, and fluent content while still failing the…
Governing Agentic AI in FinTech
arXiv:2608.11344v2 Announce Type: replace-cross Abstract: Financial institutions are delegating consequential decisions to agentic AI systems that decompose goals, coordinate models and tools, and act with little…
Generative Universal Multimodal Retrieval with Dual-role Identifiers
arXiv:2608.12987v1 Announce Type: cross Abstract: Generative information retrieval (GIR) has emerged as a compelling alternative to the conventional index-retrieve-then-rank retrieval pipeline by training a generator to…
From Observation to Intervention: Memory in Brains and Large Language Models
arXiv:2608.12377v1 Announce Type: cross Abstract: Brains and large language models (LLMs) are fundamentally different memory systems, but they can be compared through shared functional questions: where memory-related…
AQuA: Recursively Self-Improving Quantitative Trading Research Agents
arXiv:2608.12841v1 Announce Type: cross Abstract: We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier experiments to improve…
It's How You Ask: Gender-Associated Linguistic Bias in LLMs
arXiv:2608.13328v1 Announce Type: cross Abstract: Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more…
Operationalizing Cyber Threat Intelligence with GraphRAG
arXiv:2608.13050v1 Announce Type: cross Abstract: When a security researcher publishes a report on a cyberattack, detection engineers are supposed to turn it into working detection rules. In practice, most automated…
Moral Hazard in Multi-Agent Language Models
arXiv:2607.23982v4 Announce Type: replace-cross Abstract: Cooperation can fail when socially valuable effort is costly, hard to observe, and benefits mainly someone else. Building on Holmstr\"om's model of moral hazard…
Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures
arXiv:2607.22699v2 Announce Type: replace Abstract: As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond…
A Distributional Robustness Margin For Pathology Foundation Models
arXiv:2607.25497v2 Announce Type: replace-cross Abstract: Pathology foundation models encode non-biological variation introduced by tissue preparation, staining and scanning, enabling shortcut learning that undermines…
Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study
arXiv:2608.03172v3 Announce Type: replace Abstract: Structure-preserving de-identification replaces protected health information (PHI) with realistic same-type surrogates -- "Anna S." becomes "Maria S.", not [NAME] --…
SSPO: Structure-Aware Similarity-Weighted Preference Optimization for Neural Combinatorial Optimization
arXiv:2608.12443v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) relies on parallel solution sampling for training, yet existing methods fail to fully exploit the rich information latent in a…
Cueless EEG imagined speech for subject identification: dataset and benchmarks
arXiv:2501.09700v2 Announce Type: replace-cross Abstract: Electroencephalogram (EEG) signals have emerged as a promising modality for biometric identification. While previous studies have explored the use of imagined…
Gradual Code-Switching as Inference-Time Cross-Lingual Representational Alignment for LLMs
arXiv:2510.05678v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have achieved notable progress in multilingual settings, their performance remains uneven across languages as LLMs often rely…
A Unifying Perspective on Causal World Models: From Observations to Representations to Structure
arXiv:2608.13456v1 Announce Type: new Abstract: World Models (WM) are increasingly seen as a foundation for intelligent agents that can predict, plan, and act beyond their training distribution. In this paper, we study…
Synthetic Persona Pretraining: Alignment from Token Zero
arXiv:2608.13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and…
Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
arXiv:2608.12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is…
iARCS: Iterative Agentic RL for Controllable 3D Scene Generation
arXiv:2608.06161v2 Announce Type: replace Abstract: Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism…
Communication Heterogeneity and Collective Consensus in Neural Cellular Automata
arXiv:2606.21202v2 Announce Type: replace-cross Abstract: Reaching global agreement from purely local interactions is a defining problem of collective intelligence, and most models of it assume that all agents share a…
SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback
arXiv:2608.13120v1 Announce Type: new Abstract: Agent Skills are today either hand-authored or produced in a single LLM generation pass, and consequently possess no closed loop through which they might improve from the…
Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces
arXiv:2608.12585v1 Announce Type: new Abstract: Improving reasoning LLMs requires the ability to judge the quality of long reasoning traces for effective reasoning data curation, strong training signals during…
NaviDC-OCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
arXiv:2608.12898v1 Announce Type: cross Abstract: Document parsing aims to transform unstructured documents into structured and machine-readable representations. Recent advances in Vision-Language Models (VLMs) have…
Physics-informed distribution of relaxation times estimation and latent-space condition monitoring of solid oxide fuel and electrolysis cells from electrochemical impedance spectroscopy
arXiv:2608.13305v1 Announce Type: cross Abstract: Estimating the distribution of relaxation times (DRT) fromelectrochemical impedance spectroscopy (EIS) is an ill-posed inverse problem that is highly sensitive to…
Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design
arXiv:2603.08322v2 Announce Type: replace Abstract: We study mathematical discovery through the lens of neurosymbolic reasoning, where an AI agent powered by a large language model (LLM), coupled with symbolic…
Long-Horizon AI Research for Grothendieck Constant: A Case Study in Human-AI Mathematical Collaboration
arXiv:2608.11195v2 Announce Type: replace 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…
$\varepsilon$-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Program Evolution
arXiv:2608.12522v1 Announce Type: new Abstract: LLM-based program evolution systems such as FunSearch and AlphaEvolve have shown strong ability to discover novel algorithms, but typically optimize each task in…
StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
arXiv:2510.06200v4 Announce Type: replace-cross Abstract: Current time series foundation model (TSFM) training corpora largely omit data with certain complexities like irregular temporal sampling. Astronomical time…
NARU: A Benchmark for NARrative Evolution and Cultural Nuance Understanding in Japanese Extreme Long Video
arXiv:2608.13210v1 Announce Type: cross Abstract: Long-form video understanding encompasses tasks that go beyond retrieving isolated events, including tracking an evolving narrative and interpreting social meaning that…
Large-scale Testing Global Optimization Methods with Black-box Adversarial Attacks
arXiv:2608.13296v1 Announce Type: cross Abstract: Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s. This…
SPARED: Reasoning-Based AI-Generated Image Detection via Adversarially Edited Data
arXiv:2608.12876v1 Announce Type: cross Abstract: Detecting AI-generated images is only half the task: a deployed detector must also justify its verdict, yet existing detectors inherit three failure modes from their…
Train, Test, Re-evaluate: Schedule-Sensitive Evaluation of Generative Data for Hand Detection
arXiv:2606.01896v2 Announce Type: replace-cross Abstract: Generated (or synthetic) image data is increasingly used to augment or replace real training datasets when target imagery is scarce, expensive, or biased. For…
Enhancing In-Hospital Mortality Prediction Using Multi-Representational Learning with LLM-Generated Expert Summaries
arXiv:2411.16818v2 Announce Type: replace-cross Abstract: To evaluate a multi-representational framework in which large language model (LLM)-generated expert summaries of intensive care unit (ICU) notes are fused with…
Cat-DPO: Category-Adaptive Safety Alignment
arXiv:2604.17299v3 Announce Type: replace-cross Abstract: Aligning large language models with human preferences must balance two competing goals: responding helpfully to legitimate requests and reliably refusing harmful…
From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction
arXiv:2604.27906v3 Announce Type: replace Abstract: Persistent AI memory is often reduced to a retrieval problem: store prior interactions as text, embed them, and ask the model to recover relevant context later. This…
Don't Want Your LLM to Recommend Nuclear Strike? Try Asking It in Japanese
arXiv:2608.12373v1 Announce Type: new Abstract: Large language models are increasingly used in strategic and advisory contexts, yet their safety alignment is typically evaluated in English only. We test nine models from…
Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models
arXiv:2608.12391v1 Announce Type: cross Abstract: Graph reasoning provides a promising testbed for evaluating the reasoning ability of large language models (LLMs), as graph instances can be programmatically generated,…
Residual Modeling for High-Fidelity Learned Compression of Scientific Data
arXiv:2606.05389v2 Announce Type: replace Abstract: Lossy compression is essential for massive spatiotemporal data from scientific simulations. Learned compressors can achieve high compression ratios at moderate…
Erase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimized Semantic Anchors
arXiv:2608.12806v1 Announce Type: cross Abstract: The exceptional generation capabilities of text-to-image diffusion models have raised copyright concerns, particularly the unauthorized reproduction of animation…
LLM-Based Test Oracles: Source-of-Authority Taxonomy -- A Systematic Literature Review
arXiv:2607.05031v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly decide whether software behaves correctly, either by writing a test oracle or by acting as one. Yet two oracles can…
UniTexture: Cross-Task Universal Adversarial Textures for Vision-Language-Action Models
arXiv:2608.13453v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wide range of…
OEIS Open: How many conjectures can language models turn into theorems?
arXiv:2608.11941v2 Announce Type: replace Abstract: We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al. Whereas these conjectures had…
Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
arXiv:2606.00367v2 Announce Type: replace-cross Abstract: Reinforcement learning with scalar rewards is widely used for aligning machine-learning systems with user preferences. But, pairwise preferences are often more…
UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations
arXiv:2608.13031v1 Announce Type: cross Abstract: Traffic video understanding has become an important problem in intelligent transportation, as road videos provide direct evidence for accidents, violations, and…
PIPES: Securing Agent Perception with Provenance and Priors
arXiv:2608.12789v1 Announce Type: cross Abstract: Tool-using agents consume external data from sources with different levels of trust, yet tool responses rarely identify who produced each component or what it should…
OGR-MARL: Option-Guided Residual Multi-Agent Reinforcement Learning for Heterogeneous USV Cooperative Pursuit in Constrained Port Waterways
arXiv:2608.12995v1 Announce Type: new Abstract: Heterogeneous USV cooperative pursuit in constrained port waterways requires evader interception under navigation, traffic, and role constraints. This paper proposes…
InFactPlanner: Planning Sustainable Geo-Distributed LLM Data Centers
arXiv:2608.12915v1 Announce Type: cross Abstract: The rapid growth of LLM inference is shifting sustainability concerns from one-time training to continuous serving, where infrastructure decisions shape energy use,…
Static analysis-guided agentic AI translation enables Rust as a full stack bioinformatics language
arXiv:2608.13029v1 Announce Type: cross Abstract: The field of bioinformatics struggles with legacy code - old code that is commonly used but may no longer have a maintainer, or may be written in an now-unfamiliar…
Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents
arXiv:2608.12851v1 Announce Type: new Abstract: Self-improving LLM agents convert successful trajectories into persistent cross-task state. An unsafe success can thereby become reusable policy after its triggering input…
Heterogeneity-Aware Belief Synchronization for Semantic Communication in AI-Native 6G Networks
arXiv:2608.13394v1 Announce Type: cross Abstract: 6G networks will not be serving as communication infrastructures only; rather, they are expected to evolve into intelligent systems, where thousands of autonomous…
MatchMiner-AI: Open-source, Privacy-preserving Cancer Clinical Trial Matching using Artificial Intelligence
arXiv:2412.17228v4 Announce Type: replace Abstract: Background: Clinical trials are essential to advancing cancer treatments, but fewer than 10% of adults with cancer enroll in therapeutic trials. Open-source AI trial…
The Hidden Evolution of Disguised Visual Context inside the VLM
arXiv:2606.20077v2 Announce Type: replace-cross Abstract: Visual tokens enter Large Language Models (LLMs) as raw, foreign signals. How they are transformed into meaningful representations and interact with the language…
Deliberate Practice: Learning Robot Skills under a Budget
arXiv:2608.13415v1 Announce Type: cross Abstract: We consider the problem of autonomously learning robot skills under a limited practice budget for sequential tasks. We propose an active skill learning algorithm,…
REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation
arXiv:2608.11698v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) trains a student on its own trajectories under dense token-level supervision from a teacher. Reward-extrapolation methods such as…
Reduced Matrix Multiplication: Input-Adaptive Matrix-Product Reduction for LLM Inference
arXiv:2608.13426v1 Announce Type: cross Abstract: Transformer-based language models achieve strong performance but incur substantial inference cost due to repeated high-dimensional matrix multiplications. We propose…
From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
arXiv:2608.12836v1 Announce Type: cross Abstract: Large language models often fail when answer options require combining atomic judgments under explicit logical operators, even when they judge the individual atoms…
Short-term load forecasting under EU-AI Act Requirements in Safety-Critical Environments: Results from a 41-day live challenge on the aggregated German transmission-grid load
arXiv:2608.05018v3 Announce Type: replace Abstract: Short-term load forecasting (STLF) plays a vital role in the electric power industry. It is relevant for critical infrastructure. STLF is no longer purely a…
FluctlightDB: A Memory Model of Data for AI Agents
arXiv:2608.12365v1 Announce Type: cross Abstract: For fifty years, data systems have answered two questions. The relational model asked which records match a predicate; the vector model asked which vectors lie nearest a…
Agreement Is Not Alignment: Divergent Moral Grounds in Human and LLM Ethical Judgments
arXiv:2608.12368v1 Announce Type: new Abstract: Agreement with human judgments is a common proxy for evaluating the alignment of large language models (LLMs). Yet agreement in final labels does not show that human…
SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
arXiv:2607.27431v4 Announce Type: replace-cross Abstract: Generative modeling of protein backbones promises the de novo design of proteins with prescribed structural and functional properties. Existing diffusion and…
Vibe to Code: Elucidating Strategic Oscillation of Tacit Knowledge in Generative AI Design Workflows -- An Exploratory Qualitative Study
arXiv:2607.23126v2 Announce Type: replace-cross Abstract: The rapid adoption of generative AI tools has created new literacy demands for designers who must verbalize tacit knowledge through natural language prompts. Yet…
MBA: Multimodal Benchmark and Agents for Real-World Business Ideation
arXiv:2608.11616v2 Announce Type: replace Abstract: Agentic systems powered by large language models (LLMs) have opened new opportunities for business ideation. Yet existing approaches remain confined to a text-only…
Learning to Recover Task Experts from a Multi-Task Merged Model
arXiv:2606.26902v2 Announce Type: replace Abstract: Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter interference.…
Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks
arXiv:2608.12713v1 Announce Type: cross Abstract: Watermarking LLM-generated text is an important task for tracing its provenance. Existing LLM watermarks preserve provenance under editing, but this same robustness…
StorySpark: Module-wise Evolutionary Search for Story Premise Generation
arXiv:2608.12336v1 Announce Type: cross Abstract: A story premise is the creative spark from which a full narrative can grow. Yet LLM-based story generation has mostly emphasized later-stage planning, controllability,…
Rethinking Normalization Placement for LLMs: Post-Norm under Curriculum Depth Growing
arXiv:2608.13156v1 Announce Type: new Abstract: Pre-norm is the standard normalization placement in modern Transformers because it facilitates joint optimization of full-depth models. We ask whether this preference…
Safe Exploration via Policy Priors
arXiv:2601.19612v4 Announce Type: replace-cross Abstract: Safe exploration is a key requirement for reinforcement learning (RL) agents to learn and adapt online, beyond controlled (e.g. simulated) environments. In this…
Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks
arXiv:2608.12597v1 Announce Type: cross Abstract: Neural networks can often be trained or fine-tuned through random low-dimensional reparameterization, where a small latent vector is mapped into a full parameter update…
Follow the Norm: Accounting for Fine-Tuning and Prompt Effects on Model Rationales
arXiv:2608.13250v1 Announce Type: cross Abstract: Normative datasets are often used to train and align AI systems, but the norms they contain can function as action-guiding patterns rather than neutral moral knowledge.…
LLM-Guided Graph Generation for Structure-Based Local Improvement Methods
arXiv:2608.13333v1 Announce Type: new Abstract: Large neighborhood search normally selects a random subset of decision variables for iterative optimization. For efficiently solving different problems, researchers tend…
SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents
arXiv:2608.13173v1 Announce Type: new Abstract: Agent skills are crucial external instructions that enable language agents to execute long procedural tasks such as coding or document processing. Existing agent skills…
PROVE-RT: Generating Mechanized Theorem Prover Scripts for Real-Time Systems using LLMs
arXiv:2608.12762v1 Announce Type: new Abstract: Schedulability analysis is essential for certifying real-time systems, but existing tests are often developed through pen-and-paper proofs that are difficult to scale,…
From Caveman to Expert Analyst: Energy Consumption of Variable LLM Tasks
arXiv:2608.12350v1 Announce Type: cross Abstract: The energy demand growth and environmental impacts of artificial intelligence (AI) have generated substantial interest in supplying sufficient low-cost electricity for…
Do Transformers Need Three Projections? Systematic Study of QKV Variants
arXiv:2606.04032v3 Announce Type: replace-cross Abstract: Transformers have become the standard solution for various AI tasks, with the query, key, and value (QKV) attention formulation playing a central role. However,…
Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting
arXiv:2608.12590v1 Announce Type: new Abstract: Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation…
Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking
arXiv:2605.18852v2 Announce Type: replace-cross Abstract: Selecting a final checkpoint for multimodal large language models (MLLMs) is challenging when late-stage candidates are closely matched and downstream evaluation…
The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use
arXiv:2608.12959v1 Announce Type: cross Abstract: Latent world models are judged by how well they predict, so when planning fails at long horizons the natural reading is that the predictor degrades. On a reproduction of…
On the Expressive Power of Transformers
arXiv:2608.12671v1 Announce Type: new Abstract: Multi-layer transformers form the critical component of essentially all large language models (LLMs) in use today. Because of their ubiquity and computational capability,…
The Impact of Generative AI on Collaborative Open-Source Software Development: Evidence from GitHub Copilot
arXiv:2410.02091v4 Announce Type: replace-cross Abstract: Generative artificial intelligence (AI) facilitates content production and enhances ideation, with potentially important implications for developer productivity…
Beyond the Best Guess: Improving LLM Solution Coverage with Evolution Strategies
arXiv:2608.12679v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in discovery domains such as math and science. The usual approach is to present the problem to the model and use its…
StreamReason-Bench: Can Large Language Models Reason about Event-Time Stream-Processing Semantics?
arXiv:2608.12348v1 Announce Type: cross Abstract: Streaming systems increasingly hand work to large language models (LLMs) -- writing pipelines, triaging alerts, reading logs -- and all of it assumes the model knows how…
AlayaWorld: Interactive Long-Horizon World Modeling - Full Technical Report (v1.1)
arXiv:2608.13492v1 Announce Type: new Abstract: This report presents an improved version of AlayaWorld. While the backbone architecture, chunk-wise autoregressive generation scheme, and training data remain unchanged…
SchemaLink: An Intelligent Web Editor for LinkML Schema Curation
arXiv:2608.12529v1 Announce Type: cross Abstract: Motivation: LinkML is a suitable language for the representation of the structural and content constraints of different kinds of biomedical data. Even if it is a quite…
AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
arXiv:2608.13560v1 Announce Type: cross Abstract: Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a…
FlashDrive: Flash Vision-Language-Action Inference for Autonomous Driving
arXiv:2608.12932v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models promise to bring end-to-end reasoning to autonomous driving, but their computational cost remains far too high for real-time control.…
From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
arXiv:2608.13043v1 Announce Type: new Abstract: Diffusion models have achieved dominant performance in visual generation but suffer from substantial inference overhead. While cache-based acceleration has emerged as a…
SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents
arXiv:2608.12429v1 Announce Type: cross Abstract: Web agents often struggle to generalize to unseen websites because they lack website-specific supervision. Recent exploration-based data synthesis methods reduce manual…
LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning
arXiv:2608.12626v1 Announce Type: cross Abstract: Strategic reasoning in Large Language Models (LLMs) within long-horizon environments is often limited by inconsistent subgoals. In these settings, finite attention…
Moose: Latent concept learning with reasoning-shortcut awareness in $\mathcal{EL}^{++}$
arXiv:2608.12961v1 Announce Type: new Abstract: The OWL 2 EL profile is used in some of the largest production ontologies, including the Gene Ontology and SNOMED CT. Existing neuro-symbolic (NeSy) learning methods…
Foundations of MT-PDCL: Measure-Theoretic Probabilistic Definite Clause Logic
arXiv:2608.13018v1 Announce Type: new Abstract: Standard probabilistic logic programming frameworks typically rely on grounding logic programs into discrete propositional representations. This operational requirement…
Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing
arXiv:2608.12831v1 Announce Type: cross Abstract: Online platforms increasingly compare many adaptive decision policies---ranking systems, recommendation algorithms, pricing rules, and language-model agents---while each…
Predictive Memory Localization: Forecasting Selective Intervention Paths from Internal Signals
arXiv:2608.12892v1 Announce Type: new Abstract: Activation steering turns localized representations into control directions, but localization alone does not reveal whether a direction has a selective operating regime.…
Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services
arXiv:2608.13315v1 Announce Type: cross Abstract: We study a large language model (LLM) service in which a provider chooses a per-token price and a default reasoning-token allocation, while a user may accept the…
DomusFM: A Foundation Model for Event-Based Behavioral Monitoring in Smart-Homes
arXiv:2602.01910v2 Announce Type: replace Abstract: Smart-home sensor-based behavioral monitoring holds significant potential for healthcare, independent living, and early detection of functional or cognitive changes.…
Position: We Need Practical AI Alignment Methods to Mirror Human Reasoning
arXiv:2608.12372v1 Announce Type: new Abstract: AI systems are increasingly employed as decision aids, decision delegates, or autonomous decision-makers. This position paper argues that in many settings, particularly…
Foam-Agent: A Large Language Model-Based Multi-Agent Framework for Automating Computational Fluid Dynamics Workflows
arXiv:2505.04997v3 Announce Type: replace Abstract: Computational fluid dynamics (CFD) has been the main workhorse of computational physics, yet its steep learning curve and fragmented, multi-stage workflow create…
A Hierarchical Energy-Based Model for Multimodal Cognition
arXiv:2608.12398v1 Announce Type: cross Abstract: We propose IM-LEPP (Integrated Multimodal Latent Energy-based Predictive Processing), a hierarchical, energy-based model of multimodal cognition that extends a…
The Role of Natural Language Understanding in Multimodal Video-Based Dengue Diagnosis
arXiv:2608.12677v1 Announce Type: new Abstract: Detecting infection-related behavioral changes in mosquitoes from video data is challenging because mosquitoes are small, move rapidly and irregularly, and are affected by…
Novel Knowledge-Guided Generative Methods for Synthetic Transcriptomic Data
arXiv:2608.13256v1 Announce Type: cross Abstract: As biomedical research increasingly relies on data-intensive tools, the quality and utility of datasets are critical. Challenges such as imbalances, biases, and ethical…
When AI Is Your Pastor: A Benchmark for Theological Triage and Pastoral Guidance in Large Language Models
arXiv:2608.12324v1 Announce Type: cross Abstract: People increasingly ask large language models (LLMs) for counsel on questions of faith, doctrine, and pastoral care. These questions are not ordinary information…
EEG-PRIME: Prototype-Aligned Representation Learning with Multi-Level Conditioning for EEG Decoding
arXiv:2608.13072v1 Announce Type: new Abstract: Electroencephalography (EEG) decoding models often generalize poorly across datasets and subjects due to domain shifts in acquisition protocols and individual…
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
arXiv:2608.12921v1 Announce Type: cross Abstract: The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies. Existing topology generation…
Dead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues
arXiv:2608.12599v1 Announce Type: new Abstract: Multi-turn dialogues let users revoke constraints as easily as impose them, but revocation does not reliably take effect: models keep enacting withdrawn requirements…
@skills: Attention is all you have
arXiv:2608.12610v1 Announce Type: new Abstract: There are 56,804 public agent skills today, and teams write many more privately. The dominant delivery model is installation: once installed, a skill's description remains…
Query Timing Produces Opposite Positional Biases Between LLMs and Humans
arXiv:2608.12387v1 Announce Type: cross Abstract: Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their…
Memorization Diagnostics for Code LLMs Should be Scale-Aware
arXiv:2608.12771v1 Announce Type: cross Abstract: The extent to which large language models for code rely on memorization over genuine understanding remains highly debated. While current literature frequently reports…
Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
arXiv:2608.09696v3 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…
Academic League of Artificial Intelligence - An Integrative Perspective of Teaching, Research, and Extension
arXiv:2608.13447v1 Announce Type: new Abstract: Academic leagues have become important mechanisms for promoting extracurricular education and strengthening the integration between universities and society. This paper…
Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning
arXiv:2608.10473v2 Announce Type: replace-cross Abstract: Offline-to-online (O2O) reinforcement learning aims to leverage policies pretrained on static datasets while improving them through online interaction. However,…
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
arXiv:2608.13417v1 Announce Type: new Abstract: Autonomous agents are increasingly capable of improving models, systems, and other technical artifacts through long-horizon experimentation. To understand the current…
vToken: Token-Level Virtualization for Reclaimable KV Caches
arXiv:2608.13263v1 Announce Type: new Abstract: Large language model serving faces a critical memory bottleneck: the KV cache grows with sequence length and batch size. PagedAttention uses fixed-size memory blocks to…
AutoQuREO: A Framework for Automated Quantum Resource Estimation and Optimization
arXiv:2608.12936v1 Announce Type: cross Abstract: As quantum computing progresses from proof-of-principle demonstrations toward practical utility, a significant impediment is the need to augment algorithmic feasibility…
LLMs Know the Constraint But Do Not Use It: Activation Bottlenecks in Pragmatic Constraint Reasoning
arXiv:2608.12321v1 Announce Type: cross Abstract: When a salient surface cue competes with an implicit feasibility constraint, LLMs often fail -- but aggregate accuracy conflates genuine constraint inference with…
Doctorina MedBench: A Dialogue-Based Benchmark and Evaluation Framework for Agent-Based Medical AI
arXiv:2603.25821v3 Announce Type: replace-cross Abstract: We present Doctorina MedBench, an evaluation framework for agent-based medical AI based on the simulation of physician-patient interactions. Unlike traditional…
IACDM: Interactive Adversarial Convergence Development Methodology -- A Structured Framework for AI-Assisted Software Development
arXiv:2604.16399v3 Announce Type: replace-cross Abstract: Adoption of AI-assisted development in 2025 exposed a tool-agnostic failure pattern: experienced developers using frontier models were measurably slower while…
Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models
arXiv:2607.28166v2 Announce Type: replace-cross Abstract: Diffusion language models expose a provisional prediction at every denoising step, and on many tasks the candidate answer inside it stabilizes before the step…
CIDER: A Dataset of Contextual Disclosure Boundaries for Privacy Preference Alignment
arXiv:2608.09164v2 Announce Type: replace Abstract: Aligning large language models (LLMs) with human privacy preferences requires capturing individuals' disclosure boundaries beyond general privacy norms. However, a gap…
Error-Aware Reverse Auction Mechanism for Large Language Model Routing
arXiv:2608.12719v1 Announce Type: cross Abstract: Routing each query to a cost-effective large language model (LLM) is critical for balancing quality and cost, yet most routers rely on a centralized task center to…
Security and Detectability Analysis of Unicode Text Watermarking Methods against Large Language Models
arXiv:2512.13325v2 Announce Type: replace-cross Abstract: Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing control over data when it…
MOSAIC: Unveiling the Moral, Social and Individual Dimensions of Large Language Models
arXiv:2603.00048v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly deployed in sensitive applications including psychological support, healthcare, and high-stakes decision-making.…
CABS+: Efficient and Scalable Model Merging via Conflict-Aware Sparsification and Adaptive Weight Allocation
arXiv:2608.12842v1 Announce Type: new Abstract: Model merging has recently attracted significant attention as a promising paradigm for constructing unified multi-task models without requiring additional retraining.…
The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
arXiv:2608.13520v1 Announce Type: cross Abstract: We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity}…
Grok 4.6 matched Fable 5 Max at an 85% discount. Downloadable models set that price.
I’m Matt Burns, Chief Content Officer at Insight Media Group. Each week, I round up the most important AI developments, The post Grok 4.6 matched Fable 5 Max at an 85% discount. Downloadable models set that price.…
I'm Done Paying for Beautiful.ai — Here's My Free Alternative
I'm Done Paying for Beautiful.ai — Here's My Free Alternative You know the drill. You're prepping for a investor meeting, a pitch competition, or just need to present your startup idea. You open Beautiful.ai, stare at…
Markdown Dialects Need a Capability Matrix, Not Just a Name
Two tools can both claim to support “Markdown” and still disagree about tables, task lists, bare URLs, and even the HTML element used for strikethrough. That is usually not a parser bug. It is a contract problem.…
Large-Scale Pokémon Eviction Looms with Pokémon Bank Server Shutdown
After the Nintendo 3DS handheld console saw most its online services including the online store (eShop) taken offline not too long ago, it was only a matter of time before …read more
Christophe Pettus: All Your GUCs in a Row: jit and jit_provider
PostgreSQL's JIT compiler trades upfront compilation time for faster query execution—but it silently does nothing if the LLVM library isn't installed.
Anthropic says text watermarking scheme relies on inconsequential words
'Shall I compare thee to a summer's afternoon' is the sort of thing this will make, and others look likely to adopt it
Freelancer Tax Estimator：我又建了一个免费工具
Freelancer Tax Estimator：我又建了一个免费工具 原文发布于 Dev.to · 2026-08 上个月报税季，我算了一下自己的 freelance 收入该交多少税。 随手搜了"freelance tax estimator"，第一个结果就是 QuickBooks Self-Employed。界面漂亮，功能齐全——直到我看到了价格：$15/月，按年付 $180。…
Environment Variables the Safe Way
Why Environment Variables Matter Every app has secrets: API keys, database URLs, admin passwords. Hardcoding them in source code is a one-way ticket to leaks. Even if your repo is private, you never know who forks it or…
Tea5767-Radio-Tuner
Hacker News discussion (35 points, 2 comments)
Credit card debt rises to $1.26T, nearing all-time record
Hacker News discussion (30 points, 27 comments)
AI-Assisted GPU Porting of a 250k Line Legacy Weather Simulation Code
Hacker News discussion (43 points, 5 comments)
Software Engineering fundamentals matter more
Hacker News discussion (204 points, 136 comments)
SugarTrack – an offline Android logbook for blood sugar (no account, no cloud)
Hacker News discussion (41 points, 15 comments)
Modeling and Verification of Keeta's Consensus [pdf]
Hacker News discussion (10 points, 1 comments)
Bede Liu, a digital signal processing pioneer, has died
Hacker News discussion (53 points, 2 comments)
The Wow signal was a strong narrowband radio signal detected on August 15, 1977
Hacker News discussion (60 points, 11 comments)
Tracking down a Zsh history data loss bug
Hacker News discussion (93 points, 36 comments)
Abdominal fat predicts heart disease risk better than BMI
https://pmc.ncbi.nlm.nih.gov/articles/PMC13470613/
Cultivating a state of mind where new ideas are born (2023)
Hacker News discussion (245 points, 59 comments)
Humazon
Hacker News discussion (21 points, 10 comments)
Plastic mechanical computer from 1963: The Digi-Comp 1 [video]
Hacker News discussion (65 points, 17 comments)
Super El Niño Keeps Growing as New Forecasts Reach Record Territory Ahead Winter
Hacker News discussion (301 points, 194 comments)
AI in drug discovery – what it is, where we stand and the path forward
https://www.nature.com/articles/s41573-026-01496-2
Tess's Android Wayland Compositor
Hacker News discussion (61 points, 9 comments)
AI has access to a vastly larger working memory than the human brain
Hacker News discussion (525 points, 453 comments)
TreasuryDirect: Prepare for ID.me – Your New Way to Log In
Hacker News discussion (22 points, 22 comments)
Europe's scorched landscapes seen from space after summer heatwaves
Hacker News discussion (55 points, 20 comments)
The Dutch Community Where People Live on Strips of Land in a Lake
Hacker News discussion (45 points, 21 comments)
I Remain a Skeptic
Hacker News discussion (51 points, 25 comments)
A controversial Alzheimer's surgery is said to reverse symptoms
Hacker News discussion (91 points, 34 comments)
Semaglutide linked to lower predicted dementia risk
Hacker News discussion (445 points, 328 comments)
How developers scale their workflows with automation
In this clip from the OpenClaw fireside chat, Peter Steinberger explains how developers scale their output through compounding automation. By turning imagination into small workflow improvements, even silly experiments…
A spectre is haunting Unicode
Hacker News discussion (241 points, 94 comments)
Printytron – Type it. 3D Print it
Hacker News discussion (16 points, 0 comments)
At-home test for infected ticks could improve Lyme Disease diagnosis
Hacker News discussion (266 points, 103 comments)
Yadda 3.0.0: BDD in the Age of AI Agents
Hacker News discussion (44 points, 20 comments)
Could a computer scientist build a brain?
Hacker News discussion (46 points, 28 comments)
Xorshift Generators
Hacker News discussion (28 points, 20 comments)
Auto-research with codex: How I achieved a 232x Faster Kernel
Hacker News discussion (391 points, 86 comments)
Working with AI feels more like leadership than coding
Hacker News discussion (264 points, 169 comments)
Debian has begun voting on the future of AI/LLM contributions
Hacker News discussion (43 points, 26 comments)
Using GCC's Nested Functions with Wide Pointers and No Trampolines II
Hacker News discussion (73 points, 38 comments)
"That's not SoC 2 compliant"
Hacker News discussion (16 points, 9 comments)
Replay: Open Source Friday Cua with Francesco Bonacci
Join us for Open Source Friday with Francesco Bonacci, CEO of Cua, exploring the future of computer-use agents. We discuss Cua’s open-source ecosystem, including Lum, Cua Driver, benchmarks, and the shift from…
Ask HN: How do you keep up with HN these days?
In the last 2-3 years, mostly because of AI, keeping up with interesting articles on HN has become harder and harder. How do you deal with it? Besides the simple solution of simply ignoring interesting stuff more and…
Show HN: ThoughtDAG – An editable context graph for LLM conversations
Hacker News discussion (56 points, 14 comments)
The other Sean Byrne doesn't exist
Hacker News discussion (332 points, 163 comments)
The End of Mathematics
Hacker News discussion (18 points, 7 comments)
Show HN: Deltix – AI Driven Testing
Hacker News discussion (23 points, 7 comments)
Magnitude 7.7 Earthquake – 68 km NNW of Ende, Indonesia
Hacker News discussion (207 points, 51 comments)
The Ploopy A+ Trackball Is Here
Hacker News discussion (91 points, 40 comments)
2D Gaussian Splatting for Bézier Spline Line Art Vectorization
Hacker News discussion (62 points, 4 comments)
Simplifying and Refactoring Introductory Calculus (2018)
Hacker News discussion (106 points, 53 comments)