TILens Daily Edition 2026-11-18 Filters: topic=ai, github=hidden Stats: 391 articles, 33 sources, 325 research papers Top topics: AI, AI Research, Information Retrieval ## News - Announcing distributed KV caching for self-hosted LLMs with Amazon ElastiCache Source: aws-database-blog Topic: AWS (+AI, PostgreSQL) URL: https://aws.amazon.com/blogs/database/announcing-distributed-kv-caching-for-self-hosted-llms-with-amazon-elasticache/ - Amazon OpenSearch Memory is now generally available Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/11/amazon-opensearch-memory-generally-available/ - DaisyRose-27B: Pushing the Frontier of Post-Training Efficiency Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/RadixArk/daisyrose-27b-pushing-the-frontier-of-post-trainin - AWS Lambda now supports GPU instances for Event Functions on Lambda Managed Instances Source: aws-news-blog Topic: AWS (+AI) URL: https://aws.amazon.com/blogs/aws/aws-lambda-now-supports-gpu-instances-for-event-functions-on-lambda-managed-instances/ - Why your fine-tuning job takes longer than the FLOPs say Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/Dharma-AI/predicting-fine-tuning-time - How Meta Uses AI Agents to Scale ML Innovations Across Ads Ranking Models Source: meta-engineering Topic: Architecture (+AI) URL: https://engineering.fb.com/2026/11/18/ml-applications/ai-agents-to-scale-ml-innovations-across-ads-ranking-models/ - Persistent Sessions and Memory for Strands with MongoDB Source: mongodb-blog Topic: MongoDB (+AI) URL: https://www.mongodb.com/company/blog/product-release-announcements/persistent-sessions-memory-for-strands - Time-Series Models in the Streamhouse: A New Frontier and Use Cases Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/ibm-research/time-series-powered-streamhouse - Building agentic memory at the edge with Moorcheh on Arduino VENTUNO Q: Scale multimodal search engine to millions of records Source: arduino-blog Topic: Hardware (+AI, Information Retrieval) URL: https://blog.arduino.cc/2026/11/18/building-agentic-memory-at-the-edge-with-moorcheh-on-arduino-ventuno-q-scale-multimodal-search-engine-to-millions-of-records/ - The Silent Consensus Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/the-silent-consensus - Research acceleration: The jagged frontier Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/research-acceleration-jagged-frontier - Inside the Codex sandbox Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/inside-the-codex-sandbox - How Sumitomo Life’s leaders helped teams adopt ChatGPT Enterprise Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/business/customer-stories/sumitomo-life - Amazon ElastiCache now supports distributed KV caching for self-hosted LLM inference Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/11/announcing-distributed-kv-caching-for-self-hosted-llms-with-amazon-elasticache/ - Managing frontier AI risk: From training to deployment Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/managing-frontier-ai-risk - Le Groupe Figaro and OpenAI partner to bring Le Figaro journalism to ChatGPT Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/le-groupe-figaro-and-openai-announce-partnership - Advancing chip design with OpenAI models Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/advancing-chip-design-with-our-models - 180B Parameters, 32GB of RAM: Pushing MoE Inference to the Limit with Transformers Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/moe-expert-streaming - Rumble-2-Flash: an open 0.5B speech model for 40+ languages Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/rumble-2-flash - 50 Free Browser-Based Tools That Run 100% Locally (No Uploads, No Sign-Up) Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/hamhuong/50-free-browser-based-tools-that-run-100-locally-no-uploads-no-sign-up-20b1 - Anthropic prices IPO at $83 a share, above projected range Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/11/18/anthropic-reportedly-prices-ipo-at-83-a-share-above-projected-range/ - Anthropic decides to go head-to-head with GTA VI release, schedules IPO for the same day Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/11/18/anthropic-decides-to-go-head-to-head-with-gta-vi-release-schedules-ipo-for-the-same-day/5310872 - 😸 WATCH: Pika lets you direct AI actors live Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/watch-pika-lets-you-direct-ai-actors-live/ - Would You Let an AI Agent Spend Your Money? Source: ai-agents-simplified Topic: AI (+AI Tools) URL: https://aiagentssimplified.substack.com/p/ai-agent-payments-chatgpt-wallet-gemini - The latest edition of Phrack magazine is out Source: adafruit-blog Topic: Hardware (+AI) URL: https://blog.adafruit.com/2026/11/18/the-latest-edition-of-phrack-magazine-is-out/ - OpenAI spent $1.2 million finding nearly 1,000 Linux security flaws. Sam Altman says this is just the beginning. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-entire-ai-stack/ - Designing LLM Agents as Explicit State Machines in Java Source: java-code-geeks Topic: Java (+AI) URL: https://www.javacodegeeks.com/2026/11/designing-llm-agents-as-explicit-state-machines-in-java.html - Evals for AI Engineers Source: bytebytego Topic: Architecture (+AI) URL: https://blog.bytebytego.com/p/evals-for-ai-engineers - OpenAI CEO Sam Altman says it’s ‘hard to imagine the AI industry without Jensen’ Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/11/18/openai-ceo-sam-altman-says-its-hard-to-imagine-the-ai-industry-without-jensen/ - The AI Hype Index: AI is everywhere Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/11/18/1148650/ai-hype-index-ai-is-everywhere/ - GPT-6.2 Astra Draws a Python Reading a Book Source: real-python Topic: Python (+AI) URL: https://realpython.com/ai-benchmark-gpt-6-2-astra/ - GPT-6.2 Sol Draws a Python Reading a Book Source: real-python Topic: Python (+AI) URL: https://realpython.com/ai-benchmark-gpt-6-2-sol/ - “Collaboration over competition”: Hugging Face hands model inference traffic to OpenRouter Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/hugging-face-openrouter-inference/ - Everything after code, as code Source: pulumi-blog Topic: DevOps (+AI) URL: https://www.pulumi.com/blog/everything-after-code-as-code/ - OpenAI’s newest release lands to rough reviews Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/openai-newest-release-lands-to-rough-reviews - This smell startup says its AI nose is as good as a human’s Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/11/18/1148816/smell-startup-osmo-ai-nose-good-as-humans/ - 😺 OpenAI unveils GPT-6.2 Astra and Sol Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/openai-unveils-gpt-6-2-astra-and-sol/ - Not-So-Large Language Model Fits On a Floppy Disk Source: hackaday Topic: Hardware (+AI) URL: https://hackaday.com/2026/11/18/not-so-large-language-model-fits-on-a-floppy-disk/ - Zodiac date tables are wrong for about 1 birth in 80: I computed 972 Sun sign crossings Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/ricco020/zodiac-date-tables-are-wrong-for-about-1-birth-in-80-i-computed-972-sun-sign-crossings-3clc - AI Models Picked Civilians as Military Targets. A Game Prompt Made It Worse. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/ai-models-civilians-military-targets-game-prompt/ - Everything That Happened in AI Today (Wednesday, November 18, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-wednesday-november-18-2026/ - GPT-6.2 🤖, widespread outages ⚠️, being known as a good dev 👨‍💻 Source: tldr-tech Topic: General (+AI) URL: https://tldr.tech/tech/2026-11-18 - I Trained a Neural Net to Play Pokémon Source: foojay-today Topic: Java (+AI) URL: https://foojay.io/today/i-trained-a-neural-net-to-play-pokemon/ ## Research - How AI Agents Become a Tool for Attackers, and How to Stop It Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-ai-agents-become-a-tool-for-attackers-and-how-to-stop-it/ - Neurosymbolic Agents Explained, With a Z3 Example in Python Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/neurosymbolic-agents-explained-with-a-z3-example-in-python/ - When Qini Rewards the Wrong Uplift Model, Use Doubly Robust Scores Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/when-qini-rewards-the-wrong-uplift-model-use-doubly-robust-scores/ - How to Estimate Dose-Response Curves When DoubleML Falls Short Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-estimate-dose-response-curves-when-doubleml-falls-short/ - An Optimization Framework for Denoising Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22202 - Learning Optimal Transport Plans Via Autoregressive Token Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22218 - Token Commitment as a Control Surface for Steering Masked Diffusion Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21669 - Not All Mislabels Are Equal: Efficient Task-Aware Auditing with Confidence Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33262 - Margin Dynamics for Large Language Model Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21766 - GP--RL--MPC: Uncertainty-Aware Reinforcement Learning-Augmented Model Predictive Control with Gaussian Process Postdecision State-Value Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22038 - Quantifying Concentration Phenomena of Mean-Field Transformers in the Low-Temperature Regime Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10931 - World-Grounded Reinforcement Learning for Pollution-Aware Bird Movement Modeling Using a Multi-Instance DQN Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21895 - RTLReviewBench: LLM Hardware Reviewers Rarely Miss Bugs but Routinely Reject Correct RTL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21678 - From Constraints to Causality: Petri net Encodings for Explaining Binary Neural Network Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22396 - Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14912 - Exact Sequence Interpolation with Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.02270 - An AI-Based OSSE Framework to Evaluate Learned Physical Consistency: A Multi-Model Study Using FourCastNet, Aurora, Prithvi WxC, and GraphCast Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22024 - OAK-Mind: Zero-Training Mental Health Change Inference from Passive Sensing via Knowledge-Grounded Multi-Agent LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22248 - Beyond Bitwidth: Deployment-Constrained Mixed-Precision Quantization for Multilingual LLM Inference on NVIDIA Blackwell Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21974 - LEGIT: Live Eligibility Gating over Identifier Tries for Constrained Decoding of Heterogeneous Pages Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.10357 - On Formal Counterfactual Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22010 - Communicate the Change: Efficient Expert Parallelism via Activation Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22215 - Sampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Neural Combinatorial Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13087 - Annealed Gibbs Measures with Data-Driven Interaction Potentials on Hierarchical Structures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30064 - Modeling Document and Section Hierarchies in Embedding Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21980 - MedGuardBench: A Patient-Oriented Benchmark for Personalized Guardrail Development Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22069 - Improved Convergence Rates for Stochastic Multi-Gradient Descent which Close the Gap: A Proof by AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18174 - How Many Training Labels Are Wrong? Auditing a Fitted Model through Gradient Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22449 - GPTZero: Robust Detection of LLM-Generated Texts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13042 - OVAL: Output-Aware Local Page Bases for KV Cache Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06686 - PVTSizing 2.0: A Fast and Reliable Analog Circuit Sizing Operator for Agentic EDA Workflows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22328 - PRUE: A Practical Recipe for Field Boundary Segmentation at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27101 - When is Warmstarting Effective for Scaling Language Models? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13405 - Evaluating and Mitigating Skin Color Bias in Skin Lesion Classificatio Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.11627 - What RL on Expert-Built Tasks Teaches Nemotron 3.5 Super Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22161 - Does the Model Use What It Cites? Counterfactual Tests of Grounded Reasoning Chains in Small Video-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21940 - HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.15405 - Stop Early, Stay Simple: Evidence Acquisition for Power System Fault and Attack Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21695 - A physics-constrained neural solver for incompressible flows without labeled data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.18820 - ReMoE: An Interpretable Mixture-of-Experts Framework for Human Mobility Recovery Forecasting Across Disasters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22133 - OfficePrism: Benchmarking Agents on Single-Domain Operations Across Enterprise Business Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22262 - ReMaRL: Learning to Unmask and Remask in Frozen Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22576 - ScAn-Bench: Evaluating Scaling Analysis Methodology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35707 - Clustering in pure-attention hardmax transformers and its role in sentiment analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.01602 - Every Measurement, Every Direction, All at Once: Multimodal Flow Matching for Molecules and Spectra Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22098 - Where Root Cause Analysis Fails: A Retrieval-Reranking Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36686 - NovoCRF: Globally Normalized De Novo Peptide Sequencing on a Prefix-Mass Lattice Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05260 - HubEgo-100K: In-the-Wild Egocentric Video of Skilled Work for Robot Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21938 - AdaFlowLite: Scalable and Non-blocking Inference on Asynchronous Mobile Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21691 - Graph neural networks and the energetic cavity method for combinatorial optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07456 - Lost in the Funnel: Selection-Induced Miscalibration in Ranking and Decision Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22595 - Scaling Laws for Vision-Language Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22351 - Misalignment of Low-Loss Regions Causes Grokking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00620 - Spatially local mini-batching for implicit neural representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22236 - Dandelion: A Spherical Flower for Neural Simulation of Planetary Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27521 - Limite 1B - Violetto: Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21646 - Activation-Space Exploration for Visual and Textual Reasoning with RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27012 - Escaping Latent Traps by Remembering: Training-Free Episodic Kernel Repulsion for World-Model Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22470 - Natural Code Transformation Confuses Agents in Vulnerability Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14350 - What Does Weight-Space Programming Add to Diffusion Editing? Program Construction versus Score-Guided Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22228 - Regularized Score Centering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21791 - An Open-Source Training Dataset for Foundation Models for Hyperparameter Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23417 - Propose with the Gradient, Accept with the Loss: One Hedged Attack for Pixel-Sparse Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22596 - A Cherry-Picking Approach to Large Load Shaping for More Effective Carbon Reduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17990 - AI Simulations Grounded in Rich Self-Reports Increase Accuracy and Reduce Distortion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.10109 - Pseudo-Label-Triggered Retraining from Forecast Errors for Online Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39789 - VisHead-Spec: Head-Routed Visual Attention for Multimodal Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21839 - Auditing World-Model Explanations in Retail Forecasting: Faithfulness, Accuracy and Price Response Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.20811 - When Does Discrete Ricci Curvature Help? An Edge-Level Analysis of Curvature-Enhanced GCNs for PPI Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21849 - AI4Plasma II: Geometry-Aware Surrogate Modeling for Variable Electrode Gap GEC Plasmas Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15584 - VRLLM: Turning LLMs into Powerful Tabular Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22308 - iMuon: Intrinsic Spectral Optimization on Riemannian Matrix Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09238 - Forecasting How RLHF Responds to Reward-Model Edits Before Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03244 - Gradient Manipulation in Distributed Stochastic Gradient Descent with Strategic Agents: Truthful Incentives with Convergence Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27962 - Score-based neural ordinary differential equations for reaction-diffusions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18467 - Learning Greens Operators through Hierarchical Neural Networks Inspired by the Fast Multipole Method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.20591 - Testing World Models on Actions They Have Never Seen: Held-Out Plans, Forecast Accuracy and Price Rules in Retail Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22537 - Physics Informed Reinforcement Learning with Gibbs Priors for Topology Control in Power Grids Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01830 - KVUse: Reusable-KV User Memory for Efficient LLM Recommenders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21920 - Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25846 - Urban Representation Learning for Identifying Potential Disparities in Crime Reporting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21825 - Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30556 - Synthetic Crystal Data Generation for Diffusion Pretraining in Material Property Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22140 - Representation Learning with Quantum Signal Processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28828 - Latent Fact Composition under Next-Token Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21921 - Two Counterexamples for e-means Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22065 - Optimizer's Information Criterion: Dissecting and Correcting Bias in Data-Driven Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2306.10081 - When Candidate Pools Miss Active Constraints: Evidence from Electromagnetic and Thermal Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18903 - A single inference process underlies the behavior and neural circuits of working memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22054 - Video recordings and play behaviour annotations of group-housed dairy calves on two Dutch farms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21706 - Does On-Policy Distillation Need to Complete Every Rollout? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21337 - Inventa: Decentralized Self-Improving Agents for Autonomous Scientific Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21847 - Alpha-TCM: Auditable Knowledge Integration for Multimodal TCM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38754 - COTTI: Contrastive Training and Time-Aware Inference for Robust Industrial Recommendation under Promotional Drift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22597 - Towards Optimism-Pessimism Trade-off in Model-based Offline-to-Online Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22172 - Eyes in the Update? Learning Where Rewards Land in Multimodal Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22438 - Sample-efficient Personalization of Large Language Model Alignment with Multidimensional User Preference Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22210 - OpenMHC: Accelerating the Science of Wearable Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16235 - Multivariate Distributional Reinforcement Learning Using Sliced Divergences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31222 - Hybrid Quantum Selection of Learning Rates in Language-Model Training: Termination Criteria and an Interaction-Guided Schedule Oracle Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21701 - SkillBuffBench: Measuring What Agent Skills Contribute across Harnesses, Models, Skill Access Modes and Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22017 - Cancellation-Free Constrained SquareCB for Safe Controller Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21880 - Centroid Spectral Coupling: Implicit Alignment and Representation Diversity in Self-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22158 - Multistage Contextual Optimization for Vehicle Repositioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22330 - CardioLoom: A Report-Guided Electrocardiogram Foundation Model for Cross-Domain Cardiovascular Phenotyping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25446 - Information Limits of Replay-Free Recurrent State Migration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.19345 - Memorization capacity of deep ReLU neural networks characterized by width and depth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09589 - Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.19244 - Manufacturing Differential Sparsity: Planner-Hardware Co-Design for Efficient World Model Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22483 - On Minimal Observation Time for Recovering Latent Hawkes Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08400 - Formalizing the Intrinsic Dimension of Objective Landscapes by a Generalized Notion of Co-dimension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39674 - Q-LocalAdam: Memory-Efficient Client-Side Adaptive Optimization for Edge Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17552 - Stein Kernelized Molecular Dynamics for Active Learning of Interatomic Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04100 - Do Diffusion Models Learn to Generalize Basic Visual Skills? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22427 - TIBECG: Temporal Information Bottleneck for Lead-Specific Demographic Privacy in ECG Waveform Release Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21694 - Theory-Scale Auto-Formalization of Logic for Computer Science Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26525 - Similar Is Not Useful: Selecting In-Context Demonstrations by Closed-Loop Utility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22295 - Asymptotic Margins and Feature Confinement in Conic Classification Heads under Softmax Cross-Entropy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18507 - Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02190 - Quantum Cognition Machine Learning for Forecasting Chromosomal Instability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.03199 - Intuition Vectors from Pretrained Representations Steer Diffusion-Based Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32619 - Mix-Opt: Mixed Optimization for Memory-Efficient Personalization of Text-to-Image Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.10029 - ConfGuard: a physics-grounded reference monitor for predictive-maintenance large-language-model agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22288 - Temporal Diffusion Models for Joint Signal-Channel Estimation under Gaussian and $\alpha$-Stable MIMO Channels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22548 - Bookkeeping Is Not Judgement: EJBench, an Engineering Judgement Benchmark Built from a Conjugate Heat Transfer Design Campaign Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21707 - DLS: Dual-Logic Graph Neural Networks with Chaos-Fuzzy Residuals for Robust Link Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22607 - Learning Calibrated and Samplable Predictive Distributions of Surface-Ocean $\Delta p$CO$_2$ Using Tabular Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21769 - Localized LoRA-MoE: Mixture of Low-Rank Experts With Adaptive Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05114 - Cross-Epoch Bias in SGD-based Leave-One-Out Influence: Analysis and Accumulative Correction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.26185 - Better Calibrated, Better Planned: Uncertainty-Aware Multi-ASV Informative Path Planning for Oil Spill Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21783 - ReShap: Interpretable Reinforcement Learning for High-Dimensional Multi-Action Settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15507 - LeapQuant: Efficient Linear Attention with Accurate Recurrent State Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38166 - TempQuant: Learning Adaptive Temperatures for Quantized Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22128 - A Log-Timescale Perturbation Bound for Selective State Space Models at Every Sequence Length Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21952 - Toward AI epidemiology: a measurement standardization framework for prospective risk detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15783 - CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.18857 - Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05516 - Physics-informed neural networks for spacecraft trajectory optimization with exact boundary conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21933 - ALOHA Lightning: Learning Fast and Precise Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21919 - What Can a VLA Learn from the Agent That Calls It? Task-Level Experience Distillation for Embodied Navigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16246 - Beyond Single Slot: Joint Optimization for Multi-Slot Guaranteed Display Advertising Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21556 - EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16728 - DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41536 - Attention at Absolute Zero Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11937 - Encoding, Decodability, and Use: A Five-Layer Framework for Benchmark Measurement Audits with Evidence from UAV Intent Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22434 - Quantum-Classical Separation in Probability Distribution Transport via Nonlocal Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21840 - Feature Selection for Tabular Foundation Models: Exploring Feature Utility in Low-Data Molecular Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30789 - Addressing Exogenous Variability in Cooperative Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22067 - Wrong Input, Wrong Threshold: Re-evaluating Adversarial Facial Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21923 - Neural Classifiers as Error-Correcting Codes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18239 - Bias-Reduced and Parallel Heavy-Tailed Stochastic Convex Optimization in $\ell_p$ Geometries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21844 - Measuring and Decomposing Mode Separation via the Canonical Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08777 - Regularization Amplifies Subliminal Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10397 - Algorithmic Insurance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2106.00839 - Sample-Aligned Decoders for Latent Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22458 - First-order methods for stochastic and finite-sum convex optimization with deterministic constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.20630 - Nanorobot queue: Cooperative treatment of cancer based on team member communication and image processing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2111.11236 - Zero-Dimensional Attention Topology for Linguistic Acceptability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22312 - Amortizing Scaling Law Construction Costs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05016 - Semi-Supervised Learning with Noisy Proxy Covariates: Generalization Bounds and Distribution Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00512 - Probing and steering biology across Boltz-1s trunk-diffusion boundary Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11475 - Shared Context, Separate Engines: Stateful Streaming Inference for Multimodal LLMs on Edge SoCs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35309 - Recursive Learning-Based Virtual Buffering for Analytical Global Placement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.17247 - One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12253 - HyperKKL: Enabling Non-Autonomous State Estimation through Dynamic Weight Conditioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22630 - Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25267 - Efficient Machine Learning Interatomic Potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22444 - On the use of case estimate and transactional payment data in neural networks for individual loss reserving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.05274 - Lost in a Few Heads: Diagnosing and Repairing Block Selection in Sparse Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21917 - QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.14760 - Thought-deciphering via hierarchical EEG-to-text alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03623 - Transferable SCF-Acceleration through Solver-Aligned Initialization Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21657 - FACE: Flow-Guided Angular Channel Estimation Framework for mmWave MIMO Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21698 - DeltaHarness: Self-Evolving Harnesses for Resource-Adaptive Tool Execution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21688 - An open dataset of gas adsorption in deformable metal-organic frameworks for direct air capture Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.03162 - Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13319 - Benchmarking Deep Learning Models for Wheelchair Configuration Classification in Accessible Automated Vehicle Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21945 - Heave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22275 - RLDE: A Reinforcement Learning Framework for Interpretable Iterative Document Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22039 - VASR: Vector-Aware Assembly Planning with Equivalent Structures and Repair-Cost Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.20984 - Estimating aerosol particle number size distributions from PM2.5 with physics-regularized flow matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33557 - Flocking Time and Graph Volume in Nonlinear Cucker-Smale Models with Dynamic Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22204 - When does deep reinforcement learning pay off in HVAC supervisory control? Four small Modelica case studies trained directly on FMUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22144 - Goodhart in the Planner: Sampling-Based Control Exploits Rewards Learned from Human Preferences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.09670 - Semantic Prism: Generative Segmentation with an Explicit Semantic-Image Interface Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11537 - Functional Compression as Occam's Razor: Algebraic Complexity from Sensitivity Minimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.23152 - FoundCause: A Foundation Model for Causal Discovery with Latent Confounders from Observational Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17516 - Differentially Private Non-convex Distributionally Robust Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16155 - VTT: Reading Vehicle Size and Powertrain Type from Motion Trajectory Across Unseen Car Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22109 - PromptPack: Training-Free Augmentation of Diffusion Editors for Intent-Aligned Spatial and Semantic Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21865 - Bidirectional Random Projections Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10377 - Discovery of new antiviral agents through artificial intelligence: in vitro and in vivo results Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22230 - When AUC Meets Generative Reconstruction: A Unified Principle for Balanced Visual Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22094 - Fair Bubble Sort: Provably Optimal Fair Ranking with Continuous Sensitive Attributes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22352 - Bandit Online Submodular Minimisation Using Zeroth-Order Oracles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22130 - Sparse Integer Fourier Transform and Its Application In Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21976 - Sampling Design and Confidence Tubes for Integral Curves on Riemannian Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00771 - BernBRS: Certified Backward Reachability for Deep Bernstein Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22083 - Fixed Sets and the Hardness of Computing Correlated Equilibria Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28141 - Dual-Core Tensor Wheel Decomposition with Structure-Cached Acceleration for Tensor Recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13938 - Time-Delayed Transformers for Data-Driven Modeling of Low-Dimensional Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08478 - Offline Preference-Based Trajectory Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17541 - Fairness-Aware Test-Time Prompt Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25707 - PACT: Plan-Action Consistency Training by Preserving Correct Plans and Repairing Actions in GUI Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22591 - Multiply Robust Causal Mediation Analysis with Continuous Treatments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2105.09254 - SarcasTraps: Effect of Sarcasm on Turkish Hate Speech Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16957 - BQ-LoRA: Binary-Quantized Low-Rank Adapters as Implicit Regularizers for Parameter-Efficient Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22334 - Batched Stochastic Linear Bandits with 1-Bit Communication Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30976 - Chain-of-Thought Controllability Can Reduce Chain-of-Thought Monitorability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21799 - RiDEx: Reward-Informed Directional Exploration for Diffusion Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22052 - Large Language Models as Nonlinear Dynamical Systems: The Three Clocks of Depth, Training, and Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21983 - On the Feasibility of Image-Based Representations for Air Traffic Complexity Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11810 - Quantum-to-Quantum Transfer Learning Exhibits Improved Robustness in Low-Data Regimes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09118 - Weight-Space Programming Doesn't Need Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22055 - LoCaR: Localized Canvas Retrieval With Frozen Vision-Language Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22131 - Solver to System: LLM Reasoning Across Representations and Execution in Scientific Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21964 - DiffATS: Diffusion in Aligned Tensor Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09275 - A Temporal Algebraic Framework for Data Stream Evaluation Under Delayed Labels and Distribution Shifts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21914 - Higher-Order Interaction Reconstruction via Integral Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21935 - PCGRL for Complex Platformers: Synthesizing Playable and Diverse Levels via Inflated Envelopes and Forward Curricula Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22250 - Disambiguating Moral Circuits and Moral Features in Language Models: Moral content, normative judgment or cue words? Evidence from 14 models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21705 - ElectrolyteFM: Unifying Electrolyte Property Prediction through Cross-Property Knowledge Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39340 - One pool, many targets: a conservation layer and what archival data can identify Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00445 - SLICES: A Benchmark and Evaluation Framework for Self-Supervised Learning on Sparse ICU Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18868 - Seeing Is Not Enough: Knowledge-Grounded Active Inquiry from Uncertain Visual Evidence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38774 - Beyond Success Rates: Trainability and Extractability for Offline GCRL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05459 - Improving Early Detection of Scientifically Interesting Radio Sources Using Enhanced Isolation Forest Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21674 - JigSLO: Solving the Resource Puzzle for Efficient Multi-LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.06261 - SOTA or Luck? The Winner's Curse in LLM Leaderboards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22227 - Untrained CNNs Exceed Backpropagation in V1 Alignment at High Evaluation Resolution: A Systematic RSA Comparison of Four Learning Rules Against Human fMRI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16875 - PACD: Provenance-Aware Consensus Decoding for Mitigating Cross-Modal Hallucinations in Omnimodal Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22456 - Adaptive Memory for Online Reinforcement Learning under Sparse Model Changes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21879 - MAGIC-SSCIL: Manifold Anchoring and Geometric Incremental Calibration for Semi-Supervised Class Incremental Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07586 - XM-Sparse: High-Throughput Sparse-Attention LLM Serving over Scale-up Memory Pools Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22280 - V2V Communications Using Blockchain-Enabled 6G Technology and Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21932 - Dynamical Kernel Attention: Estimating the Present from a Record of the Past Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24026 - Sharp feature-learning transitions and Bayes-optimal neural scaling laws in extensive-width networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10395 - Agentic AI-Empowered Dynamic Survey Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04071 - RISA: Recoverable Sparse Attention for Block-Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22191 - DSADiff: Data Structure-Aware Diffusion for Crystal Structure Prediction via Mitigating Complexity- and Imbalance-Induced Biases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22050 - Right Labels, Wrong Reasons: Signed Feature Attribution for Multi-Label Explainability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22515 - Representable but Unlearned: Encoding Rank and the Interaction-Prediction Floor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36208 - Test-Time Coverage: Test-Conditioned Data Curation for Deployment-Aware Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22697 - Weight-space programming for tractor guidance controller: large language models natively write neural network weights that steer a real tractor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21958 - Compositional neural networks for multimodal X-ray and neutron scattering inversion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29362 - Scalable Learning from Probability Measures with Mean Measure Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.04907 - Latent Goal Prediction from Language for Model-Based Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20627 - Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.18179 - SURFing to the Fundamental Limit of Jet Tagging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.15779 - Learning Complementary Routes for Scouting Persimmon Orchards during Shoot Growth with CoverShare Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27507 - Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22401 - Deciding Without Pointing: A Case Study of Whether a Decision Model Localizes the Anomalies It Detects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21995 - How Much Distribution Shift Can a Clustering Withstand? Exact Split and Merge Certificates for Structured Transports Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22000 - Polylogarithmic Regret via Certainty Equivalence in Degenerate LQR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21927 - A closed-loop framework for perovskite precursor additive discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.20242 - Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12408 - Data-Driven Variable-Length Compression of 3D Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21802 - RelPrism: Multi-Faceted Self-Supervised Learning on Relational Databases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23241 - AI4Plasma I: Data-Efficient Surrogate Modeling of Capacitively Coupled Plasma Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15002 - WM-Quant: Rollout-Aware Post-Training Quantization for JEPA-Style World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21882 - ICA Lens: Non-Gaussianity Reveals Interpretable Directions in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11722 - From Temperature-Limited to Battery-Limited Legged Locomotion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22231 - Coordination of Heterogeneous Teams with Uncertain Task Requirements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21828 - Edge-Adaptive Hiera-Seg Model for Building-Integrated Photovoltaic Power Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21680 - SiGMA: Learning under Graph-Level Heterogeneity with Gated Message-Passing and Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.00547 - Efficient Self-Supervised Adaptation of 3D Abdominal Vision-Language Model for Institution-Specific HCC Classification via Full Fine-Tuning and PEFT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22504 - Layerwise Learning-Rate Scaling in Vision Networks: Effective-Rate Identification, Power-Mean Aggregation, and Budget Dependence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21696 - What MoE Routing Controls: Causal Interventions on Expert Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22120 - High-Dimensional Tail Index Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.01318 - Perception into Imagination: Executable Memory for World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22294 - Graph Cascades: Contagion-Based Mesoscopic Rewiring for Structure-Aware Graph Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05046 - tmol: a GPU-accelerated implementation of the Rosetta energy function for machine learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21857 - Computed Permutation Trellis Coding: Near-Optimal Quantization from Two Multiplications and a 64-Byte Table Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22019 - InfuseLoop: Cross-Trajectory Latent Injection for Scalable Parallel Looped Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22426 - The Hidden Cost of MoE Diffusion Decoding: Profiling and Fixing the Sampler Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21852 - When VLMs 'Fix' Students: Identifying and Penalizing Over-Correction in the Evaluation of Multi-line Handwritten Math OCR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22774 - ThermLeT: Transformer-based Temperature Prediction for 2.5D Chiplet Architecture Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21954 - Do Neural PDE Solvers Learn the Right Dynamics? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06952 - Physically Admissible Generative Flow Matching for Sparse Flow Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22549 - Conserved Verdicts, Drifting Commitments: Identifying Harmful Overthinking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21946 - OCCAM: Improved Single-Cell Representation Learning and Perturbation Effect Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21959 - Forecasting Retail Sales at Every Grain: Trees, Foundation Models, Transformers and World Models Compared on Four Public Data Sets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25170 - Balancing Exploration and Exploitation in Constrained Combinatorial Optimization with U(1)-Symmetric Tensor Trains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22557 - Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16989 - Kernel-based guarantees for nonlinear parametric models in Bayesian optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13160 - Generative sequence modeling for infinite memory processes via predictive states Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38524 - PEARL: Unbiased Percentile Estimation via Contrastive Learning for Industrial-Scale Livestream Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21752 - MemT-1.0: Towards Memory-Native Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26825 - From Relevance to Utility: Rubric Alignment in Yuanbao Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.22503 - RACE: Ranking-Uncertainty Aware Capacity-Adaptive Customization for Efficient Sequential Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.18244 - NONSENSE: Non-Semantic Strings Expose Semanticity Gaps in Dense Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.22353 - Teaching Language Models to Narrow Boolean Patent Searches from Search Feedback Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.22270 - RecHarness: A Bandit-Routed Agentic Harness for Self-Evolving Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.29241 - Lightfoot: Graph Retrieval-Augmented Generation with Exact, Model-Free Document Deletion Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.11010 - Retrieving Complementary Evidence for Multi-Hop RAG with Semantic Gain Graphs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.15285 - SIMQ: A Single Graph-based Index for Multi-Vector Query Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.22079 - Evaluating AST-Derived Knowledge Graph Retrieval for AIOps Incident Diagnosis in Apache Kafka Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.21625 - RICoT: Recurrent Interleaved Chain-of-Thought for Page Stream Segmentation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.22382 - MIPR: A Benchmark for Reasoning-Intensive Multimodal Intent-to-Product Retrieval with Multi-Category Solutions Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.22509 - GuardAgent: A Memory-Augmented Agentic Framework for Adaptive Detection of Adversarial Promotions in LLM-Based Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.22274 - NewsReX: An Open-Source Multi-Framework for Neural News Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2508.21572 - Complexity and precision in quantum associative retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.21941 - Deal With It: On Better Schedules for Listwise Reranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.22392 - CodeHID: Learning an Addressable Hierarchical Code Index for Generative Code Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.24089 - Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.04547 - Cluster-Guided Decoding with Trust-Region Constraints for Personalized Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.22163 - Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.24651 - Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.14434 - EE-Motion: An EEG-based Web Architecture for Live Affective Music Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.21032 - Enhancing Stock Market Information Retrieval with Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.03747 - REGER: Modeling inter-item Relations with Semantic IDs for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37584 - More Than a Score: Reinforcement Learning with Verbalized Feedback for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.22410 - Where Is the Cost of Third-Party API Routers in Agentic Software Development? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23624 - RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23466 - Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18397 - Language Models Can Rewrite Their Own Weights Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.21885 - MAVE: Reconstructing Editable 3D Blockouts from Film Shots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22464 - A Hybrid Exact-Heuristic Solver for the Integrated Passenger and Parcel Transportation Problem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22043 - Anticipating or Speculating? Making Futures Pay in AI Ethics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22268 - MillBill: A Machining Agent with Geometric Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22565 - Think Once, Act Fast: Cost-Effective Recursive Self-Improvement for Decision Model Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22432 - CADMAGEDDON: High-Fidelity CAD Reconstruction with Local Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22563 - Multi-Agent Memory Inconsistency: Where Factual Conflicts Disappear in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22245 - Regularizing Treatment Leakage for LLM-based Uplift Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.20794 - HealthCLBench:Evaluating Context Learning in Health Conversations through Controlled Case Clusters Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.22362 ## Community - llm-gemini 0.38 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Nov/18/llm-gemini/ - datasette-arrows 0.1a0 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Nov/18/datasette-arrows/ - Quoting Daniel Stenberg Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Nov/18/daniel-stenberg/ - The PSF end-of-year fundraiser Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Nov/18/psf-end-of-year-fundraiser/ - Anthropic sets share price at $83 for stock market debut, above expected range Source: hacker-news Topic: General (+AI) URL: https://www.theguardian.com/technology/2026/nov/18/anthropic-share-price-stock-market-ipo - Anthropic prices initial public offering Source: hacker-news Topic: General (+AI) URL: https://www.anthropic.com/news/anthropic-prices-initial-public-offering - U.S. School Districts Weigh Breaking Up with Google Search over A.I Source: hacker-news Topic: General (+AI) URL: https://www.nytimes.com/2026/11/18/technology/google-gemini-ai-search-schools-nyc-la-chicago.html - Anthropic reportedly prices its IPO at $83 per share, valuing at $1.5T Source: hacker-news Topic: General (+AI) URL: https://apnews.com/article/anthropic-ipo-pricing-70b660ddf900d90bbf484ecdf1fb441c - LLM assisted reverse engineering Source: hacker-news Topic: General (+AI) URL: https://www.slowchronicle.com/posts/llm-assisted-reverse-engineering - Gemini 4 Neon Source: hacker-news Topic: General (+AI) URL: https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-neon/ - The Codex Sandbox Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/inside-the-codex-sandbox/ - Anthropic promises to pursue human benefit. Its IPO filing gives it wiggle room Source: hacker-news Topic: General (+AI) URL: https://apnews.com/article/anthropic-ipo-public-benefit-corp-a2a04c9bcf681c1b46b13607171c83b4 - Just say no to Anthropic's IPO Source: hacker-news Topic: General (+AI) URL: https://garymarcus.substack.com/p/just-say-no-to-anthropics-ipo - Advancing chip design with OpenAI models Source: hacker-news Topic: General (+AI) URL: https://openai.com/index/advancing-chip-design-with-our-models/ - "Anthropic Is Not a Safe AI Company" – Coalition Challenges Anthropic Safety Source: hacker-news Topic: General (+AI) URL: https://www.businesswire.com/news/home/20261118974464/en/Anthropic-is-Not-a-Safe-AI-Company---Broad-Coalition-of-Scientists-Legal-Scholars-and-Tech-Leaders-Challenge-Anthropics-Safety-Branding-Ahead-of-IPO - Amazon and Google will together own nearly 30% of Anthropic after its IPO Source: hacker-news Topic: General (+AI) URL: https://techcrunch.com/2026/11/17/amazon-and-google-will-together-own-nearly-30-of-anthropic-after-its-ipo/ - Jensen Huang's fall hits 'open' models in boost to Anthropic and OpenAI Source: hacker-news Topic: General (+AI) URL: https://www.ft.com/content/418ca885-fbcf-4b9f-a8b9-2bd60b543fc5 - A 4.5M-parameter TTS model runs 70x real-time on CPU and cost just $10 to train Source: hacker-news Topic: General (+AI) URL: https://huggingface.co/n4ze3m/tiny-voca - LLMs can read and write executables byte by byte from a hex dump Source: hacker-news Topic: General (+AI) URL: https://sgiannopoulos.github.io/blog/machine-code-programming/ - Why is Gemini 4 Carbon taking so long? Source: hacker-news Topic: General (+AI) URL: https://kernel.dev/blog/why-is-gemini-4-carbon-taking-so-long/ ## Media - What is the Elephant-Goldfish Model (EGM)? Fresh-eyes AI review for specs and code Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/watch?v=6P1polyfAqM - What is native multilinguality? 🍿 Just a moment #03 Source: youtube-googlecloud Topic: AWS (+AI, Cloud, General) URL: https://www.youtube.com/watch?v=oImvnR5-IUI - How we optimize GitHub Copilot for every new model Source: youtube-github Topic: Open Source (+AI, General) URL: https://www.youtube.com/watch?v=JSC8eVojIWY