TILens Daily Edition 2026-09-18 Filters: topic=ai, github=hidden Stats: 688 articles, 26 sources, 641 research papers Top topics: AI, AI Research, Information Retrieval ## News - Partnering with Accenture on embedded evaluation Source: anthropic-blog Topic: AI Labs (+AI) URL: https://www.anthropic.com/news/accenture-embedded-evaluation - Should you read the code, is RAG dead, and did Skills kill MCP? Source: github-blog Topic: Open Source (+AI) URL: https://github.blog/ai-and-ml/should-you-read-the-code-is-rag-dead-and-did-skills-kill-mcp/ - Introducing the Australian Youth Safety Blueprint Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/australian-youth-safety-blueprint - Anthropic is operating a lab that conducts biology experiments Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/18/anthropic-is-operating-a-lab-that-conducts-biology-experiments/ - AI hallucination nearly triggers US military operation Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/18/ai-hallucination-nearly-triggers-us-military-operation/ - Anthropic’s first embedded evaluator is … Accenture? Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/18/anthropics-first-embedded-evaluator-is-accenture/ - Anthropic decides to support OpenAI's markdown instructions spec Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/09/18/anthropic-decides-to-support-openais-markdown-instructions-spec/5297588 - Microsoft agentically ports Copilot runtime to Rust for $120K Source: theregister Topic: General (+AI) URL: https://www.theregister.com/devops/2026/09/18/microsoft-agentically-ports-copilot-runtime-to-rust-for-120k/5297549 - High-Performance In-Memory Graph Processing in Node.js: Zero-Hallucination Neuro-Symbolic AI Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/programmingcentral/high-performance-in-memory-graph-processing-in-nodejs-zero-hallucination-neuro-symbolic-ai-3ioa - Repairo: Stop Breaking Builds When Vendor OpenAPI Specs Update Source: devto-javascript Topic: JavaScript (+AI, PostgreSQL) URL: https://dev.to/adityacs50lab/repairo-stop-breaking-builds-when-vendor-openapi-specs-update-2h1o - Claude couldn’t hack OpenAI. Then Anthropic shipped Opus 5. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/claude-exploits-openai-forum/ - Researchers used Claude to hack OpenAI employees' ChatGPT accounts Source: theregister Topic: General (+AI) URL: https://www.theregister.com/security/2026/09/18/researchers-used-claude-to-hack-openai-employees-chatgpt-accounts/5297517 - Dario Amodei and other AI leaders want to ‘Pace the Frontier’ but…how? Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/video/dario-amodei-and-other-ai-leaders-want-to-pace-the-frontier-buthow/ - ⚡ Dev lifehack: Base64 Image 🧰 (Free · No Signup) Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/codepackr/dev-lifehack-base64-image-free-no-signup-254b - Meta's less-creepy smart glasses Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/meta-less-creepy-smart-glasses - Who Grades the AI Tests? Epoch Found Problems in Nine Major Benchmarks Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/epoch-ai-benchmark-reviews-nine-flawed/ - Researchers used Anthropic’s Claude to hack into OpenAI Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/09/18/researchers-used-anthropics-claude-to-hack-into-openai/ - The OpenAI Hack Shows Why Every AI Connection Needs Limits Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openai-hack-ai-connection-limits/ - DoorDash Uses Multi Agent LLMs to Clean up 60,000 Feature Flags Source: infoq-architecture Topic: Architecture (+AI) URL: https://www.infoq.com/news/2026/09/doordash-feature-flag-cleanup/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Architecture+%26+Design - Security updates for Friday Source: lwn Topic: Open Source (+AI, FastAPI, PostgreSQL, Python) URL: https://lwn.net/Articles/1095219/ - Open-weight models now handle a majority of tokens on Vercel’s AI Gateway. But Anthropic still takes 64% of the spend. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/open-weight-anthropic-spend/ - Could AI really kill us all? Your questions, answered. Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/09/18/1144435/could-ai-really-kill-us-all-your-questions-answered/ - Astra Decoded a 1918 WWI Message. The Evidence Spans Archives. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/astra-1918-wwi-message-recovery-evidence/ - Inside OpenAI's log of misbehaving models Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/inside-openai-log-of-misbehaving-models - 😺 OpenAI Cracked an Old Riddle Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/openai-cracked-an-old-riddle/ - Anthropic Says Claude Leads 26% of Its AI Research. The Bigger Story Is Who Sets the Metric Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/anthropic-claude-leads-26-percent-ai-research-metric/ - World Labs’ Atlas Can Build 3D Worlds From a Few Images. The Hard Part Is Knowing What It Invented. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/world-labs-atlas-3d-worlds-what-it-invented/ - How AI Cracked an 85-Year-Old WWII Enigma Message Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/explainer-articles/how-ai-cracked-85-year-old-wwii-enigma-message/ - I built 59 free browser-based dev tools in vanilla JS — here's what I learned Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/yuvaraj_radhakrishnan_224/i-built-59-free-browser-based-dev-tools-in-vanilla-js-heres-what-i-learned-5gj8 - Hacking OpenAI 👨‍💻, Claude leads R&D 🤖, Safari MCP 🌍 Source: tldr-tech Topic: General (+AI) URL: https://tldr.tech/tech/2026-09-18 - Why Lovable built a Vite-compatible dev server in Rust Source: react-status Topic: React (+AI, JavaScript) URL: https://react.statuscode.com/issues/491 ## Research - MilleMiglia: A realistic instance generator for middle-mile logistics Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/millemiglia-a-realistic-instance-generator-for-middle-mile-logistics/ - Coding Agents Keep Shipping Silent Failures — Here Is How to Catch Them Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/coding-agents-keep-shipping-silent-failures-here-is-how-to-catch-them/ - We Pinned Our Model Version to Stay Safe. The Provider Deprecated It Anyway. Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/we-pinned-our-model-version-to-stay-safe-the-provider-deprecated-it-anyway/ - Starting a Career in Data Science in the Age of AI Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/starting-a-career-in-data-science-in-the-age-of-ai/ - Multi-Agent Coding Isn’t Enough — Agents Need a Commitment Layer Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/multi-agent-coding-isnt-enough-agents-need-a-commitment-layer/ - MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20747 - Epidemiological Causal Graph Identification: Challenges, Identifiability and Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20676 - Building a Neural Network from Scratch: Implementation, Evaluation, and Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16682 - L2R: Low-Rank and Lipschitz-Controlled Routing for Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21349 - FedFIbOS: Fisher Importance based Optimal Submodelling for Heterogeneous Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19559 - Labeled Incidence Structures for Native Transformer Modeling of Text, Knowledge Graphs, and Hypergraphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20278 - Randomized SVD Approximations for Spectral Co-Clustering of Word-Document Matrices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19243 - Near-Optimal Machine Unlearning Utility for Smooth Strongly Convex Losses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01527 - CrystalMO-TuRBO: Multi-Objective Trust-Region Bayesian Optimization for High-precision Joint Crystal Structure Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20592 - Training Neural Networks to Approach the Optimum Bayes Estimator in Dense Multi-Emitter Localization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20465 - Optimal Value Inference for Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.09981 - Learn Your Own Thoughts: Abstract Token Curriculum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19717 - MATCH: Model-Aware Tool Learning with Curriculum Scheduling and Hierarchically Gated Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20082 - Pre-train to Gain: Robust Learning Without Clean Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.20844 - Calibrated RF-Fingerprinting Under Interference With Heterogeneous Transmission Protocols Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20765 - Curvature Cryptanalysis of Smooth Transformer Feed-Forward Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28843 - ZeroHAT: Behavior-Conditioned Zero-Shot Human Activity Trace Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20310 - Watermarking Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.24368 - Resolution limits for process comparison from event data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20489 - VGAS: Variance-Reduced Guidance and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26585 - Graph-Based Stochastic Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19956 - Layer-wise Curriculum Learning for Efficient LLM Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19213 - Local Sparsity Enables Unsupervised LLM Safety Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20129 - Perturbing the Phase: Analyzing Adversarial Robustness of Complex-Valued Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06577 - A Transferable Learned Temporal Prior for Transmission Reconstruction and Decision-Relevant Uncertainty in Real Outbreak Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30842 - Perspective of Software Engineering Researchers on Machine Learning Practices Regarding Research, Review, and Education Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.19304 - Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16462 - Block Parallelism For Efficient Distributed Long-Context Diffusion Language Model Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19242 - How Far Can Sub-3B Open Language Models Go in Zero-Shot Essay Scoring on an 8 GB Consumer GPU? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20250 - Adversarial Water-Filling: Theory, Algorithms, and a Domain-Specific Wireless Foundation Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26163 - Not All Layers Need Tuning: Diagnosing and Directing Adaptation in Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18084 - LayerRoute: Action-Conditioned Mixture-of-Layers Routing for Vision-Language-Action Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06079 - Quantifying Overclaiming Propensity in Frontier LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20812 - The Complexity Kink: A Prompt-Side Structural Complexity Index for Code-Generation Reliability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19616 - SETTer: Sparse-Encoder Transformer for Long-term Multivariate Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20086 - Enabling automatic transcription of child-centered audio recordings from real-world environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.11747 - Mitigating Retaliatory Algorithmic Collusion in Repeated Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20548 - Noise-Robust Quantum State Characterization for Remote State Preparation with Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20523 - LEO Satellite Internet of Things: Architecture, Technology, and On-Orbit Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20165 - One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady State Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19955 - Unexplored flaws in multiple-choice VQA make benchmarking unreliable Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.22341 - Hypernetwork-Parameterized Spatially Adaptive Neural Operators for PDE Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20309 - DRL-AdaPart: DRL-Driven Adaptive STAR-RIS Partitioning for Fair and Efficient Resource Utilization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.06868 - PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20794 - Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19476 - Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21653 - Counterexamples and Sufficient Conditions: Comments on "Optimally-Transported Generalized Method of Moments" Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20260 - NeuroFlex: Lossless Element-Level ANN-SNN Co-Execution for Efficient Sparse Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14092 - Interpretable and Calibrated Classification of Clinical Data Using Supervised Feature Binarization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15394 - Scalable Policy Optimization for Networked Multi-Agent Reinforcement Learning with Continuous State-Action Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18554 - Genetic algorithm vs. gradient descent for training a neural network architecture dedicated to low data regimes in small medical datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27411 - Explaining spatial information flow in short-term traffic forecasting models using a gated graph attention network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20217 - Spending Scarce Confirmatory PET Measurements: Target-Aligned Validation in A4/LEARN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22223 - Elastic Spectral State Space Models for Train-Once Budgeted Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22488 - Learn2Drive: A neural network-based framework for socially compliant automated vehicle control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.21736 - Post-Boundary Bridge: Must Local Attention Go Global Between Global Layers? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02680 - Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19164 - When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20511 - Federated Soft Clustering via Generalized Total Variation Minimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19202 - Evaluating Financial Sentiment in the Age of AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20198 - Score Centering Stabilizes Off-policy Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20807 - A Quantum/Classical Example Oracle Separation for Making Things Up Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11648 - Attributing Preprocessing Invariance in Spectral Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14227 - Special Lagrangian cones in Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20159 - MoRE: Mixture of Reused Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18176 - EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16692 - AURA: Adaptive Uncertainty-Routed Analysis for Email Threat Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19873 - Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17652 - Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14962 - COMPASS: Ordered Clustered Routing at 100K Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20352 - dQwen3.5: Hybrid-Attention Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20751 - Prompt-Driven Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08837 - Can Vision-Language Models Judge Olympic Diving? From Reasoning to Scores in Zero-Shot Action Quality Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19354 - Spherical Cauchy Variational Autoencoders: Heavy Angular Tails and Exact KL Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.21278 - How to Guide Your Language Flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19356 - Reinforcement Learning for Graph Generation under a Hard Assortativity Constraint Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23285 - A Policy Profile for Croissant: Refusal as a Property of the Dataset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19640 - Accuracy Is Not Enough: A Cross-Architecture Audit of Demographic Bias in Deep Knowledge Tracing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20249 - Clin-JEPA: A Multi-Phase Co-Training Framework for Joint-Embedding Predictive Pretraining on EHR Patient Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10840 - Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02998 - Mammography Foundation Models for Opportunistic Prediction of Major Adverse Cardiovascular Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19385 - Fast-varying Natural Frequencies and Damping Ratio Identification for Linear Time-Varying System Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20138 - The Bias of Nonlinear Two-Time-scale Stochastic Approximation under Constant Step-Sizes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20409 - Beyond PINNs: A Unified Gauss--Newton and Petrov--Galerkin Framework for Neural and Hybrid PDE Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20641 - SoftTri: Smooth Triangular Membership Functions for Adaptive Fuzzy Inference Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20194 - VLN on the Fly: An Onboard Vision-Language Navigation Stack for Aerial Robots Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20191 - Learning-Based Reconstruction of Optical Properties in Bilayered Media from Single-distance Time-Resolved Reflectance Measurements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19786 - Delphi Scanner: efficient and interpretable static malware detection via API sequence modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19900 - When Does Retrieval Help Time-Series Forecasting? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20193 - Distributionally Robust Federated Learning with Multi-Source Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20501 - D$^3$-MOPD: Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24987 - Deep Learning-Based Classification of Cognitive and Resting States Using Electroencephalography Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20467 - DeltaSelect: Affordable A/B Testing for Coding Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19607 - Transformer fault diagnosis using an efficient simulation-driven variational quantum classifier with domain-aware feature encoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20214 - The Environmental Impacts of Language Model Training Keep Rising Now is the Time to Catch Impacts on the Rebound Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.09022 - Conservation Buys Stability and Factoring Buys Counterfactuals in Physical World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19674 - Parallelism, critical windows, and separations among diffusion language models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20539 - Accelerating Q-learning through Efficient Value-Sharing across Actions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29806 - R2DN: Scalable Parameterization of Contracting and Lipschitz Recurrent Deep Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.01250 - EssentialGIN: a new approach for gene essentiality prediction based on graph isomorphism neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07700 - GigaBrain-WBC-0.5: A Behavior World Model for Robust Humanoid Whole-Body Tracking with Environment Interaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18234 - MAPLE: Metadata Augmented Private Language Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19258 - HyperAMS-Net: Adaptive Multi-Scale Spatial Hypergraph Network for Brain Disorder Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19755 - AI-Driven Real-Time Relay Optimisation in Smart Urban NR-V2X Networks via Learning-to-Optimise Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20271 - TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20693 - Intrinsic Sequence-Likelihood Confidence in Retrieval-Dominated Extractive QA: Two Pre-Specified Negatives, and What They Do and Do Not Attribute Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19942 - VisKG-LM: Compiling Knowledge Graphs into Visual Memory for Multiple-Choice Question Answering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19158 - Sharpness-Aware Minimization (SAM) Improves Classification Accuracy of Bacterial Raman Spectral Data Enabling Portable Diagnostics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19453 - Learning Submanifolds for Subsequent Inference on Random Dot Product Graphs, Part 1: Theory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19357 - Information-Geometric Inverse Distillation for Enhancing Adversarial Transferability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.17003 - Interactive proofs for verifying (quantum) learning and testing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.23969 - Null importance: Disentangling relevance for interpretable machine learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19511 - EviRec: Continual Evidence Learning for Dual Cold-Start POI Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20313 - An Empirical Study of Harness Design for Coding Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20804 - Steering Equilibrium Selection in Regularized Self-Play via the Reference Policy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19820 - When fairness metrics fail: A utility-based perspective on $\varepsilon$-fairness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.09360 - Smart Insole Human Activity Recognition for Continuous Monitoring in Elderly Care Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19359 - Evaluating Explanation Methods by the Predictors They Induce Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20058 - Relational Attention for Data-Efficient Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20530 - A Noise Optimum in Rehearsal-Free Continual Learning: Isolation, Mechanism, and Scope Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20162 - Is It Still Worth Training a Classical Model in the Era of LLMs? A Crossover Benchmark on Tabular Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20218 - Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20744 - Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.06734 - Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19878 - Machine-Learning Assessment of the Predictive Value of Inflammatory Biomarkers for Cognitive Impairment in an Older Hispanic Adult Cohort Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19374 - PhyRestore: Physics-Structured Latent-Factor Restoration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19776 - How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19107 - OceanMoE: Structured Conditional Sparse Computation for Long-Horizon Multivariate Ocean Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19768 - Improving Generalization and Robustness in Offline Reinforcement Learning via Boundary-Aware Data Augmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20300 - Beyond On-Policy Exploration: Integrating External Policy Rollouts for Reinforcement Learning in Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01717 - A Generative-AI Modeling Framework for Explainable Decision Support in Complex Geosteering Scenarios Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.08509 - A Table-Free Index for Tapered Memoization Grids: Compact Out-of-Core Evaluation of Functions of Sorted Arguments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20276 - Multi-Resolution Attribution from Adaptive Routing State Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22866 - Why Pretraining Fails to Share Cross-Lingual Knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19291 - Detecting Deceptive Recruitment: A Signal-theoretic Machine Learning Framework for Early Identification of Labour Exploitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20336 - A Large-Scale Vision-Language Dataset Derived from Open Scientific Literature to Advance Biomedical Generalist AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.22727 - Reference-free logged energy-oracle recovery for neural approximations of symmetric coercive variational problems: conforming Riesz reconstruction and archive-level selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16473 - Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20650 - Stringological sequence prediction III: layered ziplines and a tradeoff between efficiency and expressivity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19940 - Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20575 - Generative Query Suggestion via Intent Coverage and Query-Level Credit Assignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19209 - Sequential Contextual Fit Predicts Human Behavioural and Neural Dynamics Across Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20179 - Self Improvement via Fast Tree-search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19526 - Faithful, Not Corrective: Model Capability Governs Message-Format Effects in Multi-Hop Agent Relays Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09678 - Traffic Engineering in Large-scale Networks with Generalizable Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.24203 - Chain-of-Thought Entropy as a Reliability Signal: A Preregistered Reproduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19606 - Measurement Under Selection: Decoy-Calibrated Failure Audits for Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09046 - The Output-Space Hypothesis: Enumerative Equivalence Checking for Tensor Programs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19611 - Quantum Graph Convolutional Networks: Implementation and Trainability Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19983 - Estimation of multiple mean vectors in high dimension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.15038 - CatchBench: When Can an Agent Failure Be Caught? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22808 - Double descent is the principle of least action Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19076 - Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression Proxies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19844 - Enhanced Agriculture-informed Neural Network by Domain Knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19466 - LLM-as-an-Improver: Turning Verification into Better Candidates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19515 - COIN-GP: Cooperative Online Learning in Networked Distributed Systems with Partial Measurements via Gaussian Process Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20598 - A Learning Algorithm for Threshold Boolean Networks with Prescribed Fixed Points Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20298 - Subdomain-aware representation compression for pretrained image embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20213 - Improving Offline Goal-Conditioned Reinforcement Learning via Selective Reward Stimulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19414 - GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20776 - GLAMDRING: Gait Learning And Morphology co-Design via Reinforcement LearnING of CPGs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19452 - Stable Policy Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19418 - SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.11729 - Digital Twins for Opinion Dynamics: A Generative LLM Framework for Social Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19913 - Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in LLM Activations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19150 - Online Supervised Dimension Reduction with Random Features: Diagnostics and Computational Trade-offs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20454 - Learning Principal-Agent Contracts for Equitable Smallholder Carbon Farming under Moral Hazard and Adverse Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20404 - Demystifying Linear Operator Learning for Control Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19428 - Error bounds in Sobolev norms for approximations with norm constrained ReLU neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19937 - When Faster VLA Deployment Changes Closed-Loop Behavior: Task Success-Latency Analysis of SmolVLA Across PyTorch and ONNX Variants Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14146 - Dynamic Generalized Gromov-Wasserstein Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20008 - Exploring Sparsity and Smoothness of Arbitrary Lp Norms in Adversarial Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06578 - UniExo: Unified Multi-Skill Policies for Musculoskeletal Locomotion and Co-Adaptive Exoskeleton Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19690 - Ambient Dataloops: Generative Models for Dataset Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15417 - Pretrained Medical Representations for the Practical Screening of Drug Repositioning Candidates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19865 - PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19657 - Green-ELM: Efficient Analytic Learning via High-Dimensional Random Projections Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15613 - Scene-Conditioned Relation Routing for urban cellular activity forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20209 - Transcriptomic Models for Immunotherapy Response Prediction Show Limited Cross-cohort Generalisability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05478 - When Data Imbalance Helps: Robust Generalization Through Shortcut Saturation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10116 - PaGNet: A Panel-Aware GBDT--Neural Network for Multi-Target Corporate Tax Avoidance Proxy Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20177 - Small Enough to Know Everything: The Fully-Enumerable Transformer as an Instrument for the Science of Delayed Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20166 - Bayesian Optimization with Rich Auxiliary Information via LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19437 - Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20761 - Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20758 - TorchCraft: Unified binder design by inverting an all-atom structure predictor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19770 - QoS-Aware Federated Learning for Multimodal In-Cabin Interaction in Smart Vehicles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20123 - Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19472 - Sharp Reconstruction Bounds for Autoencoders Using the Same Forward Map Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20333 - Improving Online Reinforcement Learning via Bidirectional Behavior Prior Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20268 - Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19499 - Stiefel Attention: When the Geometry of Transformer Projection Matrices Dominates Optimizer Choice---and When It Does Not Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19363 - Correct Now, Insufficient Later: Auditing Update Sufficiency in Context Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20045 - Personalized Federated Hierarchical Gaussian Processes for Privacy-Preserving Modeling of Heterogeneous Distributed Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19337 - The First-Order Oracle Complexity of Lipschitz Convex Optimization in Nondual Settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20687 - CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19970 - Radio Frequency Detection and Classification of Microplastics in Water Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20507 - FOCAL: Fine-Grained Optimal-Transport-Driven Contrastive Alignment of Language and ECGs with Waveform Enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.11939 - Intact-to-Amputee Transfer in Surface-EMG Gesture Decoding: Training Source and Calibration Budget Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20297 - Neural Langevin Machine: a local asymmetric learning rule can be creative Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.23546 - TTSR: Test-Time Self-Evolving via Reflection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03297 - Automated Membership Inference Attacks (AutoMIA): Discovering MIA Signal Computations using LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19375 - Beyond Flattened Tokens: Structure-Preserving EEG Decoding with Reusable TriDim Blocks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19842 - FCx: An algorithm for finding Feasible Counterfactual Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19383 - Model-Aware Data Cleaning for Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25154 - Teach and Grow: An Agent-Centered Architecture for General Robot Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17209 - Fast Cross-Strength Multi-Contrast Brain MRI Translation using Latent Bridge Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20341 - Correlation-Free Transition Path Sampling through Shooting Point Generation Guided by Committor Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20461 - Placement Is Free, Composition Is Not: The Latin Square as a Provably-Balanced Construction for Heterogeneous Sequence-Mixer Stacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20269 - QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04620 - ALIBI: Adversarial Legitimacy Injection in Binary Input against LLM Malware Analyzers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19722 - REARL: A Closed-loop Autonomous Driving Simulation Enhancement Framework with Real Traffic Data and Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19903 - Subliminal Prompting Beyond Static Geometry: Causal Depth and Multi-Token Confounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19149 - QEncodeBench: Can Large Language Models Encode Classical Problems into Verified Quantum Oracles? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20319 - Truncated automatic sparse differentiation for machine learning interatomic potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20510 - From Models to Systems: A Comprehensive Survey of Efficient Multimodal Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19445 - EmbodiedMind: Adaptive Data Curation and Prefix-Tree Reinforcement Learning for Efficient Embodied Intelligence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19659 - Seismic Site Response Prediction from Sparse Observations Using Finite-Element-Pretrained Latent Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20451 - SCGFM-ART: Amortized Relational Transport for Structure-Centric Graph Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20419 - Task-Directed Residual AddUNet:Perfect-Reconstruction Routing for Full-Rate Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15857 - SAGG: Sample-Adaptive Gradient Gating for Robust Multimodal Learning under Heterogeneous Corruption Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20302 - QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20156 - PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20653 - Online Adaptive Kernel Mixing for Gaussian Process Decision Making Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19891 - CARE-VI: Conservative Adaptive Reliability Estimation for Value Improvement in Off-Policy Actor-Critic Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20098 - An Architecture for Long-Horizon Agents: Levels, Ticks and Cascaded Intelligence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19519 - Stop Removing Stopwords: How an Inherited Preprocessing Default Distorts Legal Text-as-Data Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.19153 - Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19203 - The Life of a Token: from Words to Bits on the Wire Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19924 - Next-token functional estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19529 - Compressed Active Subspaces for Scalable Bayesian Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19539 - Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19915 - RISC-V and machine learning: a survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20677 - Low-rank Orthogonalization for Large-scale Matrix Optimization with Applications to Foundation Model Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.11983 - Not All Nodes Are Created Equal: Homophily-Aware Stratification for Stable GNN Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19210 - CoRe: Coherence and Relational Alignment for Multivariate Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19670 - Poodle: Seamlessly Scaling Down Large Language Models with Just-in-Time Model Replacement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.05525 - Near-Optimal Pure Single-Loop Extragradient Method for Strongly Convex--Strongly Concave Minimax Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20327 - Model-based Bootstrap for Offline Policy Evaluation in Tabular Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20389 - Paint-Anything: Unified Any-Color Control for Image Generation and Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20816 - Alliance Beats Isolation: Unifying Heterogeneous Allied Datasets Improves Classifier Performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19748 - Embedding Models Measure in Peculiar Ways Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20821 - TinyCNN: A 193K-Parameter Network for On-Device Plant Disease Detection, with a Cross-Dataset Robustness Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20290 - Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20715 - Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19985 - High-Resolution Range Profile Classifiers Require Aspect-Angle Awareness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00087 - SGM: A Statistical Godel Machine for Risk-Controlled Recursive Self-Modification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.10232 - Towards a Unified Modality-Agnostic Multimodal Framework for Cognitive Workload Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20199 - From "Who Is This User?" to "What Does This Purchase Mean?": A Deployed Pipeline for Semantic User Profiling at Bank Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19928 - Deep Learning Detection of Beyond-General-Relativity Deviations in Gravitational-Wave Signals: A Detection-Threshold Study with Real LIGO Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19416 - Odds-Ratio Thompson Sampling: A Specification and Design Guide for Contrast-Based Multi-Armed Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19709 - Do LLM Attribution Metrics Transfer? Auditing Retrieval-Augmented Generation Evaluation Across Datasets and Constructs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23915 - Sparse Data Augmentation for Optimization with Provable Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08133 - Stable Movement for Nondual Lipschitz Convex Optimization: Efficiency and Nearly Optimal Oracle Rates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20701 - QVAC Genesis III: A Large-Scale, High-Quality Open Synthetic STEM Corpus for Efficient Language Model Pre-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19513 - Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10330 - A Finite-Sample Analysis of Quantile Temporal-Difference Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27313 - When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19671 - DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19801 - Robust Federated Q-Learning with Almost No Communication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20174 - TAP Accuracy Below the Fluctuation Scale and Universal Posterior Geometry in Spherical Linear Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20577 - Score-based diffusion models for severely ill-posed problems in diffuse optical tomography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03449 - Batch Normalization Amplifies Memorization and Privacy Risks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24420 - Learning-Induced Dynamical Transition in Recurrent Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19288 - Comparison of Image Processing Models in Quark Gluon Jet Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00141 - Compositional Reasoning in Language Models under Reinforcement Learning Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19465 - An Efficient and Modular Framework for Targeted Harm Mitigation in LLMS Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13624 - ResNLS: An Improved Model for Stock Price Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2312.01020 - NS3Learn: Transferring 5G NR Mode-2 Reception Realism from ns-3 to the Veins/SUMO Stack for Connected-Vehicle Safety Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20578 - Personalising a Cross-User Surface Electromyography Encoder Under a Small Calibration Budget Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20296 - A Network Science Approach to Granular Time Series Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.17640 - Evolution or Illusion? Rethinking Evaluation in LLM Evolutionary Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19799 - Precision autotuning for linear solvers via contextual bandit-based RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00728 - Task-Oriented Semantic Feature Transmission for Multi-Task Satellite Remote Sensing over Low-SNR Channels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20150 - Expected Hypervolume Maximization for Multiobjective Optimization under Uncertainties Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19858 - Sufficient Decision Proxies for Decision-Focused Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.03953 - When Retrieval Metrics Mislead: Measuring Policy Signal in Long-Horizon Tool-Use Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23937 - TacSushi: Tactile-Grounded World-Action Modeling for Dexterous Sushi Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19613 - When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24077 - Physics-Informed Support Vector Kernels via Green-Function Analogies and Jackson-Chebyshev Spectral Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.11153 - Recovering Governing Dynamics from Distributed Observations via Exact Spline Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16579 - Self-Replicating Neural Cellular Automata: Quantifying Emergent Phenotypic and Genotypic Diversity in an OpenEnded Substrate Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19902 - LSTM-UT and Recurrent-Depth Transformers on Cellular Automata Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19521 - Support Thresholds, Not Algorithms, Limit Rare-Association Recovery in Co-Purchase Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20171 - Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16812 - Well-posedness of neural turbulence closures and tangent dissipation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19647 - How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20814 - Recursive Quantum Long Short-Term Memory for Stable Short-Horizon Temperature Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20594 - Minimax-Optimal Online Contract Design with Unrestricted Bounded Contracts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20353 - Radio-Frequency Convolutional Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19279 - SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08372 - OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20756 - CliniCIRCA: A Modular LLM Framework for Constructing Longitudinal Mental Health Patient Journeys from Raw EHR Narratives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19585 - Exploring a Layer-Wise Design Space for KV Cache Eviction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15157 - A Computational Tropical Geometry Framework for Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2405.20174 - Opinion Dynamics-based Coalition Formation for Federated Learning in Heterogeneous IoT Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19695 - On the Inherent Privacy Amplification of Missing Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01928 - EPIG-Tree: Compute-Optimal Branching for Gradient-Efficient Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20004 - Cross-Architecture Foundation-Model Distillation for Edge Flood Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20441 - Learning to Theorize the World from Observation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03413 - Why $\beta_1 = \beta_2$ Is Dynamically Special in Adam Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21739 - Out-of-Sample Embedding with Proximity Data: Projection versus Restricted Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.06756 - Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04663 - Federated Learning Framework for Privacy-Preserving Kidney Stone Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19740 - The Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.20050 - Can We Do Interpretable NLI with Graphs Based on Atomic Propositions? Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.16814 - Beyond Private Training: The New Landscape of AI Privacy Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19456 - Beyond Similarity through Zero-Token Geometric Graphs for Multi-Hop RAG Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19622 - FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.20175 - MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2509.01184 - Algebraic Retrieval: Composable Search for Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19482 - FootprintRAG: Visual Analytics for Evidence Context Refinement in RAG-based Scientific Literature Exploration Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19601 - Characterizing Web Search by Conversational LLM Agents: From Search Decisions and Strategies to Results and Responses Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19244 - Viveka-Insight: a cross-lingual concept graph and citation-grounded retrieval resource over the complete works of Swami Vivekananda in English and Bengali Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.20303 - Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoning Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.06027 - Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2506.17277 - Reasoning Quality Matters: Combating Reasoning Collapse in LLM-based Embedding Learning Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.20563 - FINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19680 - SCOUT: Sim-to-Real Text-Based Person Retrieval by Embedding-Space Prediction over Frozen Video Features Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19483 - What Users Think of Generative AI: A Cross-Platform NLP Analysis of Trust and Friction in App Store Reviews Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19151 - Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Reranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.20131 - SPAR: Enhancing Industrial-Scale Generative POI Recommendation via Real-World Spatial Perception Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.02062 - Semantic Layer Induction from Raw Telemetry via Hierarchical LLM and RAG Abstraction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19615 - Time-Aware Diffusion based on Preference Disentanglement for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.01670 - Dense Feature Representation over Sequence Modeling: A Solution to the KDD Cup 2026 UniRec Challenge Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19787 - Self-Evolving Search Index Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19656 - The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side Intrusion Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.25245 - Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.19831 - Reverse Neighbor Sliding and Order Selection for Efficient Multi-Proximity Graph Merging Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2602.17099 - Spectral Gap of Down-Up Walks via Trickle-Down: A Simplified and Sharpened Analysis Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2609.19514 - Quantum Speedups for Log-Concave Sampling from Local Structure Source: arxiv-cs-ds Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2609.20253 - LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.03405 - Generalization through Lexical Abstraction in Transformer Models: The Case of Functional Words Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19887 - FakeSpotter: A content and strategy agnostic Viral Misinformation Detection Tool Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19152 - Redemption Score: A Multi-Modal Evaluation Framework for Image Captioning via Distributional, Perceptual, and Linguistic Signal Triangulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.16180 - KoNeoBench: A Curated Evaluation Dataset for LLM Understanding of Korean Neologisms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19916 - Less Is More: Graph-free Multimodal RAG via Multi-signal Late Fusion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19417 - On-Demand Attention: Language Models Know When to Recall Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20734 - Edustories: A Collection of Real-world Case Studies from Classroom Practices Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20484 - Message capacity and claim wording set the transition points of collective truth-finding in language-model networks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19183 - Improving Cross-Lingual Transfer for Sequential Sentence Classification in Research Papers via Structural Similarity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19650 - How Loud Rumbles Hit Newsstands: A Data Analysis of Coverage and Spatial Bias in German News about Landslides Around the World Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18105 - Unifying Models of Intergroup Hostility in Online Discourse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20808 - Finding Common Ground: Graded Communal Knowledge in Bluesky Starter Packs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19549 - By Their Fruits You Will Know Them: Comparing Formalizations of Law by the Decisions They Encode Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25186 - An Analysis of Training-Free Self-Reported Confidence in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20541 - Automated Gradient-Driven Parameter Sharing for Low-Resource Multilingual Speech-to-Text Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25836 - The Role of Fine-grained Harm Signals in LLM Safety Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19366 - Towards Safer RAG: Only Agents Capable of System 2 Thinking may Access Untrusted Documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17153 - Rollback the World, Keep the Reflection: Rollback-Induced Reflection for Long-Horizon LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18304 - Full-Duplex Speech Models Take the Floor When Asked, Not When Needed Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19596 - JEPA-Anything: Learning Predictive Models across Different Worlds Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20800 - MyMentorLLM: A psychotherapy GenAI environment with multimodal voice/text patients, trainees and experts for deliberate practice Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.25667 - CovR: Coverage-Aware Hardware Verification via Reasoning-Guided Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19189 - SEA-LION-v4.8: A Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18310 - When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05810 - Model-Agnostic and Language-Agnostic Voice Pipeline Improvement for the Agriculture Domain Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20504 - A Cross-Lingual Acoustic Disease-Alignment Framework for Respiratory Health Assessment from Spontaneous Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19398 - A Phonemically Comprehensive, ASCII-Only Romanization Scheme for Thai and Lao: Systematic Cross-Lingual Correspondence and Chinese-User-Friendly Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19736 - CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30175 - Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19155 - F$^{2}$DR: A Fine-Grained Full-Pipeline Reward Framework for DeepSearch Workflows Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.19827 - Chronicle: Cut-Point Replay for Regression Testing of LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20625 - Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17986 - PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13481 - oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.07731 - Marginal utility, matrix factorization, and the Key-Value (KV) cache: a unified information-economic framework for sovereign geo-mining inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20068 - Phoneme-guided TTS augmentation for ASR: A unified pipeline and multilingual evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26697 - PolyJarvis: An LLM-Orchestrated Agent for Automated All-Atom Molecular Dynamics of Amorphous Homopolymers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02537 - When Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent R\'esum\'e Screening Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19530 - TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18748 - M2Tok: Multi-head Multi-codebook Discrete Action Tokenization for Vision-Language-Action Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18259 - Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25595 - ViTOED: A Dataset for Target-Oriented Emotion Detection on Vietnamese Social Media Texts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12776 - Schema-Anchored Latent Reasoning for Semantic Parsing-Based Knowledge Base Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20398 - AI Should Facilitate Democratic Deliberation at Scale Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20059 - LaSR: Context-Aware Speech Recognition via Latent Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00507 - Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07663 - Redact or Keep? A Fully Local AI Cascade for Educational Dialogue De-Identification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18372 - PetriBench: Benchmarking LLM Reasoning over Dynamic State Spaces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19883 - Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11639 - Social Simulacra in the Wild: AI Agent Communities on Moltbook Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16128 - When Perplexity Lies: Generation-Focused Distillation of Hybrid Sequence Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26556 - What Does Privileged Information Add to On-Policy Self-Distillation? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20612 - UniPolicy: Unified Objective-Specific Policies for Generative Search Advertising Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20630 - Decoupled Contrastive Decoding via Expert-Aligned Drafting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12913 - CounselReflect: Opportunities and Challenges for Designing Tools to Support Self-Reflection on Mental Health and Well-Being Conversations with AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29429 - Design of the IBM Granite 5.0 TurboCTC ASR Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20104 - MUSE: A Theory-Harnessed Story Engine for Vibe Narrativizing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15188 - Causal Analysis and Mitigation of Spurious Onsets in Full-Duplex Speech LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13445 - Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19587 - JustMem: Just-Enough Memory Access for Long-Term Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19877 - Reflective Recovery: A Self-Supervised Method for Reasoning by Learning from Mistakes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19156 - Foundations of Stochastic Lexical Calculus: Semantic Descent and Random Dynamics on Probability Simplices Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20207 - Language-model groups overstate consensus when replaying human deliberation on a reasoning task Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20543 - From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15097 - Mitigating Fabrication in Multi-Stage LLM Pipelines for Hiring: An Empirical Evaluation of Prompt Guardrails and Human-in-the-Loop Checkpoints Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26171 - Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11176 - AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19325 - From Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19630 - Compass-v3: Scaling Domain-Specific LLMs for Multilingual E-Commerce in Southeast Asia Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.09121 - To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20186 - YNU-HPCC at SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Using Multiple Prediction Headers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19238 - For Your Eyes Only: Evaluating Coordination Between Isolated Language Model Instances Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19504 - AutoData: Agentic Search for Pre-training Data Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19754 - DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19969 - The Neutral Mask: How Alignment Training Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09735 - Limits of Reliability and Scaling in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14112 - Evaluating Communicative Success in Machine-Translated Conversation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19885 - SlopShape: Identifying AI-Generated Commercial Web Content Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15369 - To Memories and Beyond: From Remembering to Knowing You across Long-Term Multimodal Personal Archives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19167 - What Do We Expect from LLMs? Mapping the Design of LLM Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19182 - Factors Influencing the Emergence of Dependency Length Minimization in Neural Agent Simulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06025 - V\={a}kQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19879 - HerHealthEval: Evaluating Multilingual and Register-Sensitive Understanding of Women's Health Communication Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20684 - PAA: The Probabilistic Allen Algebra: A Generative and Complete Probabilistic Extension of Allen's Interval Relations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20634 - RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20784 - Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15964 - Dictionary-Constrained Grapheme-to-Phoneme for Unsegmented Languages from LLM-Annotated Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19805 - D-Quant: Driftable Entropy Coding for KV Cache Quantization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19880 - Kinship Data Benchmark for Multi-hop Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07794 - RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16900 - TripScore: Aligning LLMs for Real-World Travel Planning via Expert-Calibrated Reward Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.09011 - GeLaCo: An Evolutionary Approach to Layer Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.10059 - Zarya: A Hybrid Autoregressive--Masked Diffusion Language Model with Flexible Training and Dual-Mode Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19868 - Fine-Tuning Models for Biomedical Relation Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20169 - LongWoF-Bench: Evaluating EvoMap Genes for Verifiable Long-Workflow Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23200 - Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19154 - Stress-testing Alignment Midtraining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20412 - Reading Emotions in the Token Space: Discriminative Adaptation of SpeechLLMs for Emotion Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20081 - Before the Warning Comes Too Late: Incremental Phone-Scam Detection from Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20223 - Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20822 - Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01432 - The Public Discourse Corpus (PDC): A Speaker-Attributed Dataset for Valence and Epistemic Modality with Target Speaker Participation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20232 - Benchmarking LLM Compliance with China AI Generated Content Regulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19989 - Modality Discrepancy Transformer for Ambivalence and Hesitancy Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19148 - When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.24651 - Lens: Bringing the Right Semantic Perspective into Focus for Training-Free Multimodal Representation Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20252 - WiC is Not WSD: A Study on LLMs and Lexical Ambiguity Resolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20593 - Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20779 - Summarization Bias: The Directional Collapse of Objective Projection into Told-Mode Labels in Large Language Models --- A Conceptual Framework and Registered Test Protocol Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20712 - BurnRiSc: Toward Non-Invasive Burnout Screening in Open Source from Public Repository Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19422 - Xeno-Interpretability: Investigating the Alien Minds of LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20408 - A frontend-backend architecture for tool calls in full-duplex speech models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19334 - SAFARI: An Industrial Benchmark for LLM-Assisted Hazard Analysis and Risk Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20584 - EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19523 - Form Over Content In Gradient-Based Data Attribution Methods Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19589 - Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19965 - From Parameters to Behaviors: A Survey of Model Fusion for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19553 - Learn Before You Judge: Progressive Knowledge-to-Decision Alignment for Explainable Hateful Meme Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19778 - Geopolitical Divisions Across Languages in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20005 - How Humans and LLMs Read Gender into "Gender-Neutral" Physical Descriptions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16366 - Riemannian--Lorentz Fusion of Vision Transformers and State-Space Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19384 - Steering the Compass: Aligning Dynamic Psychological Counseling Conversations with Cognitive Behavioral Therapy Strategies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20565 - FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18766 - Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19634 - IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29960 - Large Language Model Agents for Evidence Based Genetic Disease Severity Classification Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.19569 - Reproducibility is not construct validity: LLM measurement of institutionally situated communication Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19866 - Diagnose, Recover, Certify: Task Readiness under Hidden Dynamics Changes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20304 - Robust Workflow Generation via Adversarial Learning for Audio Deepfake Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20063 - Physics-Informed Hemodynamic Modeling for Data-Free Prediction and Sparse-Data Assimilation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19290 - TouchSight: Bare-Handed Tactile Prediction from Egocentric Video via Generative Visual Augmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20414 - DataCanvas-EDU: An Agentic Framework for Instructor-Guided Synthetic Data Generation in Business Analytics Education Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19617 - When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29251 - Regularized Emphatic Temporal-Difference Learning: Stability under Constant Stepsizes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19170 - CoMa: Contextual Massing Generation with Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08464 - Can Data Attribution Filter Out Subliminal Learning? Not Reliably Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20027 - Behavioral Coherence: A Method for Sensitive-Domain LLM Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13142 - Architectural Design, Not Only Model Intelligence, Governs Multi-Agent LLM Performance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03128 - The Organization of Inference: Information, Resource Constraints, and AI Production Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20449 - Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19830 - NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20323 - FedVideoMAE: Efficient Federated Video Moderation with Differential Privacy and Secure Aggregation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.18809 - Evaluating Large Language Models for Symbolic Security Protocol Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20712 - Mitigating Stethoscope-Induced Shortcuts in Respiratory Sound Classification under Federated Domain Generalization with Causality-Inspired Interventions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29862 - AnyAudio-Judge: A Dynamic Rubric-Based Benchmark and Evaluator for Audio Instruction Following Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03116 - Scaling Audio Models Efficiently: Joint Optimization of Scale, Resolution, Adaptation, Precision, and Sparsity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22790 - A Two-Stage Multi-Modal MRI Framework for Lifespan Brain Age Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16655 - Efficient Nash Equilibrium Computation for Cybersecurity Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19399 - FreqCondNorm: Towards Cross-domain Predictive Maintenance through a Frequency-Conditioned Transformer Foundation Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20535 - PAPC: Platform Mediation for Privacy-Propagation Externalities in AI-Mediated Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19226 - Risk-Set Transported Synthetic Control with Difference-in-Differences Adjustment under Staggered Treatment Adoption Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20264 - Music Hallucination in Audio-Language Models: A Hierarchical Formulation and Empirical Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20195 - MeshKV: A Network-on-Chip KV Cache Fabric for Scalable Transformer Decoding Accelerators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19207 - Beyond Depth Truncation: Controlled Evaluation of Depth Utilization in Recursive Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19934 - Drag-Aware Aerodynamic Manipulability for Torque-Limited Redundant Multirotors: Aerodynamic Promptness based on the Symmetric Acceleration Capacity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.07998 - Designing Against Deskilling: Metacognitive Feedback Reduces Cognitive Offloading to LLM Assistants Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20143 - Refuse, Decompose, Refresh: A Claim-Safe Protocol for Closed-Loop AI Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20538 - Cross-Sectional Asset Retrieval via Future-Aligned Soft Contrastive Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10711 - Optimal Transport Metric Learning for Feature Alignment in Partially Supervised Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19176 - Human and AI-generated texts between modal logic and statistics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20311 - Long-horizon autoformalization of a core theorem underlying MIP* = RE Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19814 - From Rollout to Reset: A Graph-Based Harness for Autonomous Long-Horizon Manipulation Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19413 - AIREP: A Protocol for Per-Decision Evidence in AI Runtime Governance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21363 - Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20139 - WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31672 - A Scalable Trust Discovery Architecture for the Internet of Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20095 - Generating a Consistent Enterprise: Synthesis and Reference-Free Evaluation of Multi-System Business Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.11286 - JointMatch: A Unified Heterogeneous Graph Neural Solver for Large-Scale Ride-Sharing Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20200 - Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19406 - Efficiently Distributed Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19972 - Ownership in AI-Assisted Everyday Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20658 - VLM-CAD: VLM-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.07315 - SoK: Trading Agents or Market Crashers? Dissecting Robustness and Security Failures in Academic Financial LLM Trading Schemes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19705 - STR-Agent: An LLM-Driven Agent for QoS-Aware Routing in LEO Satellite Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20347 - A Proposal for an Agentic AI Architecture to Support Multi-Domain Decision-Making in the Brazilian Armed Forces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20080 - What Do Current Systematic Generalization Tasks Miss? A Reasoning-Centered Analysis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19212 - Modeling Human Behavior with Type Vectors Using AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18265 - PonderPounce: A Pretrained MLLM as an Episode Context Engine for Robot Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24115 - Reinforcing the World's Edge: A Continual Learning Problem in the Multi-Agent-World Boundary Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06813 - Self-complementary completions on six vertices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20231 - CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18462 - SIMLIFE: Pattern Understanding for Long-Horizon Human-Agent Partnership Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19610 - greCAPTCHA: Assessing Understanding as Evidence of Research Authorship Under Generative AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20481 - Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19531 - MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19391 - Agentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19538 - No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10854 - The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18063 - Efficiently Linking Unstructured Data for Multi-step Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19491 - Semantic Feature Analysis: Improving Agents Without Searching Over Rollouts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.10513 - A Mathematical Model of Motivated Emotional Mind - Cognitive Embodied System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20437 - Predict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19441 - AntiGrounding: Executable Robot Trajectories as Visual Prompts for VLM-Guided Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12374 - Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19199 - A Qualitative Model for Reasoning about Path and Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20349 - Fingerprinting Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20457 - Rethinking Multi-Agent Collaboration: When More Is Less Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.19759 - TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19897 - Legislating World-Model-Based Planning with Legal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15113 - Neuro-Symbolic Agentic AI for Networked Low-Altitude UAVs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19961 - AURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19527 - Astronex-World 1.0: Real-Time Interactive World Model Foundation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20034 - StarVLA-$\alpha$: Reducing Complexity in Vision-Language-Action Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11757 - Solving Minimum Span Antibandwidth and Cyclic Antibandwidth Labeling Problems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20091 - UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12397 - Limits of Confidence in Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20581 - FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20817 - Explicit Language Memory for Long-Horizon Planning in Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04765 - A Hybrid Gaze-Motor Imagery BCI Framework for Effective Decision Communication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20273 - BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25248 - SkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20455 - The syntax and semantics of goals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19448 - LearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19721 - AI Training Manager: Bounded Closed-Loop Control of Adaptive Training Recipes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29871 - Replan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19654 - Integrating knowledge from case reports: a medical ontology based multimodal information system with structured summary Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19775 - JEPA-WAM: Connecting Generated Visual Instructions to World Action Models through JEPA Latent Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20277 - Inference-Time Nash Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08082 - AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20130 - Tailored to you: longitudinal effects of personalising language models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20077 - A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02540 - Semantic Action Graph: A Shared Representation for Agent Grounding and Human Interpretation of Sports Highlights Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20768 - AVTrace: Diagnosing Audio-Visual Temporal Reasoning in Omni Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19991 - Continual Enterprise World Model Discovery in Dynamic Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19551 - Bridging Modalities on the Cortex: Surface-based MRI to PET Translation with a Diffusion Bridge Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20147 - LinePilot Digitizer: Line-Plot Recovery with Manual and Automatic Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19377 - Guideline-grounded retrieval-augmented generation for ophthalmic clinical decision support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21925 - PACE: Precise AI Cinematic Expression: A Typed Specification for Script-Grounded Previsualization and Geometric Conformance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19853 - CoreSense: Traceable Failure Recall and Conflict-Aware Belief Gating for Auditable Robot Decisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19512 - MaskHarness-WAM: Instance-Grounded Harnessing for Long-Horizon Robot Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19974 - Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20820 - FedeRICo: Federated Region-Influenced Coupling for Traffic Flow Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20026 - Structured Four-Stage Legal Translation: From Natural-Language Traffic Rules to PROLOG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20334 - SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20519 - Perception, Layout, and Validation: Calibrated Confidence for Reliable Straight-Through Processing of Financial Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20110 - Perceptual Refinement of an End-to-End Video Streaming Pipeline via Generative AI Layers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19215 - AutoResearch: Insight In, Hallucination Out Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17906 - How Do Agent Harnesses Create Value? Planning Information and Release Control in Stateful LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20474 - BioPhys-Bridge: A Benchmark for Interdisciplinary Scientific Reasoning in Physics-Grounded Biological Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19180 - Customizable and Jointly Optimized Route Planning: A Deep Architecture Enabling Differentiable Shortest-Path Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19996 - Closed-World Resolution Against Tool Hallucination in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19425 - A Multi-Modal Generative Model for Tomato Disease Leaves Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19555 - ERCPMP-Gx: Endoscopic Image and Video Dataset for Morphological, Histopathological, and Genomic Characterization of Colorectal Polyposis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20815 - CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20267 - DART: Distillation-Aware Reparameterization for Training-Free LoRA Reuse in Few-Step Video Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20051 - When AI Agents Commit: Cognitive Serializability Across Data, Evidence, Policy, and Authority Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20261 - REACT: A Fully Spiking State-Space Model for Real-Time Event-Driven Temporal Perception Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.19204 - Understanding Role Switching in Human-AI Collaboration through Multimodal Behavioral Signals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.20666 - UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20089 - Multi-Dimensional Prosody Judgment For Live Streaming Speech Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20124 - A Mathematical Theory of Pragmatic Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.10986 - Improving Cross-embodiment Transfer in Latent Action Models with Action-Similarity Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19846 - MAGMA-GEN: Validated Recovery Supervision from Ambiguous Failures via Counterfactual Re-Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20056 - ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19644 - A Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19524 - AquiLLM: Evaluating Faithfulness in Open-Weight RAG-LLM Systems for Scientific Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16519 - CoRELoop: Parameter-Efficient Controlled Recurrent Refinement for Audio Deepfake Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19818 - Reach or Solve? Attributing Agentic RL Gains with Checkpoint Handoffs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19636 - A Multi-Objective Optimisation Framework for Corticomuscular EEG-EMG Pair Selection in Hybrid BCI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20275 - Kinematics-Grounded Agentic AI for Robotic Additive Manufacturing Process Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19347 - A Functional Pilot for Certified Freshness-Aware Semantic--Spatial Range Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19855 - E-AVI: Evidence-Grounded Multimodal Assessment for Automated Video Interviews Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20001 - Effective and Efficient Threat Hunting with Small Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.06660 - When Do Language-Grounded Explanations Help? A Graph-Bottleneck for Farm Monitoring Interpretable Sheep Facial Pain Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20427 - Large Language Models as Falsifiers for Cyber-Physical Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20752 - Domain Elastic Transform: Bayesian Function Registration for High-Dimensional Scientific Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21235 - Deep Noir: Autonomous Steering Discovery via Architectural Chronometry in Transformer Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20722 - Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19789 - GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19315 - MTVA-Bench: Evaluating the Language Model Inside Cascaded Voice Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20152 - A Simulation Platform for AUV Fault Recovery: Exploring LLM-Based Diagnostic Strategies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20620 - Learning and Transferring Closed-Loop Robot Software Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19906 - AgentPProf: Semantic Profiler for Long Horizon AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20301 - ClashBench: Conflicts Leading Agents to Seize and Harm Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19892 - Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18820 - Constraint-Safe Graph-Context Scoring for Stable Point-Feature Labels Under Text-Width and Accessibility-Inspired Profiles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19848 - Do AI Agents Understand Computer Architecture? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19387 - MetaRTL: Meta-path Attention Enhanced Relational Table Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19832 - Large language models eroding science understanding: an empirical study of malignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25639 - Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20732 - Robust Conformal Intrusion Detection via Traffic-Aware Calibration and Attack-Orbit Invariance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19241 - IWC-Bench: Evaluating Web Application Generation from a Software Testing Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15387 - MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.22924 - A Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19843 - FCA-Guided Counterfactual Explanations for Multi-Modal Breast Cancer Diagnosis: A Framework Achieving Perfect Validity with Emergent Sparsity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20067 - Governance-as-Code: Translating EU AI Act Technical Requirements into Executable Compliance Pipelines for Generative AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20016 - The AR Fairness Metamodel: A Structured Framework for Fairness Measures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19234 - WiCleanData: Guaranteeing the Type Consistency of Wikidata by Taxonomy Refinement and Constraint Enforcement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20057 - FORGE: Forensic Reasoning with Grounded Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.15867 - Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01346 - Not All AI Agents Are Equal: Characterizing Resource and Performance Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19947 - LLM-Guided Transformation of Non-Critical Driving Scenes into Safety-Critical Scenarios Using Augmented Reality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20318 - Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20358 - Physical knowledge on historical data matters more than enforcing physical constraints on the forecast Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19871 - FitAQA: A Benchmark of Fitness Action Quality Assessment for Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08736 - SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18630 - MaSCoD: A Multi-Agent Framework for Structural-Context-Guided Candidate Causal Graph Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19944 - HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20659 - Inference-Engine Fingerprinting Attacks are Practical: Exploring Model-Driven Environmental Discovery, Exploitation, and Escape Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20614 - Accelerating Sharded Data Parallelism at Scale with Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20359 - Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.19137 - PointEvent: Rethinking Event-based Tiny Object Detection via Serialized Motion Evidence Accumulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20066 - RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20754 - Atria Dawn: The Dawn of Agentic Superintelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15818 ## Community - Gemini Hacked Three Companies in First Known Breakout by Google’s AI Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/18/gemini-hacked-three-companies/ - Note on 18th September 2026 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/18/probably-gonna-eat-you/ - Quoting Thariq Shihipar Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/18/thariq-shihipar/ - The Creative Spirit of Who Framed Roger Rabbit Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/18/the-creative-spirit-of-who-framed-roger-rabbit/ - Why Agentic Development Needs Stricter Architecture and Design Source: adam-bien Topic: Java (+AI) URL: https://adambien.blog/roller/abien/entry/why_agentic_development_needs_stricter_architecture_and_design - ListenData: AutoGPT : Everything You Need To Know Source: planet-python Topic: Python (+AI) URL: https://www.listendata.com/2023/04/autogpt-explained-everything-you-need.html - How OpenAI Used Its Own LLMs to Design Its Jalapeño Chip Source: hacker-news Topic: General (+AI) URL: https://spectrum.ieee.org/llms-for-chip-design - Hackers Used Anthropic's Claude to Break into OpenAI Source: hacker-news Topic: General (+AI) URL: https://www.wsj.com/tech/ai/hackers-used-anthropics-claude-to-break-into-openai-b40ba883 - The Implications of Linguistic Illegibility for LLM Security Source: hacker-news Topic: General (+AI) URL: https://arxiv.org/abs/2609.02852 - Cache-to-Cache: Direct Semantic Communication Between LLMs (2025) Source: hacker-news Topic: General (+AI) URL: https://arxiv.org/abs/2510.03215 - Anthropic finally adds AGENTS.md support to Claude Code Source: hacker-news Topic: General (+AI) URL: https://twitter.com/trq212/status/2101009392611278961 - OpenAI 'ethically hacked' with help of Anthropic's Claude chatbot Source: hacker-news Topic: General (+AI) URL: https://www.theguardian.com/technology/2026/sep/18/openai-hacked-anthropic-claude-chatbot - US judge denies OpenAI bid to review X Corp's settlement with Apple Source: hacker-news Topic: General (+AI) URL: https://www.reuters.com/legal/litigation/us-judge-denies-openai-bid-review-x-corps-settlement-with-apple-2026-09-18/ - Researchers used Claude to hack OpenAI Source: hacker-news Topic: General (+AI) URL: https://arstechnica.com/ai/2026/09/researchers-used-claude-to-hack-openai/ - Hacking OpenAI Source: lobsters Topic: General (+AI) URL: https://www.hacktron.ai/blog/hacking-openai - The Provenance Tax: How LLM Watermarking Changes AI Agent Behavior Source: hacker-news Topic: General (+AI) URL: https://www.lasso.security/blog/the-provenance-tax-understanding-the-impact-of-llm-watermarking-on-ai-agent-behavior