TILens Daily Edition 2026-09-07 Filters: topic=ai, github=hidden Stats: 578 articles, 21 sources, 544 research papers Top topics: AI, AI Research, Information Retrieval ## News - AWS Weekly Roundup: Claude Fable 5.1 on AWS, Amazon Linux 2027 preview, AWS Certified AI Business Strategist, and more (September 7, 2026) Source: aws-news-blog Topic: AWS (+AI) URL: https://aws.amazon.com/blogs/aws/aws-weekly-roundup-claude-fable-5-1-on-aws-amazon-linux-2027-preview-aws-certified-ai-business-strategist-and-more-september-7-2026/ - Supporting independent journalism in Ukraine Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/supporting-independent-journalism-in-ukraine - “Some agents will be pursuing their own objectives”: OpenAI’s chief scientist warns AI could trick and blackmail humans Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-voluntary-slowdown-safety/ - Bắt LLM trả JSON đúng chuẩn: ba lớp và vòng repair Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/bean_bean/bat-llm-tra-json-dung-chuan-ba-lop-va-vong-repair-hjp - How to Build an AI Chatbot with Gemini and Vercel Serverless Functions 🚀 Source: freecodecamp Topic: General (+AI, JavaScript, React) URL: https://www.freecodecamp.org/news/how-to-build-an-ai-chatbot-with-gemini-and-vercel-serverless-functions/ - Query-Aware Code Compression for LLMs: 1.3M LOC to 1,500 Lines in 2.8s Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/tim860/query-aware-code-compression-for-llms-13m-loc-to-1500-lines-in-28s-1oad - AI agents are creating more work, not less — and OpenAI’s own numbers back it up Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/openai-agent-research-bottleneck/ - My Quiz Has an AI Rival. Its Scoring Doesn't Need an LLM. Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/nomurasan/my-quiz-has-an-ai-rival-its-scoring-doesnt-need-an-llm-1hm7 - From Blueprint to Production: How AI Revolutionizes App Development Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/melissadissouza/from-blueprint-to-production-how-ai-revolutionizes-app-development-58bn - OpenAI’s new model costs 2.5x more per token — and developers are saving money anyway Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/astra-reasoning-effort-cost/ - Matt Clifford to leave ARIA before Anthropic role becomes a 'distraction' Source: theregister Topic: General (+AI) URL: https://www.theregister.com/public-sector/2026/09/07/matt-clifford-to-leave-aria-before-anthropic-role-becomes-a-distraction/5294861 - How to Deal With Errors and Failures in LLM-Powered Applications Source: bytebytego Topic: Architecture (+AI) URL: https://blog.bytebytego.com/p/how-to-deal-with-errors-and-failures - A catwalk at IFA, but for robots Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/a-catwalk-at-ifa-but-for-robots - How To Talk To A Machine Without Anthropomorphising It Source: hackaday Topic: Hardware (+AI) URL: https://hackaday.com/2026/09/07/how-to-talk-to-a-machine-without-anthropomorphising-it/ - Import AI 472: DeepMind's cheating math agents; populist AI policies; and Forethought theorizes a nightwatchman Source: importai Topic: AI URL: https://importai.substack.com/p/import-ai-472-deepminds-cheating - Another OpenAI agent swarm surfaces Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/another-openai-agent-swarm-surfaces - 😺 OpenAI's chief scientist is calling for brakes Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/openai-s-chief-scientist-is-calling-for-brakes/ - OpenAI's rebel agent swarm died young, but its chilling logs live on Source: theregister Topic: General (+AI) URL: https://www.theregister.com/columnists/2026/09/07/openais-rebel-agent-swarm-died-young-but-its-chilling-logs-live-on/5294446 - Building an Automated Background Removal Micro-Service with Next.js and Canvas API Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/jojo_willnn_/building-an-automated-background-removal-micro-service-with-nextjs-and-canvas-api-28ao - Building KORTEX: How We Engineered a Next.js 16 B2B AI Agency Architecture for $10k/Month Retainers Source: devto-javascript Topic: JavaScript (+AI, React) URL: https://dev.to/aisiteflow/building-kortex-how-we-engineered-a-nextjs-16-b2b-ai-agency-architecture-for-10kmonth-retainers-3mcn - I built Obyflow. Try it, break it, and tell me what goes wrong Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/anupam_kumar/i-built-obyflow-try-it-break-it-and-tell-me-what-goes-wrong-3mmf - Stay ahead in web development: latest news, tools, and insights #153 Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/urbanisierung/stay-ahead-in-web-development-latest-news-tools-and-insights-153-4hio - Jensen's purchase of a new toy could reshape the entire AI industry Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/09/07/jensens-purchase-of-a-new-toy-could-reshape-the-entire-ai-industry/5294610 - OpenAI research automation 🤖, Tim Cook's role 💼, agent secrets 👨‍💻 Source: tldr-tech Topic: General (+AI) URL: https://tldr.tech/tech/2026-09-07 ## Research - I Vibe-Coded an App in Just Two Hours (And Regretted It the Next Day) Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/i-vibe-coded-an-app-in-just-two-hours-and-regretted-it-the-next-day/ - Why Most Multi-Agent Systems Fail Even When Evaluation Passes Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/why-most-multi-agent-systems-fail-even-when-evaluation-passes/ - Hakken: Predicting future discoveries to fill the gaps in today's knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04494 - Compute-in-Memory Attention: A Time-Domain Analog Softmax Circuit with RC-Tunable Temperature Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04266 - An Energy-Based Conservative-Dissipative Latent Neural Evolution Operator for Magnetization Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04530 - TACIT-Switch: Cost-Aware Model Escalation for LLM Agents from Censored Supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27911 - When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04281 - Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.20314 - Enhancing Multimodal Emotion Recognition via Multi-Feature Encoding and Attention-Based Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04690 - A Constraint-Aware Generative Framework for Synthetic Origin-Destination Demand in Logistics Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04345 - Coarse-Graining Hidden Representations: Unsupervised Neuron Selection via Mapping Entropy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05126 - REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Concept Representation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04415 - HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13536 - Fast Gauss Sums via Flash Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04910 - WEECFP-SuRGE: Wide Embedded Extended Connectivity Fingerprint with Substructure Rotary Graph-distance Encoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04672 - SocialBuddy: Tailoring Search Agent for Social Scenarios Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01641 - SMILE: Bridging Continuous Optimization and Discrete Symbolic Recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04639 - DeepAffinity: Long-Term Aspect Preference Prediction in eCommerce using Small Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02468 - Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05194 - Omega-N: Interpretable Structural Node Descriptors and Their Applicability Domain Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01633 - Beyond a Universal Forecasting Selector: Demand-Conditioned Model Selection across Demand Patterns and Horizons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04425 - Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04710 - Across-Design Uncertainty in Short Pricing Panels: Inference and Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21334 - A Comparative Study of Counterfactual Explainers for Graph Neural Networks Enabling Multiple Types of Graph Edit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05113 - Conformal Prediction for Offensive Security Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05165 - MURAL: Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04574 - TrajMind: Chaining Role-Specialized LoRAs for Fast-and-Slow Collective Trajectory Anomaly Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02540 - A Data Fusion Framework for Grounding Aerospace Surrogate Model via Experimental Wind-Tunnel Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04267 - Learning from VAE Errors to support ECG-based Differential Diagnosis of Myocardial Scar Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05294 - Online Change-point Detection for Cooperative Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05298 - Canalization Before Generalization: Grokking as a Dynamical Probe Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25813 - LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09596 - Improving Energy Efficiency of Oil Platforms Through Optimal Loading of Diesel Generators Using Machine Learning and Search Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22076 - MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07885 - FluxDisco: Symbolic Regression for Stoichiometric Dynamical Systems via Monte Carlo Graph Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05207 - Forecast Skill Is Not Decision Skill: Evidence from Weather-Dependent Decision Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14779 - A Fairness Audit of the Duckworth-Lewis-Stern Method: Format-Specific and Gender-Differential Bias, with an Interpretable Calibration Layer for Cricket Target Revision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04754 - Corporate-Family Resolution Is Not a String-Matching Problem: A Public Benchmark Stratified by Name Visibility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04269 - Representation Redundancy and Structural Complexity in Finite-Field Inversion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04583 - Procedural Content Generation via Generative Artificial Intelligence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.09013 - The microscope is the mask: privileged views and labels from a cryo-ET forward model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04325 - Data-Driven Learning of Unknown Nonlinear Differential Equations Using Functional Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04329 - TeleTables: A Benchmark for Large Language Models in Telecom Table Interpretation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04202 - The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08234 - KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04852 - Optimizer Memory Schedules for Outscaling the Overtraining Axis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04577 - Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26491 - Tracing Audio Grounding and Answer Selection in Audio LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04637 - Hyperedge Anomaly Detection with Hypergraph Neural Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.05641 - Counterfactual Fairness Audits of Multi-Step Clinical LLM Agents Require a Measured Per-Action Instability Floor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03221 - Fast Surrogate Modeling of Excitable and Oscillatory FitzHugh-Nagumo Dynamics with Parametric Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04549 - From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07537 - Towards Efficient Parametric State Estimation in Circulating Fuel Reactors with Shallow Recurrent Decoder Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.08904 - EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09773 - Enhancing Affine Maximizer Auctions with Correlation-Aware Payment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09455 - Deep Divide-and-Reduce in Symbolic Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02628 - Coupled Control and Wireless World Models for Resilient Remote Robotic Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04851 - Fractal and Chaotic Activation Functions in Echo State Networks: Preprocessing Topology Governs the Echo State Property Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14675 - Interface-Induced Trajectory Censoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03966 - Extremely Sparse Supervision Incentivizes Reasoning Ability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04565 - Embedded Graph Flows for Categorical Graph Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05328 - Locating and Steering Refusal Beyond Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04721 - DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Task Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25073 - Sound-based Multi-Person 3D Pose Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04902 - VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04355 - How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05309 - Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Construction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11318 - Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29354 - Post-Training Language Models for Gold-Medal Performance in Coding Competitions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02849 - SharedSAE: One Feature Dictionary Across Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04344 - Interpretability for Turing Machines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04661 - Degradation-Aligned Self-Supervised Learning for State of Health Estimation of Lithium-Ion Batteries under Label Sparsity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16612 - Small Molecule Optimization with Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.18897 - ProToMEx: Rapid, Interpretable Explanations via Structured Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04265 - Almost Free State Prediction Separation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03807 - An Integrated Vision-and-Language Pretraining (VLP) and Visual Question Answering (VQA) model to Automate Nondestructive Evaluation Image Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29408 - SCAPES: Semantically Conditioned Autoregressive Prior for Environmental Sounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04634 - Candidate Comparability Before Promotion: Conditional Validation in Adaptive Network Intrusion Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04388 - Second-order consistency for learning chaotic dynamics via randomized Jacobian matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01596 - Learning-Augmented Algorithms: Guarantees, Construction Mechanisms, and System-Level Implications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04787 - The Sample Complexity of Learning Lipschitz Operators with respect to Gaussian Measures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.23440 - Reservoir-Based Graph Convolutional Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.24131 - PAC-Bayesian Reconstruction Guarantees for Time Series Variational Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05212 - Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving Cascades Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01345 - Spectral-Target Physical Latent Structuring for JEPA-Style World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04264 - Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04748 - Mitra-v2 Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04540 - Single-Query Black-Box Calibration Auditing via Logit Bias Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05125 - Hidden In Plain Gaze: Gaze Representations as Privacy Controls for Utility and Re-identification Risk in XR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04592 - Beyond Stationarity in Time Series: Discovering Causal Structures and Latent Regimes via Markov Blankets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05150 - Beyond Homoscedasticity: Decoupled Uncertainty Optimization for Deep Imbalanced Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04995 - ClosureBench: A Constructive Benchmark for Compositional Graph Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18242 - From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06924 - Optimal Data Acquisition for Reinforcement Learning: A Large Deviations Perspective Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28675 - Too Rare to Learn: Prescribed Cyclone Tracks Degrade a Bay of Bengal Ocean Emulator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04635 - From Deep to Shallow: Unconstrained and Efficient Layer Merging Strategy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04881 - Multi-Modal Time Series Prediction via Mixture of Modulated Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21547 - Inducing Permutation Invariant Priors in Bayesian Optimization for Carbon Capture and Storage Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02409 - MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23473 - Dual-Scale State-Space Modeling with Speaker-Wise Dynamic CRF for Speech Emotion Recognition in Conversation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22399 - Resilience Beyond Stationary Client Unavailability: Unlocking Efficient and Unbiased Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04763 - Adaptation Interfaces for In-Context Tabular Foundation Models in Time-to-Event Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04901 - Latent Fact-Checking: Detecting Misinformation through Activation Engineering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06417 - Proton Irradiation Characterization of an Open-Source ML Accelerator on a Zynq UltraScale+ MPSoC Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05249 - Latent-Aligned Reasoning for Multimodal Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04645 - BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04971 - Variational Continuation for Double Pendulum Periodic Orbits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05337 - When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04490 - Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12368 - Amortizing Scaling Law Construction Costs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05016 - SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05174 - GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15751 - Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04382 - Statevector-to-Hardware Reconstruction of a Four-Qubit ZZ Quantum Kernel: A Single-Backend Case Study of Three Execution Jobs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20377 - DeltaGNN: Graph Neural Network with Information Flow Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.06002 - A Differentiable Neural Surrogate for Photon Propagation in Neutrino Telescopes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04695 - From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04894 - Lightweight Vision Transformer Compression for On-Device Plant Disease Detection in Resource-Constrained Agricultural Field Conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05334 - Beyond Co-purchase Relation: Evolution of Complementary Recommendations at Allegro Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05063 - Token-Level Advertising Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27382 - Robust and Efficient Guardrails with Latent Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29068 - YOLO with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection with trustworthy multimodal AI in computer vision perception Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23037 - An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.02465 - PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05235 - Dynamic Heterogeneous Graph Representation Learning: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04779 - SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22894 - Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05363 - Modular Deep Recurrent Neural Network: Application to Quadrotors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04339 - LexFlip: A Dissociation Diagnostic for Legal Meaning Preservation Metrics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05296 - Federated Attack Campaign Detection via Contrastive Encoding of Threat Indicators in Gradient Updates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04815 - LookThere! Sparse Vision by Reinforced Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04698 - GNN-Guided Graph Coarsening and Adaptive QUBO Penalties for the Capacitated Vehicle Routing Problem with Time Windows on a Quantum Annealer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04593 - Centered Permutation Prefixes for SGD with Random Reshuffling: Sharp Rates, H\"older Geometry, and Composite Proximal Extensions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04578 - One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario Generation in Closed-Loop Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04921 - PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04832 - Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04526 - Conformity Breaks Conformal Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04445 - Sustainable Edge Vision via Empirically Calibrated DVFS: Eliminating Thermal Throttling on Passively Cooled Hardware Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04705 - Self-Supervised Pretraining of Molecular Graph Encoders with LeJEPA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04261 - Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04575 - GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05253 - Minimax Lower Bound for Estimating Diffusion-based Local Intrinsic Dimension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04822 - LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease Screening Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04013 - Boosting Data Augmentation with Stochastic Weight Averaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14373 - Regularity of Second-Order Elliptic PDEs in Spectral Barron Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.19381 - Methane Detection On Board Satellites from Unorthorectified Imagery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04906 - Graph Foundation Models for Recommendation: A Comprehensive Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.08346 - Explainable Clustering of Mixture Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.01576 - Evidence Integration in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04290 - TSMini: A Simple Yet Highly Effective Trajectory Similarity Learning Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.00285 - An Analysis of Self-supervised Pre-training with Dependent Samples Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05031 - UniMate: One Unified Model to Animate Diverse Skeletons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05415 - Recovering molecules from coarse-grained beads: free-energy-conditioned generative backmapping across chemical space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04432 - Improving Weak World Models Behind Strong Agents in Atari Pong Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15142 - FedDRAW: Federated Dual Reputation Annealing Weighting for Heterogeneous Multi-Institutional Chest Radiograph Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05223 - How Faithful Is Attribution for Sales Forecasting? A Counterfactual Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04797 - Nested Inductive Bias Framework for SPD Manifold Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04466 - MomentQuant: an even more minimalist interval method with linear time complexity for time series classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05136 - A Sim-to-Real Study of Surface-Code Decoder Benchmarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04557 - Tree species mapping in Denmark: A comparison of spectral-temporal features with geospatial foundation model embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03480 - Shallow neural network approximation in mixed Sobolev spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05263 - Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04735 - From 80x to 385x: A Best-Matching-Unit Search at the L2 Roof, Measured Against a Symmetrically Tuned Baseline Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05138 - Efficient Clustering with Quality Guardrails for LLM-based Recommender Systems at Industry Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19704 - Gradient-based Model Shortcut Detection for Time Series Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.10075 - A Repeated-Measurement Study for Cultural Analytics of English Song Lyrics Using Five Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04428 - Dimension-Adaptive Batched Lipschitz Narrowing Without Knowing the Zooming Dimension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05214 - WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.11839 - EXAONE Forecast for Finance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04239 - Client-Side Probing of Deleted Ridge Statistics in Federated Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04475 - Relocation of compact sets in $\mathbb{R}^n$ by diffeomorphisms and linear separability of datasets in $\mathbb{R}^n$ Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21393 - NEAT-POCKET: Pocket-Conditioned Autoregressive 3D Molecular Generation with a Neighborhood-Guided Set Transformer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05097 - Adaptive Gated Deepfake Detection for Low-Resolution and Resource-Constrained Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05320 - Impact of Data Loss in Postprocessing on Training and Inference of Quantum Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05060 - A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04772 - Physics-Aware Random Walk Fingerprints for Scalable Power Grid Graph Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04943 - TNFlow: Amortized Posterior Inference for Trans-Neptunian Object Surface Composition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04305 - Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04531 - Confounding-Valid Conformal Inference for Counterfactual KPIs in Wireless Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05073 - On the Abundance of Critical Points of the t-SNE Energy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04379 - Aletheia: An Offline-First Clinical Decision Support System for Differential Diagnosis in Low-Resource Healthcare Settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24814 - When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04453 - Nepali Passport Question Answering: A Low-Resource Dataset for Public Service Applications Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2603.13320 - Deep Learning-Driven Peptide Classification in Biological Nanopores Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.14029 - Data-Optimized Contingency Screening: A Machine Learning Approach to Power System Security Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04300 - OR-Transformer: Scaling Real-Time Decision-Making to 1,000 Items Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01933 - When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04861 - Optimal Rates for Agentic Networked Information Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05318 - ResLearn-XR: Residual Learning for Network Traffic and Quality-of-Experience-Aware Modeling in Extended Reality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04493 - A Location-Invariant Estimator of Extremal Quantile Treatment Effects for Heavy-Tailed Distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04018 - On-board ML for Trace Gas detection in Imaging Spectroscopy data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04458 - Not All LLM Reasoning is Visible in the Chain-of-Thought Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22925 - Quantum-Assisted Memory-Efficient Training for Parameter-Intensive Wi-Fi-Based Human Activity Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04271 - Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.06813 - Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00184 - A Quantum Variational Approach to Prototypical Recurrent Unit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04354 - Solution-space heterogeneity shapes federated learning dynamics across partial differential equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05012 - Low-Latency Spell Correction for Japanese Music Search Queries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04262 - Brain4FMs: A Benchmark of Foundation Models for Electrical Brain Signal Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11558 - KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27231 - Advancing Subseasonal Forecasting with Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16238 - A Verifier-Guided Explainable Reasoning Framework with Gold-Anchored QLoRA, Task-Aware Mixture-of-Experts, and Group-Relative RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05221 - Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23723 - Inductive Venn-Abers and related regressors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06646 - Persistent Teacher Anchoring for Tool-Using Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04773 - Tuning Collective Patterns to Alleviate Congestion in Shared AI Clusters Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.04417 - Quantum Kolmogorov--Arnold representation theorem for continuous unitary-valued maps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03187 - Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.21203 - Evaluating Large Language Models for Forced Outage Risk Prediction: Benefits and Comparison to Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04272 - Disentangling Attention in Deep Operator Learning: A Controlled Study of Data-Driven and Physics-Informed Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04407 - GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.16248 - To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23492 - Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04108 - SiLR: Structure-Preserving Admission and Process Reward for LLM Tool Agents Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.04629 - Fractal basins trap latent reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04963 - Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05081 - Communication-Efficient Personalized Federated Learning via Layer-Wise Multi-Threshold Random Sketching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04830 - Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.31108 - Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23873 - RegionFed: Federated Learning for Personalized Query Understanding in Heterogeneous Retail Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05403 - BER-PEF: Unified Human Mobility Predictability Evaluation via Bayes Error Rate Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04292 - Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13612 - The Geometry of Polynomial Group Convolutional Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29566 - Hessian-based molecular conformation augmentation for a scalable and efficient strategy of machine learning interatomic potentials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05233 - A Hybrid Predictive Ensemble of Machine Learning and Deep Neural Networks for Early Cardiovascular Disease Risk Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05146 - SPD: Single Pass Decoding for Generative Reranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.01807 - How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05274 - GEPARD - Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04222 - Consensus Group Relative Policy Optimization for Text Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03102 - Automatic knot selection in smooth additive models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21083 - E-SENS: Exclusion-Sensitive Penalization for Negative-Constraint Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.30130 - AtomRec: Evolving Atomic Memory for Agentic Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04882 - Personalized Task Dependency Graphs for Mitigating Signal Erosion in Multi-Task Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04862 - VizIt: A multi-view framework for exploring single-cell, spatial, and genetic data online Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04658 - Inventory-Grounded Policy-Level Optimization for Training-Free AI Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04813 - Beyond Maintenance Manual Multimodal RAG: Suggesting What Tool Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.05116 - InsightToast: Proactive Information Retrieval & Glanceable Visualization in the Side Channel of Data-Rich Meetings Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.31115 - Embedding Surgery: Localized Updates for Adaptive Ranking Correction in Dense Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.05110 - BioSync: Transformer-Based Cross-Modal Fusion for a Multimodal Physiological Digital Biomarker Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04504 - CAGE: Coherence-Aware Graph Encoding for Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04647 - SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04961 - UniCon: A Unified Context-Centric Modeling Paradigm for CTR Prediction Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.03290 - A Tree-based RAG Framework for Evidence-Intensive QA via Adaptive Planning and Topology-Aware Evidence Gathering Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04981 - Students' Perception of Big Data Engineering in Higher Education Curricula: Expectations, Interest and Ethical Implications Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.05160 - Repeated Queries Exhaust an LLM's Brand Recommendations but Not Its Sources Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.05059 - SAGE: Semantic Attribute Graphs for Multi-Entity Visual Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04255 - An Event is Worth One Token: Event Tokenization for Industrial-scale LLM Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.25546 - Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.05339 - Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.05025 - An almost quadratic bound for the minimal excluded minors for a surface Source: arxiv-cs-dm Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2604.02796 - Evaluation of Phonetic Encoding Algorithms on Transcription Datasets Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.04391 - A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04409 - On Epistemic Diversity in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04835 - From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05149 - Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23989 - Large Language Models with At Most One Spike per Neuron Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05151 - Cache-Aware Joint Router Adaptation for Memory-Efficient MoE Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04895 - Do Androids Dream of Unseen Puppeteers? Probing for a Conspiracy Tendencies in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.03699 - Agentic Context Cracking: Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.31082 - Memory as transformation: LETHE, a self-referential gan-inspired architecture Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04289 - Cross-Preference Learning for Sentence-Level and Context-Aware Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25183 - Influence Score and Transformers interpretability: Measure of the Effective Impact of Attention Heads at inference time Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05074 - Why We Care About Understanding: Competence through Predictive Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04962 - INSPIRE: An Internalize-Then-Improve Approach for Example-Driven Mathematical Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27501 - Don' t Box Me In: Dynamic Cultural Adaptation and Cognitive Tracking for Social Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22411 - Self-Supervised Lexical Representation Learning for Fast, Large-Scale Phylogenetic Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05262 - How Much Does Corpus Choice Change Dependency-Distance Estimates? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04223 - Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04484 - Rhythms of Work: Multi-Scale Interpretation of Human Behavioral Traces for Workplace Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04556 - WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05405 - Large Language Models for HVAC Operations in Building Energy Systems: A Critical Review of Methods, Applications, and Deployment Readiness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05314 - Scientific Domain Knowledge Improves Vision-Language Fundus Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02720 - How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05037 - Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3 Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04808 - Rethinking Indirect Prompt Injection as a Test-Time Search Problem Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04495 - Abstraction Agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04303 - Uncertainty Signals for Network Intent Translation: Risk Ranking and Ambiguity Localization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04486 - Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25731 - When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04582 - Does the Selected Object Reach the Reader? Auditing Identity Handoffs in Grounded Language-Model Pipelines Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.04579 - MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04841 - Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04298 - A Calibrated Reflection Approach for Enhancing Confidence Estimation in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04539 - What Attention Recalls and Recurrence Controls in Hybrid Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04434 - RealCADBench: Benchmarking Parametric CAD Modeling from Industrial Design Intents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03773 - LentEx: Generalizable Latent Entity Extraction via Synthetic Data and Instruction-Tuned LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04511 - Unified Deployment-Aware Evaluation of Open Reasoning Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07035 - CacheWeaver: Cache-Aware Evidence Ordering for Efficient Grounded RAG Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19667 - Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05036 - JLIR: A Julia-Native MLIR-Inspired Intermediate Representation with Automatic JACC Kernel Extraction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04585 - You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful Chinese Online Comments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04384 - Reviewer Capability Governs Rejection Targeting, Not Repair Skill: Evidence from LLM Execute-Review-Revise Pipelines Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04270 - Same Trajectory, Contradictory Rewards (ROBORMBENCH): Paraphrase Fragility in Vision Language Reward Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05401 - EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04280 - Fixed Suffix Dependency Ratio: Quantifying the Dual-Track Mechanism of Gender Assignment in Latvian Loanwords Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03930 - VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03811 - Retinal OCTA Phenotyping with LLM Reporting for Alzheimer's Disease Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04689 - GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04442 - IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03781 - Labels have Human Values: Value Calibration of Subjective Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06631 - QoNext: Towards Next-generation QoE for Foundation Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.21889 - MedProb: Probing Internal Representations of Vision-Language Models for Medical Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04336 - Technical Manual for a Toolkit for Measuring Contextual Individuation in Transformer Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05333 - Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05395 - CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04855 - PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04598 - Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04753 - Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.24377 - Generating Constructive Feedback on Stories via Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04824 - Automatic Speech Recognition for Multilingual Oral History Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04232 - ConfRAG: Confidence-Guided Retrieval-Augmenting Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.07309 - Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26627 - Enoki: Efficient Multi-Level Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00581 - Controlling and Assessing Appropriate Persona Use in LLM-based Dialogue Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04676 - MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2605.30931 - Adapting from Downturns: Prediction of Long-Term Conversational-Skill Development in Mental-Health Crisis Counselors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04350 - ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05169 - A Systematic Comparison of Multilingual Interpretability Methods Reveals Anisotropy-Driven Failures Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04819 - Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15913 - Compiler-Guided Adaptive Proof Search with Cross-Model Synergy on Context-Dependent Theorem Proving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18084 - Improving Language Identification for Code-Switched Utterances with Integer Linear Programming Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05099 - EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05043 - Knowing When Not to Answer: Pseudo-Ensembles for Abstention in Music Audio-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04362 - GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody Explodes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28514 - Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04489 - Measuring the Novelty of Biomedical Papers Using the Latent Distances between Knowledge Units Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05175 - Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07531 - KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10403 - Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04482 - Role-Aware Artificial Intelligence Across Augmentation and Automation in Human-Machine Symbiosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00440 - BIT.UA at BioASQ 14B: Modular Retrieval with pg_textsearch and Qdrant, and Agent-Based Answer Generation Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval, PostgreSQL) URL: https://arxiv.org/abs/2609.04999 - Choosing the Right Language Mode at Inference Time for Multilingual Reliability Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04653 - Multilingual Models for Check-Worthy Social Media Posts Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2408.06737 - Vectorizing Classical Tamil: Representation Learning for Verse-Commentary Pairs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04755 - Shared circuits predict whether LLMs generalize across formats in arithmetic reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04463 - MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04842 - NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05617 - From Plausible to Actionable: A Position on LLM Self-Explanations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15957 - Auditing Bias and Safety in Voice AI Customer Care Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04206 - A Structured Debate-Mixture-of-Agents Framework for Complex Clinical Diagnostic Decision Support Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05069 - Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05189 - PROMPT2BOX:Improving LLM Weakness Discovery and Specificity Estimation by Uncovering Entailment Structure among Prompts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21438 - Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04720 - From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02679 - Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22480 - Can Activation Steering Capture Multidimensional Authorship Style? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04792 - VERGE: Verification-Enhanced Refinement for Grounded Extraction of Early-Onset Colorectal Cancer Symptoms in Clinical Notes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04366 - GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25160 - Quality Recovery for Quantized KV Caches via Low-Rank Attention Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04263 - Editable Visual Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04034 - NS-ST-GraphRAG: Neuro-Symbolic Spatio-Temporal GraphRAG for Literary Knowledge Processing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05139 - How Do Language Models Represent and Use Phonological Information for Allomorph Selection? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04708 - Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05088 - TRILOGUE: A Trilingual Spoken Dialogue Fact-Checking Benchmark with Evidence and Paired Audio Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04452 - MoirfEolas and Cr\'iochScore: Developing Resources for and the Evaluation of Tokenization Alignment with Irish Morphology Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05022 - CT-$\Delta$Bench: A Benchmark for Longitudinal 3D Medical Imaging Difference Reporting with Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11534 - The Anatomy of an ASR Hallucination Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04404 - Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06327 - TruthInsightBench: An Evidence-Grounded Benchmark for Automated Evaluation of Open-Ended Scientific Discovery Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05079 - Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Through Targeted Fine-Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04485 - Reinforcement Learning for improving Large Language Models' Catalan text simplification capabilities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04823 - A Human-in-the-Loop Framework for AI-Assisted Scoring in Large-Scale Writing Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05143 - A Removal Based Approach to Improve LLM Faithfulness at Test-Time Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04343 - RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04898 - Detect, Remask, Repair: Diffusion Editing for Faithful Summarization of Evolving Contexts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12807 - ConsensusBench: Benchmark of Consensus Nodes for LLM Reasoning via Outcome Reward Densifying Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04648 - Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05152 - Discourse Dependency: A Continuous Criterion for Translation Difficulty Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04959 - Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04714 - Robust Text Watermarking for Large Language Models via Dual Semantic Embeddings Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31602 - When Linguistic and Internal Confidence Diverge in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28382 - AI Revealed Preferences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26178 - SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01139 - LLM-Assisted Behavioural and Scenario Augmentation for Agent-Based Energy Adoption Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04866 - When Financial Fine-tuning Fails: A Three-Level Detectability Analysis of Numerical Hallucination in Domain-Adapted Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04806 - Label Over Logic? How Source Cues Bias Human Fallacy Judgments More Than LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29928 - Language models judge war differently when tested for alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05009 - Constructing and Evaluating Clinical Reasoning Trajectories for Medical Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05090 - Train What You Deploy:Token-Faithful Post-Training of a Production Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04678 - Diffusion TV: Experiencing Diffusion Models through Tangible, Embodied Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05404 - Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05275 - MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04947 - Harness-agnostic detection and immunization of reward hacking in self-evolving language models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04665 - X-VC: Zero-shot Streaming Voice Conversion in Codec Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12456 - Data-Driven Discovery of Composition-Dependent Constitutive Models for Hyperelasticity and Viscoelasticity of Digital Materials Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04541 - TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05019 - DODR: Deterministic Operator-Driven Reasoning in Latent Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04782 - From Answers to Interpretations: Rethinking Ambiguity-Induced Aleatoric Uncertainty Estimation in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04543 - RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05324 - Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05261 - HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04444 - Continual Field-Adaptive Models (CFAMs) for Post-Deployment Physical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04552 - Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04681 - Predicting Spatiotemporal Mobile Sensing-Based PM2.5 Concentrations Using Low-Rank Adapted Spatially Attentive Graph Neural Network Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04693 - Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04778 - Solving Hard XAI Queries Based on a Compiled Dual-Rail Encoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04931 - AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.20654 - Artificial Intelligence in Equity and Crypto Markets: Progress, Profitability Evidence, and the Limits of Automated Investing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04917 - Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.11194 - Model Retirement Creates Reproducibility Risk in Biomedical AI Publications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04699 - Quality-diversity in dissimilarity spaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2211.12337 - Do LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective from Knowledge Space Theory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05245 - Global to Local: Topology-Preserving Adaptive Graph Pooling via Granular-Ball Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04978 - AI-Powered CPS-Enabled Vulnerable-User-Aware Urban Transportation Digital Twin: Methods and Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.10396 - Adaptive Multi-Granularity Temporal Modeling for Weakly Supervised Video Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05066 - The Mirror Agent Model: a Bayesian Architecture for Interpretable Agent Behavior Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05190 - Hierarchical Possession-Aware Graph Pointer Network for Pass Receiver Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04803 - Dual-Part Multi-Lateral Branched Network for Multi-Class Segmentation in Cardiovascular Catheterization Angiograms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04590 - AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04871 - ProtLingo: Efficient Protein Language Modeling via Conditional Memory and Expert Routing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04793 - Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13596 - What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04518 - MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18718 - LLM-Driven Algorithm Design for Quantum Circuit Synthesis based on Binary Decision Diagrams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05327 - CHAMP: Cross-domain Hybrid Architecture for Matchmaking and Prediction in Online Multi-Player Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04870 - TRNet: Learning with Topographic Priors for VHR Paddy Rice Mapping Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04154 - Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04875 - AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03693 - MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05075 - CPR-IE:A Compression-Prediction-Resource Intelligence Efficiency Metric Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04809 - CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05227 - Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2606.08151 - Compact Bellman-Grounded Cognitive Maps for Cost-Aware Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05104 - Ultrasound-Based Prediction of Cirrhosis Decompensation Using Large-Scale Computer Vision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04365 - LLM-Guided Program Evolution for Circle Packing: Breaking 10 Packomania Records for $28 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05093 - SQL-Zero: Self-Evolving Text-to-SQL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04697 - CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05269 - AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimensional Quantum Mechanics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05157 - GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05284 - MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18892 - FVSpec: Real-World Property-Based Tests as Lean Challenges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01008 - "**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03090 - Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04860 - AI for Computational Design Science: A Responsible Human-AI Framework and Case Study on Short-Form Video Safety Surveillance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05270 - FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04706 - Cross-Task Generalization Between Understanding and Generation in Unified Vision-Language Models: A Controlled Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23043 - Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04909 - $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04611 - Why Better Models Can Create Riskier Systems: Evidence from LLM Agents in Financial Markets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04373 - Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04513 - La Agente \'Optima: Towards Agentic Self-Driving Laboratories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04564 - Beyond Aggregate Scores: Behavioral Correctness Assumptions for Assessing Reference-Based Automatic Evaluation Methods Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05289 - RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05765 - A Deep Generative Model for Synthesizing Labeled Wireless Signals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05396 - Shadow Queries for Private Retrieval in Vector Databases Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.04767 - ProCA: Progressive Contrastive Alignment for Robust EEG Visual Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05094 - When Does an Interpretation Count as Established? The Formation, Evaluation, and Responsibility of Interpretation in Generative AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04766 - CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04865 - RISE: Recursive Improvement via Self-Extrapolating Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05295 - Comparables XAI: Faithful Example-based AI Explanations with Counterfactual Trace Adjustments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13784 - ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04850 - Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05623 - CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05374 - TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04912 - SoK: AI-Augmented Binary Reversing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17398 - PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04867 - From Matching Models to Recruiting Agents: A Systematized Narrative Review of AI Recruitment Systems, Evaluation, and Governance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04286 - Who Should Grade My Work? Student Perspectives on Transparent AI-Assisted Writing Assessment in Higher Education Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05346 - TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05117 - ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04913 - Towards Efficient Evaluation of Evolutionary Transfer Optimization: Case Studies on Task-Parameterized Applications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05040 - MaxKernel: Agentic Kernel Generation for TPUs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04523 - MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04804 - ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04878 - SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05141 - Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00063 - PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04715 - Whose record is this? Diagnosing and authorizing record use in personalized multimodal models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04801 - Commonsense Reasoning in Computer Vision: Foundations, Recent Advancements, and Future Directions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05257 - Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05364 - A Roadmap for MEG Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04461 - Where Appearance Fails, Geometry Recognizes: A CAD-Free 3D Shape Prior That Complements Vision Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04381 - Attention-guided super-resolution of 4D flow MRI in carotid arteries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04891 - A Cost-Aware Agentic Architecture for NL-to-SQL over Nested Enterprise Schemas, with a New Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04641 - Building a research-software catalog with a coding agent: from hackathon prototype to public deployment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04711 - Cross-modal triage network: a multimodal deep learning framework for severity-based triage and visual explainability in chest radiographs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04357 - What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05376 - FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03889 - MM-IFEval-Pro: A Multilingual and Attack-Resistant Benchmark for Instruction-Following in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04859 - Corporate Language Model (CLM): Transforming Tacit and Fragmented Enterprise Knowledge into a Sovereign, Auditable, and Executable Corporate Intelligence Layer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04377 - Qlippy: A Retrieval-Augmented GenAI Assistant for Reproducible Quantum Workflows and Experiment Tracking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05039 - Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04802 - SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization Reweighting for Cross-Platform 3D Object Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04886 - Iris: Climbing to the Search Frontier Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.04304 - ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05228 - VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04948 - NxN E-valuation: Hypothesis Certification via a Conformal CRT Null Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06621 - Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09055 - A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05251 - Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09686 - Wireless Foundation Models: State-of-the-Art and Open Challenges Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04707 - FORESIGHT-9: Prospective and Process-Aware Evaluation of Adaptive Trading Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29372 - Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10534 - Compact-Memory LLM Agents via Online Max-Member Clustering and Atom-Aware Packing Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.04915 - MZ-Rain: Moisture-Budget-Guided Zero-Inflated Model for Station-Level Precipitation Nowcasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04864 - MARLA: A Conceptual Scaffold for Regulatory Learning under the EU AI Act Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04877 - Active Inference for an Intelligent Agent in Autonomous Reconnaissance Missions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.17450 - Continual Graph Memory for Adaptive Recommendation under Intent Drift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04651 - What Moves? Localized Motion Representations for Compositional Scene Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04383 - Measuring proximity to standard planes during fetal brain ultrasound scanning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.07124 - Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05111 - What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05198 - From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04869 - ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04667 - Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04570 - Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05258 - When LLM Decompilers Recompile More and Preserve Less Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05370 - GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.07314 - Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Maps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03483 - The History Is the Detector: Executing CVE Patch History, End-to-End Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05335 - AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14941 - $A^2E$ : An End-to-End Agent Auditing Engine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07346 - Reducing Hallucinated Transcripts in Whisper via Hallucination Space Projection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04561 - OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Heuristic Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13769 - ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.12762 - The Fake Friend Dilemma: Relational Trust and the Political Economy of Conversational AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03222 - CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.24622 - A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05133 - Testing Interchangeability in LLM Agent Teams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05279 - DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04749 - SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.20686 - BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28026 - Blockchain-Enabled Secure Logging for Fiscal Electronic Mechanisms: Evaluation of the Greek eSEND and myDATA Tax Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04356 - Long Horizon Transformer Quantile Fault Prediction for Multi Site Industrial Predictive Maintenance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04840 - Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04533 - Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04820 - Pitch-class Steering for Diffusion-based Music Generation via Latent-space Probes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04516 - Molecular D\'ej\`a Vu: Digit-Level Retrieval of Published Values in Frontier Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05381 - Xiaomi-TabLDM: A Tabular Foundation Model Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03880 - Uncensored Open-weight Models: Redistribution as the Persistence Layer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05241 - PerfReasoning: How Well Do LLMs Reason on Hardware Performance? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04476 - A Semantic Model of Genetic Evidence: A Step Toward Bridging the Basic-Science-Clinic Gap Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04509 - Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04738 - Substrate-Aware AI Agents: Execution Context as a First-Class Input Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05232 - Scalable Context Orchestration for Serving LLMs Over Voice Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04288 - Towards a universal language of concepts: A survey Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04528 - IPGeoAI: Transformer-Based Geolocation with LLM Semantic Fusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04559 - Leveraging Imperfect Restoration for Data Availability Attack Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04627 - Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05385 - SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30277 - Reinforcement Learning for Sequential Solar PV Policy Design under Uncertainty: An Agent-Based Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04880 - A Survey on Semantic Modeling for Building Energy Management Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.11716 - How a Chatbot's Response Style Shapes a Classroom: A Multi-Agent Simulation of Students Consulting AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05018 - Reflection-aware Generative Novel View Synthesis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.05382 ## Community - llm 0.35 Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/7/llm/ - Creepy crawlies Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/7/creepy-crawlies/ - Quoting Jakub Pachocki Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/7/jakub-pachocki/ - Video compressor Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/7/video-compressor/ - Mercator ↔ Equal Earth Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Sep/7/equal-earth/ - Armin Ronacher: Astra for Coding: Why Are We Doing This Again? Source: planet-python Topic: Python (+AI) URL: https://lucumr.pocoo.org/2026/9/7/astra-why/ - The smallest edge AI device for local LLMs Source: hacker-news Topic: General (+AI) URL: https://tiiny.ai/ - El Yayster – a resident LLM that inhabits Emacs Source: hacker-news Topic: General (+AI) URL: https://github.com/yayster/yayster.el - Tell HN: OpenAI brings back 5 hour limit for plus and business standard users Source: hacker-news Topic: General (+AI) URL: https://news.ycombinator.com/item?id=49600233 - OpenAI 2025 financials $38.5B loss ahead of IPO Source: hacker-news Topic: General (+AI) URL: https://qz.com/openai-leaked-financials-losses-revenue-ipo-061626