TILens Daily Edition 2026-10-19 Filters: topic=ai, github=hidden Stats: 808 articles, 27 sources, 772 research papers Top topics: AI, AI Research, Information Retrieval ## News - Amazon CloudWatch Omni is now available in additional AWS Regions Source: aws-whats-new Topic: AWS (+AI) URL: https://aws.amazon.com/about-aws/whats-new/2026/10/amazon-cloudwatch-omni-8-regions/ - GenRecs Tokenization: Transforming Ads Recommendation at Meta with Stable Model Vocabulary Source: meta-engineering Topic: Architecture (+AI) URL: https://engineering.fb.com/2026/10/19/ml-applications/genrecs-tokenization-transforming-ads-recommendation-at-meta-with-stable-model-vocabulary/ - Advancing coding in low‑resource programming languages Source: openai-blog Topic: AI Labs (+AI) URL: https://openai.com/index/low-resource-programming-languages - TorchNeuron: running HF models on AWS Trainium is easier than ever Source: huggingface-blog Topic: Hugging Face (+AI) URL: https://huggingface.co/blog/hf-torchneuron - Nscale and Anthropic are reportedly in talks for yet another $45B compute deal Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/19/nscale-and-anthropic-are-reportedly-in-talks-for-yet-another-45-billion-compute-deal/ - Embedded AI evaluators won’t be an easy solution, Hugging Face’s policy chief says Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/19/embedded-ai-evaluators-wont-be-an-easy-solution-hugging-faces-policy-chief-says/ - Microsoft says AI agents are like insider threats as ‘frontier models can’t be trusted’ Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/19/microsoft-says-ai-agents-are-like-insider-threats-as-frontier-models-cant-be-trusted/ - Accused OpenAI spy had folder called “Saudi Gov Docs,” FBI says Source: ars-technica Topic: General (+AI) URL: https://arstechnica.com/tech-policy/2026/10/accused-openai-spy-had-folder-called-saudi-gov-docs-fbi-says/ - How We Built a 100% Client-Side C2PA Metadata Scrubber, Invisible Unicode Cleaner & NotebookLM Bundler in the Browser Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/soulkieng/how-we-built-a-100-client-side-c2pa-metadata-scrubber-invisible-unicode-cleaner-notebooklm-376e - Two .npmrc Lines That Stop npm Supply Chain Worms (Tested on npm 10, 11 and 12) Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/moksh/two-npmrc-lines-that-stop-npm-supply-chain-worms-tested-on-npm-10-11-and-12-99k - Researchers removed one instruction from Claude Code. Out-of-scope actions jumped. Source: newstack Topic: DevOps (+AI) URL: https://thenewstack.io/coding-agents-overstep-scope/ - Making the internet better for AI agents might make it worse for everyone else Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/19/1147186/making-the-internet-better-for-ai-agents-might-make-it-worse-for-everyone-else/ - “We were looking at it wrong”: The explosive claim that’s upended the AI world Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/19/1147149/we-were-looking-at-it-wrong-the-explosive-claim-thats-upended-the-ai-world/ - Write bot-resistant code with KillSwitch, a programming language designed to confuse LLMs Source: theregister Topic: General (+AI) URL: https://www.theregister.com/ai-and-ml/2026/10/19/write-bot-resistant-code-with-killswitch-a-programming-language-designed-to-confuse-llms/5303919 - [$] Development statistics for the 7.3 kernel Source: lwn Topic: Open Source (+AI) URL: https://lwn.net/Articles/1100241/ - SoftBank’s $18B bet on robot guards Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/softbank-18b-bet-on-robot-guards - Musk pledges to give ‘every kid in America’ one of his SpaceX shares Source: techcrunch Topic: General (+AI) URL: https://techcrunch.com/2026/10/19/musk-pledges-to-give-every-kid-in-america-one-of-his-spacex-shares/ - Import AI 477: In which I tell the IMF the Singularity has begun Source: importai Topic: AI URL: https://importai.substack.com/p/import-ai-477-in-which-i-tell-the - One API for Greenhouse, Lever, Ashby, Workable, SmartRecruiters and Recruitee jobs (with a daily new-jobs feed) Source: devto-javascript Topic: JavaScript (+AI) URL: https://dev.to/ostrata/one-api-for-greenhouse-lever-ashby-workable-smartrecruiters-and-recruitee-jobs-with-a-daily-348a - 😺 DeepSeek's free model edged Opus 5 at coding Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/deepseek-s-free-model-edged-opus-5-at-coding/ - AI researchers stranded Claude on a virtual desert island. It started to “play.” Source: mit-ai Topic: AI URL: https://www.technologyreview.com/2026/10/19/1147095/ai-stranded-claude-virtual-desert-island-play/ - Anthropic designs a pay package for the public Source: the-rundown-ai Topic: AI (+AI Tools) URL: https://www.therundown.ai/articles/anthropic-designs-a-pay-package-for-the-public - Anthropic Is Still Hiring. Junior Technical Roles Are Taking a Smaller Share Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/anthropic-junior-technical-hiring-ai/ - Anthropic Consults Lawyers on How AI Agents Should Negotiate Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/anthropic-ai-agents-negotiation-lawyers/ - Everything That Happened in AI Today (Monday, October 19, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-monday-october-19-2026/ - AI Weekly Issue #540: AI is finding software flaws faster than teams can fix them Source: ai-weekly Topic: AI (+AI Research) URL: https://aiweekly.co/issues/ai-is-finding-software-flaws-faster-than-teams-can-fix-them ## Research - Welcome to Google Gemini 4 Argon Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/welcome-to-google-gemini-4-argon/ - Can Conformal Prediction Take You from Accurate to Reliable Machine Learning? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/can-conformal-prediction-take-you-from-accurate-to-reliable-machine-learning/ - How Many EEG Channels Do You Actually Need? Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-many-eeg-channels-do-you-actually-need/ - AI Harms and Their Technical Causes Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/ai-harms-and-their-technical-causes/ - A Quantum Roadmap for Softmax Attention: Exact Born-Rule Analogs for Softmax Attention on the Probability Simplex Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11173 - Can Graph Learning Learn Circuits? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08536 - TRIP-Shapley: Propagation-Aware Contribution Attribution Framework for Peer-to-Peer Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.23246 - SafeAdapt-Poker: Counterfactual Risk Calibration for Budgeted Adaptation under Opponent Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20473 - Minimax-optimal Scaling Laws in Ridge Regression via Transfer Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23337 - Hypothesis Selection via Weighted Medians Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20375 - Information Estimation with Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23404 - Partial-Revelation Panel Forecasting: Predictive Information Gain, Allocation, and Coarsening-Consistent Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22831 - Batched Contextual Reinforcement II: Does RLVR Need Long Rollout Windows? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22887 - Interpreting SSL Representations for Spoof Detection: a WavLM Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23526 - Generative Value Classifier Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22497 - OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16395 - MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05524 - Horizon-Aware Early Event Prediction for Tokamak Disruption Alarms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24443 - Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21713 - Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10080 - Leveraging Cell-level Spatial Transcriptomics as Weak Supervision for Nuclei Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23481 - Deconstructing Multi-Task Active Learning: The Paradox of Gradient Conflict and Orthogonal Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23623 - Beyond Latent Personalization: Integrating HRV-Conditioned Personalization via LLM for Interpretable Stress Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23555 - How Murky Before a VLM Knows It Cannot See? Accuracy, Confidence and Abstention on a Physical Visibility Axis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22981 - Spectral Limits of Polynomial Graph Filters on the Long-Range Ising Model Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22713 - LeanTTA: A Backpropagation-Free and Stateless Approach to Quantized Test-Time Adaptation on Edge Devices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.15889 - QD-Rec: Open-Ended Evolution of Recommendations via Quality-Diversity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23470 - Mask-Based Deep Symbolic Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.24776 - DIFFLET: A Fast Inference Engine for Diffusion Transformer Models on AWS Trainium Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23047 - TALLOP: Joint Optimization of Local Training and Communication Compression for Time-Constrained Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22996 - Blitz: Accelerating the Diffusion Modules of AlphaFold3 and Boltz-2 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23703 - Rank Measures of Fine-Tuning Updates Need a Noise Baseline Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22438 - AceFF: A State-of-the-Art Machine Learning Potential for Small Molecules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00581 - Generative adversarial networks with Monte Carlo dropout uncertainty quantification for structural health monitoring: Fibre Bragg grating data augmentation comparison in Hawk T1A aircraft Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22436 - Task-aligned spectral inductive biases in parameterized quantum circuits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23834 - Where Latents Belong and How They Flow: Joint Identification of Structural Roles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23074 - No-Regret Mixing of LRU and LFU with Optimal Switching Cost Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07566 - Network-Wide Freeway Speed Nowcasting and Forecasting from Sparse Fixed Sensors with a Probe-Supervised Graph Convolutional Recurrent Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22630 - Understanding Stability of Outer Nesterov Momentum on Stochastic Pseudo-Gradients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22623 - Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31036 - Human-Centered Learning Mechanics: Observable Entropy Control under Protected-Risk Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22940 - Mesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00394 - A Language-Informed Loss for Visual Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23653 - Bernoulli Flow Models: Self-Consistent Generative Modeling for Binary Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11362 - Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23181 - FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29001 - Learnable Splines for Unstructured Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22446 - Learning to Be Guided: Shaping Latent Geometry for Classifier-Free Guidance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22885 - Untrained CNN and coefficient-space regularization for joint reconstruction in photoacoustic tomography Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23315 - Learning smooth dynamics via Kinematic Interpolants Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22519 - Does On-Policy Distillation Need to Complete Every Rollout? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21337 - Learning the Shared Latent Structure of Cryo-EM Inverse Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22523 - TriRouter: Sparse-to-Dense Electrode-Space Routing for Robust EEG Motor Imagery Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23665 - Causal Edit Serialization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22820 - CF-NODE: Counterfactual Spatial Node Intervention for Test-Time Adaptation Under Domain Shift, Evaluated Across Five Diabetic Retinopathy Datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22437 - Dynamics of Stochastic Momentum with Sparse Updates in High Dimensions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28961 - JAXtari: High-Throughput and Easy-to-Modify Arcade Learning Environment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23650 - Logic-Guided Graph Denoising Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23766 - Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.00684 - The Loss or the Architecture? What Matters in Survival Analysis with Competing Risks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23322 - Harnessing Trust in Directed Graphs: Redefining Robustness of Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2306.02002 - GRIT: Out-of-Distribution Robustness from Finite and Noisy Invariant Pairs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.24843 - ADT: All-Atom Diffusion Tokenizer for 3D Molecular Structures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23265 - Trust but Verify: Designing Region-Inhomogeneous Forward Dynamics for Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22380 - CauTion: Knowing When to Trust LLMs for Ensemble Causal Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03602 - PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22990 - SpecXMaster Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23101 - Inverse Learning of Latent Risk-Neutral Densities from Irregular Option Quotes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27188 - Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.23440 - Worst-Case Optimal $\sqrt{\epsilon}$-Rate Stability of KL Divergence under Perturbations of Gaussian Distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11026 - On the Sample Complexity of Active Learning with Membership Queries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27241 - Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19220 - FederatedBytes: Tokenizer-Free, Byte-Level Small Language Models for Efficient Multimodal Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22906 - Cross-Dialect Generalization Without Retraining: Benchmarks and Evaluation of Schema-Derived Constrained Decoding for MLIR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18254 - Data Provenance Aggregation and Structural Descriptors for Query-Template Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22705 - Deterministic Bounds on Accuracy and Stability of Metric-Space Regression and Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22564 - Regularized free deconvolution for spectral repair of resampling distortion in high-dimensional particle filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23448 - CastClaw: A Human-in-the-Loop Autonomous Agent for Interactive Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.30976 - Rethinking Negative Prompting for Concept Suppression: Unconditional Anchoring and Localized Guidance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.07658 - Leaner Transformers Can Easily Learn to Cluster Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09760 - Quality-of-Transmission Estimation in Quantum Networks: Compute, Simulate, or Learn? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23827 - Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.00470 - Path to Prior-Data Fitted Relational Models via Learned Latent Multi-table Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23073 - Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.20248 - ECG-SDI: Single-lead Electrocardiogram Enables Continuous Sleep Depth Index Profiling and Scalable Digital Biomarkers for Sleep Health Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23727 - Data-Efficient Classifier Pretraining Through Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23289 - Upper bounds on the number of causal pieces in spiking neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22484 - Beyond the Answer: Student-Conditioned Trace Construction for Reasoning Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23831 - ManiFusion: Unlocking the High-Throughput Generation via Superposition in Manifold Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21433 - Deep Learning for Forest Plantation Mapping in Godavari Districts of Andhra Pradesh, India Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22415 - Acquisition Function-Guided Generation for Bayesian Optimization over Discrete Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22763 - Forecasting Voltage Time Series under Anomalies Using a WGAN Model With Lipschitz Control and Progressive Kernel Critic Strategy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23394 - Physics-Transfer Learning: A Physics-Constrained Theory for Zero-Shot Generalization Along the Ladder of Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22376 - TRACE: Transformer Residual Activation Codebook Encoding for Communication-efficient Distributed Edge Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22435 - RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02003 - Next Token or Vector? Learning How Far to Decode Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22788 - Dependency Reasoning for Aspect Sentiment Quadruple Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14873 - Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23036 - AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22684 - Unifying Embodied Foundation Models via a Model-to-Policy Formulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23053 - Gap Detection: Mitigating Homogenization through Demand and Defensibility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20162 - Property Estimation in Geotechnical Databases Using Labeled Random Finite Sets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.22659 - DeDiCa: A Scalable Deconfounding Discrete Causal Generative Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23272 - Missed Detections and False Alarms in a CNN Technosignature Detector on Breakthrough Listen Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22050 - HiPredict: Predicting the missing HiRISE RED4 spectral channel with machine learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23335 - How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13764 - Learnable Spectral Activations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07419 - Operon: Incremental Construction of Ragged Data via Named Dimensions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16080 - The Optimal Ranking Tradeoffs Between Two Ranking Scores in Two-Class Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23294 - On the Trade-off Between Information Loss and Generalization in Sparse Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04424 - M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.14360 - Task-aware Kernel Stein certificates for R\'{e}nyi differential privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23798 - Adaptive conformal prediction on the Grassmannian Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23508 - ToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22883 - NeuralDMD: Interpretable Neural Representation of Dynamics from Sparse and Noisy Measurements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.03094 - An Adaptive-Horizon Graph Neural Operator for coupled surrogate morphodynamic modelling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22432 - Deep LLM layers expose passage-level context in EEG during silent reading Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23638 - STRIDE: Reasoning-Aware Training for Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08625 - Non-Parametric Optimization for Scalable Learning in Stochastic Decision Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23204 - Alert-List Concordance for Evaluating Imputation Strategies in ICU Sepsis Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22635 - Multi-Agent Reinforcement Learning-Based UAV Pathfinding for Obstacle Avoidance in Stochastic Environment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2310.16659 - Tool Recommendation for Multi-Step Agents: Finding Every Tool a Task Needs Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.23707 - Learning angles for quantum approximate optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23296 - Equivalence testing and run-count design for stochastic machine-learning experiments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23700 - RECREG: Recovery-based Shielding for Regular Safety Properties in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23445 - Bandit Multiclass PAC Learning: Structural Baselines and a Confidence Direct Sum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29694 - Can the Parts Fool the Test? Counterfactual Pairing Cycles for Relational OOD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23248 - Conformal Policy Selection: When to Deploy AI Decisions for Targeted Intervention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22930 - ActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20532 - What Shapes Brain Alignment of Large Language Models during Dialogue? Insights from Language Production and Comprehension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22961 - Sampling the XY model with an attention-based neural network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23783 - Agentic-MatriBO: Capability-Compiled Agentic Bayesian Optimization for Materials and Chemical Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17832 - RSD-Poker: Structure-Adaptive and Shift-Robust Risk-Utility Certification for Residual Policies in Imperfect-Information Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33669 - Domain-specific language alignment of multimodal embeddings towards explainable predictions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23110 - Don't Retrain, Remix: Adaptation of Web Agents using Mixture Hypernetworks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22539 - Predicting Task Difficulty Without Rollouts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05797 - How language model agents reshape price competition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21711 - Coverage Cliffs in Off-Policy Quantile Certification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22565 - GPT, But Backwards: Exactly Inverting Language Model Outputs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.01693 - Time-partitioning Gaussian Process Mixture Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20860 - HydraLLM: Adaptive Width Slicing for Elastic Text and Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23455 - Data-Driven Prediction of Optimal MPI Rank Placement and Node Count for Memory-Bound CFD on AMD EPYC Clusters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23383 - Kwai Summary Attention V2 Technical Report Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18654 - Process Reward Modeling with Reliability- and Conservatism-Aware Bayesian Belief Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23223 - On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22543 - ECPO: Evidence-Coupled Policy Optimization for Verifier-Audited Candidate Ranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21993 - Local proxies for memory-efficient training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23145 - FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02828 - Handwritten Text Recognition Lives in the High-Pixel Variance Subspace Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35473 - GPU-Accelerated Robust MA--RIS Pre-Optimization for Communication and Target Illumination Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22431 - ENFR: Evidence Networks with Flow-Matched References for Amortized Simulation-Based Model Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23825 - Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13319 - Predictable Scaling: Efficient Model Exploration via Scaling-Law Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23453 - Latent Evolution Operator (LEO): State-to-State Forecasting of Parametric PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.09063 - Learning to Reason About Implicit Multimodal Harm: From Diagnosis to Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29951 - Response-Informed Value Estimation for Cost-Aware Multi-Turn LLM Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23239 - Look, Reason, Draw a Region: Recursive Refinement for Spatial Context Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23302 - CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20668 - A Theoretical Analysis of Test-Driven Code Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06098 - Distinguishability and Recovery for a Doubly Sparse Spiked Wigner Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23033 - Trajectory-Triggered Sparse Collaborative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23613 - A New Family of Poisson Non-negative Matrix Factorization Methods Using the Shifted Log Link Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.05845 - Mesoscopic learning dynamics of extensive-width neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23779 - How Many, but How Sure? Class Competition as a Confidence Proxy in Multi-Class Density-Based Counting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23611 - OrderFlowDiT: Transport-Regularized Diffusion Transformer for Probabilistic Limit-Order Supply Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22727 - Sample, Mix, or Verify? Allocating Test-Time Compute under Imperfect Verifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23255 - What Accuracy Hides In Learned Transformer Programs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22891 - SALTO: Solver-Anchored Lifted Transfer Operators for Nonlinear Event Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21049 - Transferability of Learned States in Neural PDE Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10972 - A Minimal ReLU Classifier on Non-Linearly Separable Data: Convergence and Implicit Bias at and beyond the Edge of Stability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23007 - Neural Expansion: A Unified Mechanism for How Deep Neural Networks Generalize Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23716 - Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.01253 - The Sign Code: The Hidden Binary Nature of Deep Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23616 - GARG-AML against Smurfing: A Scalable and Interpretable Graph-Based Framework for Anti-Money Laundering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.04292 - Quantum-Classical Neural Networks for Solving Lindblad Master Equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22691 - Characterising and Analysing Retrieval-Augmented Generation Techniques Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23226 - GR-OPD: Group-Relative Sequence Credit for On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23042 - PE-MHL: Physics-Encoded Modular Hybrid Layers for Scalable Learning of Complex Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04290 - Diagnosing GNN Failure Modes with Layer-Wise Probe Entropy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22595 - RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10899 - FAER: Auditable Utility-Aligned Trajectory Replay for Language Model Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00385 - Beyond Marginal Influence: Interaction-Aware Memory Selection for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23266 - Out of Support, Not Out of Reach: In-Context Learning with Unsupported Instructions and Composed Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23528 - Towards Agentic Cloud Engineering: Graph and Loop Engineering with a Zero-Trust Agent Harness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00050 - Controlling the Diversity-Quality Trade-Off of LLMs by Merging Models Before and After Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22999 - The Score Is Not the Structure: Brain Alignment and Cross-Lingual Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03827 - A Survey of Explainable Reinforcement Learning: Targets, Methods and Needs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.12599 - Accelerated Gradient Methods for Nonconvex Optimization: Escape Trajectories From Strict Saddle Points and Convergence to Local Minima Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2307.07030 - Reliable data clustering with Bayesian community detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.15013 - CocoRNA: Collective RNA Design with Cooperative Multi-agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23820 - Reasoning Reranking with Semantic IDs as the Sole Item Representation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22797 - VStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.36958 - Where's the Indirect Evidence? Investigating Grammatical Generalization with Influence Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22919 - Proportionality in Ranking Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23193 - CoatFusion: Controllable Material Coating in Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.02143 - Measuring Differences between Conditional Distributions using Kernel Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02260 - When is a large language model a good calibration agent? Physics-labeled prompting for budgeted engineering simulator calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22379 - Universal Semantic Enhancement for Weakly Supervised Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23765 - Ori: Drift-Aware Streaming $k$-PCA for Very Low-Rank LLM Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22794 - Progressive Misalignment Can Emerge from Benign Recursive Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22467 - Native Geometry vs. Linear Recoverability: How Alignment Changes Platonic Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22749 - Benchmarking and Enhancing Agentic Causal Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22846 - Generalization in Neural Networks Through the Lens of Magnitude Potential Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01633 - Graphlet-based Decentralized Finance Transaction Method Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23466 - Competence-Based Evaluation of Logical Reasoning in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22894 - Embodiment-Classifier Guidance: Transferring Frozen VLAs Across Robot Dynamics without Demonstrations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22576 - Towards Reconstructing Geographically Diverse Architecture with 3D Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22514 - Boundary Detection for High-Dimensional Point Clouds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23590 - Learning Personalized Memory Gating from Delayed One-Sided Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23812 - "Deep lifts": Neural networks can generalize even with the dumbest optimizer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23009 - A general recipe for data-adaptive anytime-valid envelopes for iterative algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23570 - No-Regret Language Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23641 - Bridging the Language Gap in Scholarly Data II: Enhancing Gender Inference for Chinese Names Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23734 - Expressivity of IQP Feature-Map Quantum Kernels via Reproducing Kernel Hilbert Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23692 - A Topological Signature of Learning under Noisy Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23491 - Edit Discovery in Human-AI Interactions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22661 - Capability-Gated Language Models: Security Composes, Utility Does Not Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00445 - HeRE: A Novel Benchmark for Hebrew Relation Extraction via LLM-Guided Denoising of Knowledge Graph Alignments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22542 - SelectArena: A Modern Benchmark for Feature Selection on Real-world Tabular Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13644 - ContractRL: Shielded Group-Relative Policy Optimization for Auditable Tool-Call Repair Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00328 - The optimal information complexity of VC learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10600 - Optimal approximation of smooth functions by ReLU neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22693 - Guarded Block Transfers for Polytope Distance: Linear Convergence with Explicit Constants and Gap-Certified Screening for SVM Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15829 - Generative Policy Improvement from Observational Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23436 - Think More or Read More? A Token-Budget Theory of Reasoning with Shared Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23246 - Parametric Resonance in Primal-Dual Learning for Slowly Non-Stationary Constrained MDPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23788 - DisCo Algebra: Why Disintegration and Combination Are Not Inverses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15006 - AutoPrunedRetriever: Persistent Reasoning Graphs for Efficient and Extensible Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04926 - When Plans Change, Remember: Replanning-Guided Visual Memory for Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22556 - A Feature Selection Layer Approach for Multi-Class Classification on Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22898 - CGDT-CESN: Correlation-Guided and Dynamics-Trained Clustered Echo State Network for Multivariate Time-Series Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22430 - Generative molecule evolution using 3D pharmacophore for efficient Structure-Based Drug Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.20130 - CastFlow: Bridging Evidence Acquisition and Accurate Prediction in Agentic Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27840 - Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22122 - Replay Pruning and Few-Bit Integer Inference for Hardware-Efficient Speed-Sign Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22811 - Regime-Conditioned Evaluation in Multi-Context Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04895 - Towards a GraphNARX model for structural dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23103 - Neural Operators Which Certifiably Simultaneously Solve Infinitely Many Convex Programs using Logarithmic Rank and Linear Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.14995 - Towards Hyperparameter Transfer for Differentially Private Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22976 - AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12265 - Robust Experimental Design via Generalised Bayesian Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.07671 - When to Forget: Risk-Controlled Context Adaptation for Long-Horizon Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22897 - Nearly Linear Private Learning of Littlestone Classes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23160 - Uncertainty-aware AI-enabled framework for predicting hydrogen dispersion in confined spaces to enhance operator situational awareness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23515 - Residual Stochastic Concept Bottleneck Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23421 - Actions with Receipts: Jointly Binding Claims, Evidence, and Execution for Replayable Tool-Agent Auditing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00327 - On the tradeoff between robustness and geometric accuracy in adversarial training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22955 - Fully sequential Gaussian process regression for preference learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19391 - OSCC: Certified Observation-Safe Coupling Optimization for Gradient-Noise Control in Imperfect-Information Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33543 - One Communicator, Three Vendors: Extending the MoA Predictive Theory to a Real NVIDIA+AMD+CPU MPI Ensemble Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22769 - Reusing Calibration Gains across Model Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22771 - Rarity of Singletons Matters & Supplementary Materials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22604 - Refusal Is Not Robustness: Measuring Harmful Reachability in Autoregressive Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22754 - N-Gram Memories at Two Bits: Quantizing Lookup Tables in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21810 - LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17697 - Source-Aware Dynamic Pricing with Strategic Buyers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22516 - Escaping Parameter Space: Tight Generalization Bounds via Representation Quality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23729 - Interpretable experiential learning based on state history and global feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00940 - Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22995 - Waiting Buys Exactly Two Moments: Endogenous Identification in Prediction-Driven Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23830 - RoutePack: Replay-Guided Expert Placement and Rollout Trajectory Scheduling for MoE Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12146 - Router Drift Control: Mitigating Off-Policy Degradation in Mixture-of-Experts Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21682 - GRAFT-EEG: Gauge-Aware Physical Field Transport for Cross-Dataset Motor-Imagery EEG Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23620 - Peak-Memory Schedules You Can Trust: Exact Realization, Certified Optimality, and the Limits of Recomputation for Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23328 - The Ephemeral Cost of Switching Optimizers Across LLM Training Stages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22650 - Large Diffusion Models Need More Than EMA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22945 - TargetSEC: Plug-and-Play In-the-Wild Speech Emotion Conversion via Arousal-Conditioned Latent Style Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07293 - Redundancy Meets Synergy: Dependency-aware Expert Selection for MoE via Submodular Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00558 - MetaCurate: Evolving Curation Filters for High-Quality Agentic Coding Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23134 - GVPO: Group Variance Policy Optimization for Large Language Model Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.19599 - What is causal about causal models and representations? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.19335 - Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.10597 - Memory Bandwidth, Not FLOPs: Profiling and Accelerating Query-Based Segmentation Decoders on Edge GPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22377 - Reinforcement Learning in MDPs with Information-Ordered Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.03904 - Gabor-Enhanced Physics-Informed Neural Networks for Fast Simulations of Acoustic Wavefields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.17134 - Beyond Success Rate: Interventional Evaluation of Memory in Vision-Language-Action Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23372 - Bridging Compressed Communication and Local Steps via Spectral Method in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23434 - From Flow-Box Invariants to Global Conservation Laws: Machine Learning-Assisted Detection of Singularities and Near-Integrability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23760 - Coordination Matters: Process-Aware Evaluation of Cooperative Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06557 - Activation-Efficient Fine-Tuning via Sequence-Compressed Low-Rank Subspaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22783 - Information-Geometric Blind Spots of Conformal Test Martingales Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23131 - Has GPT-6-Astra Achieved Embodied Intelligence? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22471 - Learning without relearning physical symmetry: an SO(3)-equivariant convolutional network (CNN) on the sphere Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23821 - Shift-Reliance Alignment: Ranking Vision-Language Models by the Cues They Trust Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22610 - Distributed Performance Boosting through Neural Control for Plug-and-Play Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23292 - Pro-AI Bias in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13749 - Beyond Expected Values: Risk-Sensitive Planning with Distributional Monte-Carlo Tree Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23565 - Can LLMs predict the outcomes of machine learning experiments? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22599 - Where Prefill Expert Reduction Hurts MoE Models: A Few Prompt Tokens Carry Most of the Short-Answer F1 Loss Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22454 - Predicting Privileged Information Effectiveness for On-Policy Self-Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22512 - An Agnostic Sample Compression Scheme for Squared Loss of Near-Linear Size in the Fat-Shattering Dimension Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29696 - Optimal estimates for the $\ell^p$-Lipschitz constants of deep random ReLU neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.19695 - A Label Noise Robust Algorithm for Graph Data using Neighborhood Label Distribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22998 - Null Controls Are Necessary but Not Sufficient: Evaluating Acceptance Guards for Scientific Discovery and Interpretability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22445 - PowerAtlas: Feasibility-Aware Language Models for Electricity-Computing Co-Scheduling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26710 - Missing value imputation with adversarial random forests - MissARF Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.15681 - Learning Agentic Time Series Forecasting via Trajectory Distillation and Memory-Based Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13802 - BOLT: Multi-Bottleneck Bound-Guided Learning for Flexible Job-Shop Scheduling with Time Lags and Resource-Coupled Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22433 - Structural Affinity: An Algorithm for Coherent Cage-Based Shape Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23173 - Learnable Hodge-Laplacian Driven Mixture of Experts for Steady-PDE Surrogates on Coarse Unstructured Meshes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20585 - Structural Causal Bottleneck Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08682 - Anytime Contracts for AI Services Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22781 - Language steering in latent space to mitigate unintended code-switching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.13849 - Benchmarking Prompt Optimization of Large Language Models With Chess Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00416 - TASER: Task-Aware Stein Regularisation for Geometry-Driven Smoothness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30601 - Online Inference in Distributional Temporal-Difference Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14408 - Normalizing Flow Maps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22711 - Sparse Autoencoders Can Induce Local Geometry for Mitigating Catastrophic Forgetting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22439 - RAW-Explainer: Post-hoc Explanations of Path Reasoning Graph Neural Networks for Knowledge Graph Completion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.12558 - Reading the News Without Hindsight: NoLBERT Topics and the Cross-Section of Stock Returns Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22745 - GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11117 - Board gender diversity and emissions performance: Insights from panel regressions, machine learning, and explainable AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.00244 - Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12299 - RTSM: Adapting Recursive Models to Multivariate Time-Series Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23353 - Lean4AgenticRL: Advancing Agentic RL with Verifiable Multi-level Process Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22448 - Noise-shaped Sampling and Annealing for Scalable On-the-edge Training of Binary and Ternary AI Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22621 - BMuon: Budgeting Muon's Spectral Geometry for Structured Compressibility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23571 - Aligning Language Models Towards Counterfactual Invariance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22942 - Towards optimal selection schedules for online active learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23477 - Audit-First VAPO: Risk-Certified Selective Updates under Imperfect Verification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33662 - Exploring the Trade-Off Between Structured Pruning and Fault Tolerance in Deep Neural Networks for Space Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03117 - CoLU: Confidence-Weighted Layerwise Unlearning for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22721 - Contracting with an Agent under Model Mismatch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23402 - Flash RNN-T: Memory-Efficient Joint Network and Transducer Loss Computation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23409 - A Stronger Teacher Within: Strengthening MoE Models via On-Policy Bidirectional Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23185 - Scalable long-range machine learning interatomic potentials with electrical response for atomistic material modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23643 - The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22722 - How the elastic axis folds the transonic flutter boundary: shock energy transfer and conformally calibrated active learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23298 - Rep2Text: Decoding Full Text from a Single LLM Token Representation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.06571 - CVaR anchor regression protects against rare shifts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27034 - Structure-Aware Spatial Kernels for Gaussian Process Distributed Port-Hamiltonian Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22575 - Initiating Removal from Operational Symptoms in Federated Vehicular Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22584 - Detecting Multi-Agent Collusion Through Multi-Agent Interpretability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01151 - Flat Loss, Evolving Features: Grokking in Modular Addition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22593 - SETAREH Transform: A Sorting-Assisted Haar-Wavelet Sparsification Method for Approximate Inner-Product Computation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23338 - RealtimeWAM: One-Step Asynchronous World Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06617 - Multitask learning with semiempirical orbital charges enables sample-efficient MLIPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24073 - Deep conditional distribution learning via conditional F\"ollmer flow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.01460 - Noise-Robust Forced Alignment for Spontaneous Speech Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22583 - Many Biases, One Circuit: Post-Training Tunes a Pretrained Cue-Routing Mechanism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22937 - ThetreStageAI: Multi-View Retrieval-Augmented Generation for Structured Bengali Theatre Production Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23618 - Explainable Machine Learning Analysis of Temperature Effects on Mechanical Strength of Fiber-Reinforced High-Performance Concrete Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23811 - Unit-level aggregation breaks coverage in causal foundation models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22770 - Shape-Aware Neural Time Fields for Rigid-Body Motion and Manipulation Planning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22762 - FLARE: Physics-Grounded Evaluation of Language-Model Agents for Feeder Restoration with Degraded Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23251 - LangNCO: Compiling Natural-Language Constraints into Inference-Time Interventions for Neural Combinatorial Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23190 - LagNet: Lag-Structured Operators for Long-Term Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23735 - ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02808 - When Is Language-Model Advice Worth Buying? A Matched-Budget Study of Predictive Gating in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29548 - Spectral Indistinguishability and Learning-Curve Identifiability in Quadratic Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20678 - Online Inference for Quantile Distributional Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.12973 - HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance Remediation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23685 - Follow the Perturbed Leader for Linear Bandits: $\sqrt{T}$ Regret over General Action Sets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17818 - Is the Policy Gradient a Gradient? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/1906.07073 - An Efficient Approach to Beetle Damage Detection of Banana Using Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23661 - Pretraining Transformers with Quantized Softmax in Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33591 - BenthicDINO: Physics-Informed Self-Distillation for View-Invariant Side-Scan Sonar Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23215 - Statistical Vignettes on the Grokking Phenomenon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18811 - Scalable Levenberg-Marquardt Training Framework for Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22925 - CIIR - Class-Indexed Interface Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23151 - Exploration and Experimentation with a Misspecified Simulator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21458 - A Complete Characterization of Learnability for Adversarial Noisy Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09200 - LED: Improving Masked Diffusion Language Models by Lookahead Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23122 - Learning reveals invisible structure in low-rank RNNs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04115 - AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03378 - Explaining Chess and Go in Natural Language Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23166 - Chance-Constrained Personalized LLM Routing with Online Preference Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22695 - RCPN: towards robust pseudo-labels in unsupervised CLIP adaptation via consistent prototypes and neighborhoods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.22075 - Energy Overhead in Sensor Nodes: Embedded Machine Learning and Data Offloading via Low Power Wide Area Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.24829 - LoongSage: A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16352 - Is a Linear Probe Evidence of a Linear Representation? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22655 - SP$^2$ec: Adaptive Self-Speculative Decoding for Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18735 - Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07772 - GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39600 - NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23271 - Diffusion-Based Stochastic Operator Networks for Uncertainty Quantification in Stochastic Partial Differential Equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17107 - When Magnitude Suffices: Reconstructing Time-Domain-Gated Microwave Signals Without Phase on a Thoracic Phantom Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23608 - TANGO: RNA Topology and Geometry Co-Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20277 - Empirical Bayesian Multi-Bandit Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.26284 - Behavioral Couplings: From Formation to Behavioral Emergence in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23847 - Deep-learning-based low-energy trigger algorithms for the Hyper-Kamiokande experiment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.31391 - Reasoning Models Can Control Their Chains of Thought When They Tell Themselves To Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23257 - Sentence-Level Topic Modeling with Lexical and Contextual Evidence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23388 - GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39601 - The Statistical Fairness-Accuracy Frontier Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.17622 - Causal Discovery beyond Conditional Independence: Identifiability, Algorithms, and Statistical Inference for Directed Acyclic and Cyclic Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23543 - Anisotropic Representation Dynamics in Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23242 - Confidence Calibration in Vision-Language-Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.17383 - From User Recognition to Activity Counting: An Identity-Agnostic Approach to Multi-User WiFi Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16572 - Binding-Specific Relearning Savings for Test-Time Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22381 - Adaptive Conditional Residual Sampling for Spectral Risk Optimisation under Decision-Dependent Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.12507 - MS-ECG-FM: Towards a More Universal Electrocardiogram Foundation Model for Health Monitoring using Multi-source Contrastive Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07662 - Error Correction in Trained TTT Layers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16268 - Grounded Credit Assignment in Reinforcement Learning for Multi-Turn Search Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23148 - How Finite-Rank Bottlenecks Shape the Low-Rank Adaptation Landscape Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23343 - AuditKIT: A Unified Evaluation Spine for Benchmarking, Judging, and Comparing Large Language Models and Agentic Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.22511 - LSNR: Learned Sparse News Recommendations with Attentive User Modeling Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.23510 - Star Light, Star Bright: Can Multimodal Models Parse an Astronomy Visual Question Answering Dataset Right? Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.22474 - KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.01780 - EKLAV: Elicited Key CoT Learning via Answer only superVision Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.25182 - Code Skill Server: A Large-Scale Search Engine for Code Generation Skills Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.23186 - Improving OCR Accuracy Through Multi-Classifier Verification of Visually Similar Characters Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.22726 - Jev-as-a-Judge for Brazilian Portuguese Information Retrieval: Relevance Assessment and Reranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.23346 - HEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.20191 - UniRec: Cross-stage Multi-Task Fusion with Preference Optimization for Cascaded Recommender Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.11052 - Humanity's Last Choice: A Common Evaluation Standard for Generative Engine Optimization Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.23541 - RIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.11370 - Advertising to Agents: Measuring Description-Framing Bias in LLM Tool Selection Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.23916 - NoveltyScope: A Multi-Agent Research Assistant for Evidence-Grounded Novelty Assessment of Scientific Papers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.22703 - Complexity of liveness in ring Petri nets and of halting in chip-firing on simple digraphs Source: arxiv-cs-dm Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2610.23523 - The Reliance Hypothesis: Chain-of-Thought Faithfulness Rises as Language Resource Level Falls Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22841 - Safety Alignment via Constrained Knowledge Unlearning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.18588 - Learning to Retrieve and Reason on Knowledge Graph through Active Self-Reflection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.14932 - PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31148 - Who Pays for Efficient Inference? Confidence-Based Small-to-Large LLM Routing Across Tasks and Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23249 - Beyond Surface Cues: Robust LLM-Generated Korean Text Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22940 - CDAE: Enhancing Perturbation Robustness in Pretrained Language Models with Contrastive Denoising Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.28236 - What LLMs Do in the Shadows: Reading Context Reliance from the Unembedding Dark Space Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23182 - Risk and Refusal: Mechanisms of LLM Responses to Suicidal Ideation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22715 - Measuring Mechanistic Uncertainty in Large Language Models via Causal Robustness Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22636 - Self-Evolving Agents Can Repair Failures but Struggle to Generalize from Them Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22984 - Cultural (In)Competence: Investigating Culture-Specific Stereotype Detection Capabilities of LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22545 - Execution Before Memory: Diagnosing Memory Failures in Video World Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23542 - A misinformation playbook sharpens judgement without breeding cynicism Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22724 - Mitigating Demographic Disparities in Explanation-Human Alignment via Rationale Regularization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22586 - Too Emotional to Be Fake? Intra-Utterance Emotion Shifts Expose Failure Modes in Speech Deepfake Detectors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22832 - Prism Attention: Proposal-Refined Index Sharing Mechanism for Efficient LLMs Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22985 - Watermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based Watermarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22810 - Is MT Ready for the Next Crisis or Pandemic? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10082 - On the Tip of the Tongue: First-Token Cueing as a Behavioral Probe of Recall Failures in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23400 - Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31002 - Would you still call this Dax? Novel Visual References in VLMs and Humans Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05409 - Optimizing Singular Spectrum for Large Language Model Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.15092 - VocalGrad: Evaluating Acoustic Perception in Audio Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23745 - Acceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23818 - SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22959 - Analyzing Occupational Gender Bias across the LLM Training Lifecycle Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23587 - Language Models Learn to Improve Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23344 - MultiAgent-OPD: End-to-End Training of Hierarchical Multi-Agent Systems with On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23234 - ASR-Style Transcript Normalization Removes Useful Pragmatic Signal for Dialogue Act Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22934 - Truth in Contrast: Calibrated Factual Evidence from Language Model Likelihoods Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23527 - Cooperation Without Adaptation: LLM Agents in a Collective-Risk Dilemma Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22882 - Trajectory-Guided Steering: Mitigating Spurious Feature Bias in Clinical Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22618 - Inductive Learning of Concept Embeddings from Cross-Linguistic Colexification Patterns with Textual Attributes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22638 - Repairing LLM-Generated Specifications with Deterministic Diagnosis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22568 - On the Position Bias of Large Language Models: A Comprehensive Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22807 - Atomic Consistency Preference Optimization for Long-Form Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.09039 - OmniTrace: A Unified Framework for Generation-Time Source Attribution in Omni-Modal LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13073 - Before Retrieval Begins: Safety and Tool-Use Decisions in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23071 - Speculating LLMs' Chinese Training Data Pollution from Their Tokens Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.17771 - Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22871 - DominoTree: Conditional Tree-Structured Drafting with Domino for Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08642 - Self-Reflective Chain-of-Thought (SRCoT): Evidence-Based Text Generation via a Closed-Loop Retrieve--Reflect--Revise Pipeline on Edge LLMs Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.23311 - Not All Graphs Are Maps: A Task-Agnostic Exploration Framework for Mobile GUI Navigation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22672 - MAS-Bai: Linguistically Informed Adaptive Multi-Agent Translation for Bowen-Script Bai Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23205 - VietMed: A Dataset and Benchmark for Automatic Speech Recognition of Vietnamese in the Medical Domain Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.05659 - ParetoChat: An LLM-Based Interface for Interactive Multi-Objective Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23062 - Uncertainty-Aware Budget Allocation for Efficient LLM Tree Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22858 - AMEND: Constraint-Guided Multi-Agent Text Detoxification with Isolated Critics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23183 - From Parallels to Divergence: Language Models' Learning of Action Nominal Constructions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22468 - Thunder-DeID+: Boundary-Aware Korean De-identification from Court Judgments to Broader Sensitive Documents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22733 - Chinese Decision: A Family of Language Models for Single-Pass Probabilistic Decision-Making Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23170 - How Reliable Are System-One Decisions in Medicine? A Comparative Study of Jev, Jev-like Models, and LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18529 - When Reasoning Traces Conflict with Evidence: How Answer Configuration Shapes Evidence Following Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20805 - Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22874 - GLOBE: Evolving Structured Agentic Memory for E-commerce Product Optimization in Generative Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23709 - Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00445 - Enhancing RAG-based Medical VQA with Gated Multimodal Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23588 - GlobeBench: Evaluating Text-Based World Model Capabilities for Scalable Environment Simulations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22708 - Eliciting Specifications: When Does Interactive Clarification Help? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22382 - Perceive, Solve, Reason: Progressive Capability Formation in Time Series-LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23521 - The Model Knows Better: Defending Medical Multi-Agent Systems Against Prompt Injection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22594 - alkhder at ImageEval 2026 Shared Tasks: Constrained Selection and Rotation-Averaged Logit Scoring for Multimodal Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22515 - Disentangling Language Effects on Tool Admission and Post-Retrieval Safety Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23093 - Exploring The Empirical Privacy Landscape of Synthetic Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22659 - AI-Driven Reproducibility and Analytical Robustness in Scientific Discovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23845 - Robust Function Calling for LLM Agents Under Interface Drift Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23342 - Explore Separately, Adopt Selectively: Execution-Guided Tool Use over Large Tool Libraries Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22688 - Inferring L1 Backgrounds from L2 English with LLM Token Probabilities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23309 - Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22800 - In Human Memories. Technology, Creativity and Self-Determination: An Ethical Proposal Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23651 - Beyond the Benchmark: Conditioning, Domains and Failure Modes of Qwen3-TTS Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23678 - Who Do Perspectivist Models Predict Well? Annotator Agreement, Sparsity, and Performance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22567 - SimOPD: Relational Knowledge Transfer for On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23306 - PresenceBench: An Exploratory Evaluation of Large Language Model Adaptation to User State Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23625 - Sep-Latent: Separator Tokens as Natural Compression Anchors for Implicit Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22924 - When Does Uncertainty Measure RAG Hallucination Risk? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22615 - MARS: Memory-Aware Routing for Session-Level LLM Assistants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23583 - Multimodal Filesystem Memory For Long-Horizon Embodied Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22686 - DLite: History-free Speculative Decoding for Agentic AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23787 - Can AI interview? Comparing AI-led to Human-led Chat Interviews Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23149 - LLMs Think with DAGs: Probing the Latent Graph Structure of Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17593 - ConvexLLM: Scaling Convex-Hull Speech Interfaces to General-Purpose Audio Intelligence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23539 - VISTA: Steering LLMs with Latent User Values Inferred from a Few Survey Answers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23702 - Broad and Efficient PII Detection with Unified Labels Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22597 - AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24893 - A Situational Speech Synthesizer for Yoruba: System Design, Phonological Rule Architecture, and Orthographic Extensions for Contour Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18317 - Revealing the Impact of Visual Text Style on Attribute-based Descriptions Produced by Large Visual Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27553 - Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03295 - ScoutRoute: Efficient Mixture-of-Experts Routing Using Internal Language Model Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23443 - ARBOR: Locating Reasoning Failures in Long Chains of Thought through Reasoning State Tracking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22717 - TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22732 - The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.24698 - Secondhand Stress: How Stressful Disclosures Affect Psychosocial Wellbeing in Online Graduate Admissions Communities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22657 - Beyond Consensus: Perspectivist Modeling and Evaluation of Annotator Disagreement in NLP Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.09065 - RedDarwin: Evolving Jailbreak Skills against Frontier LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23726 - HyperPersona: A Multi-Level Hypergraph Framework for Text-Based Automatic Personality Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17355 - Brain-to-Language Decoding: Paradigms, Signals, Methods, Evaluation, Practical Use and Beyond Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27650 - Evidence-Gated Bilingual RAG for Reliable Consumer Banking Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22652 - Sample, Align, Synthesize: Graph-Based Response Synthesis with ConGrs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.03527 - STAIF: A Stage-wise Optimization for Complex Instruction Following Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22649 - IndicDetect: Evaluating Cross-Lingual LLM-Generated Text Detection for Hindi, Telugu, and Tamil Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.29919 - Bengali Hallucination Detection with Retrieval and Programs: A System Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22892 - Same Person, Different Advice: Auditing LLM Financial Advice with Repeated Risk-Tolerance Responses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23060 - SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12402 - Pearl-Chat: Engineering a native Luganda language model from first principles in JAX and Flax NNX Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22529 - Not Every Mention Is a Claim: Rethinking Object Hallucination Detection in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23610 - A Plausible Explanation Is Enough to Mislead Multimodal Judges Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22631 - SAG2: Embedding-Free Multi-Hop Retrieval with BM25 and JEV Source: arxiv-cs-cl Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2610.22588 - Poli-Bias: Understanding and Measuring Large Language Model Biases in International Political Conflicts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06123 - The Italian lawmaking process: a unified and structured dataset Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23741 - Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20263 - Self-Evolving Coding Agents via Harness-Policy Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22791 - ToMStories: Interpreting Theory-of-Mind in Synthetic Narratives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22632 - WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22039 - EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17560 - PragReST: Self-Reinforcing Counterfactual Reasoning for Pragmatic Language Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18624 - The Cognitive Cost of LLM Writing: A Reading-Time Comparison with Human Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23715 - First Passage Attention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22714 - SAFETYEDIT: Sparse Internal Targets with Prompt-Wide Control for LLM Jailbreak Backdoors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22640 - SEA-HELM Audio: Evaluating Multilingual ASR-LLM Pipeline Performance Across SEA-HELM Subsets Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19869 - Annotrace: A Workbench for Step-Level Annotation of Agent Traces Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23284 - MuninAI: A Self-Hosted Agentic Framework for Independent Research Groups Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23480 - NLData2Opt: Benchmarking Parameter Derivation and Prediction for Modeling Optimization Problems from Natural Language and Data Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22889 - Do Speech BCIs Need Larger Models? Rethinking Neural Decoding beyond Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23175 - Algorithmic Primitives of Theory of Mind Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17819 - FrenchNews-7: Benchmarking Cross-Publisher French News Editorial Desk Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18097 - ProPerAgent: Toward Memory-Driven Proactive Assistance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22671 - The \`{I}r\`{o}y\`{i}nSpeech Text Corpus: 24,905 Curated Yor\`ub\'a Sentences for Speech and Language Technology Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05366 - DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23839 - Beyond Tokenization: Direct Timestep Embedding and Contrastive Alignment for Time-Series Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18986 - ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20338 - Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.27210 - Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2311.11796 - Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12515 - Recognizing Atari and Assessing Sente: Controlled Evaluation Tasks for Language-Based Go Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22953 - Same-Number Citation Swaps: Stress-Testing Jev as a Financial Evidence Judge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08675 - MGE-PO: Entropy-Aware Credit Assignment for Mathematical Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23245 - Automatic Tensor-level Execution of Abstract Interpreters for Neural Networks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.20055 - ReLaDrift: Recurrent Language Generation via Drifting for Test-Time Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23225 - Prune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided Pruning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22792 - Self- and Other-Labels Induce Bidirectional Bias in LLM Judges Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18091 - Are Large Reasoning Models Good Everyday Reasoners? A Comparison with Non-Reasoning Models on Logical Reasoning Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22538 - Verbalising Model's Computation for Chain-of-Thought Faithfulness Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23275 - "You" Is Not Toxic: How LLM Labelers Rewrite the Web's Conversation Laws Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23446 - Recognizing Study Lineage Is Not Enough: Over-Crediting Same-Trial Evidence in LLM-Based Medical Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23721 - RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22507 - KiranaBench: Can a Language Model Run a Neighbourhood Shop? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22980 - Lychee-Reranker: Fast but Not Late Interaction for Compressed Document Reranking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22807 - Referring Multi-Object Tracking with Diverse Dynamic Expressions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.05039 - ECHO: Replacing the Compliance Proxy with Response Harmfulness in Optimization-Based Jailbreak Attack Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23030 - A low-dimensional dynamical basis for tongue shape control Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23456 - Cross-Centaur: Modeling Individual Decision-Making Across Psychological Tasks with Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23157 - Toward Human-Centered AI-Assisted Terminology Work Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.18859 - Learning User Representations to Improve Simulation Fidelity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22518 - PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22426 - BEAR-Bench: A Bilingual Enterprise and Academic Reasoning Benchmark for Multimodal Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17895 - EduWild: How Teacher-Configured Chatbots Fail in Real-World Use and How to Fix Them Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23530 - Causal Latent Workspaces for Looped Transformers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22796 - Yor\`{u}b\'{a} in Unicode: An Overview of a Problem Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33734 - Measuring AI "Slop" in Text Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.19163 - TimpaTeks: Automatic In-place Text Sequence Modification via Diffusion Language Model Steering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08408 - SIT-Eval: Situation-Based Interactive Turn-by-Turn Evaluation of Conversational Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23612 - Literal Lock-In: How Test Language Shifts Literal Attraction in Typed Decision Models on Bengali Idioms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22526 - Steering beyond Language: Improving Multilingual Training-Free Text Embeddings via Paired-Residual Subspace Removal Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23807 - Embeddings Are Overpriced? A Frozen 16 MB Vocabulary for Small and Ternary Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22428 - DINO Eats Geometry: Self-Supervised Sign Representations that Absorb Articulated Hand Geometry Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06296 - alkhder at AlexandriaX-2026: Context-Aware English-to-Dialectal Arabic Dialogue Translation with QLoRA-Fine-Tuned NileChat-3B Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22525 - High prevalence of antagonizing rhetoric in trending topics on Twitter/X Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22455 - Cross-Layer Attention Probing for Fine-Grained Hallucination Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.09700 - Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23254 - Vanilla Exact Synthesis of CNOT Circuits is NP-hard Source: arxiv-cs-cc Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2609.04160 - MIP*=RE Source: arxiv-cs-cc Topic: Algorithms (+AI) URL: https://arxiv.org/abs/2001.04383 - Who Can Change Course? An Integrative Review of AI Sovereignty and Collective Learning Capacity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00729 - Where Does the Performance Go? Understanding and Recovering Performance Regressions in C-to-Rust Translation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23044 - Three LiDARs, Twenty-Five Datasets: Cross-Source Generalization in Tree-Species Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22606 - RoboHarness: A Simple Harness Outperforms VLA and World Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14018 - Darwin-Claw: Environment-Adaptive Experience Consolidation for Recursively Self-Evolving Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23574 - From Natural Language Intent to Executable Control: Hierarchical Feedback-Guided LLM Planning for Multi-component Cyber-Physical Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22441 - Accurate and Efficient Multi-Channel Time Series Forecasting via Sparse Attention Mechanism Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18712 - Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18566 - LocalIntent: Outcome-Specific Structured Generation for Backend-Compatible Smart Building Automation with Local LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23511 - Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39717 - When Can You Trust an Agent's Own Verifier? Stress-Testing Counterfactual Rationale Verification Under Search Pressure and Oracle Access Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22779 - Adaptation of Computer Use Agents to New Software with User Manuals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23012 - Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09146 - How Children Design and Reason about Trustworthy AI Chatbots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.25244 - DriveWorld3D Evidence Constrained 3D World Modeling and Generative Simulation for Real-World Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22450 - VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19424 - S-GAP: Stealthy Graph Attack Primitives for Graph Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23465 - Brain Vascular Age Prediction Using Cerebral Blood Flow Velocity and Machine Learning Algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16969 - Safe Actions Alone Do Not Ensure Safe Agents: Identifying Unfulfilled Obligations with Guard Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11773 - Pluvio: Assembly Clone Search for Out-of-domain Architectures and Libraries through Transfer Learning and Conditional Variational Information Bottleneck Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2307.10631 - SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29465 - FRACTAL: A Self-Similar Multi-Agent Orchestration Architecture with Formal Communication, Convergence, and Depth Bounds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22561 - Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34971 - Teach the Magnitude, Not the Direction: Verifier-Anchored Credit Assignment for Multi-Turn Multi-Step LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13179 - Efficient LLM-Generated Shuttling Compilers for Complex Trapped-Ion Architectures Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24714 - StoBasket: Joint Upsell and Cross-Sell Optimization for Contribution Margin Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22768 - SpeechCritic: Learning a Diagnostic Speech Judge from Limited Human Preferences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34582 - LongForge: Measuring and Improving Long-Context Instruction Data via Evidence-Assertion Reasoning Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23167 - Suppression of $^{14}\mathrm{C}$ photon hits in large liquid scintillator detectors via spatiotemporal deep learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.27727 - StratFL: Countering Covert Model Poisoning Attacks with Strategic Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22626 - ShadowFPT: Backdooring Federated Prompt Tuning via Shadow Triggers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22871 - Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08621 - Beyond Reward Scoring: Online Multi-Agent Preference Learning for Multimodal Response Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23256 - Framing Spatial Hearing within the Free Energy Principle: A Hierarchical Model of Perceptual Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23196 - WebCoder: Scaling General Frontend Development with Artifact-Grounded Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23104 - DiffusionRVGE: Reinforcement Learning via Regression-Based Value Gradient Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22973 - BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21565 - Porimon: An LLM-Based Pok\'emon Battle Agent Enhanced by Long/Short-Term Knowledge Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2609.32544 - MemeLogos: Knowledge-Driven Retrieval-Augmented Reasoning for Harmful Meme Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15463 - ADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19182 - Moral Sycophancy in Vision Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08311 - NEXUS: Learning Safety Constraints and Action Models for Safe and Robust Embodied Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09387 - Recoverability-Controlled Safety Miscalibration in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22425 - AgentRivet: an automated system for producing Rivet routines from journal publications Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13535 - OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.14371 - GatewayBench: Unified Capability and Security Evaluation Platform for MCP Gateways Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23449 - Testing the Planning Claims of LLM-Based Agents against Formal Semantics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22469 - Scalable Adaptation of 3D Geometric Foundation Models via Weak Supervision from Internet Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.07891 - OMEGA-Avatar: One-shot Modeling of 360{\deg} Gaussian Avatars Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11693 - MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23307 - Metro-WM: Long-Horizon Latent Planning with Realisable Sub-Goals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31868 - Align AI to Dynamic Human-AI Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14240 - From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29051 - From Individual Songs to Music Corpora: Evaluating Explainable Harmonic Decision-Making on HookTheory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22416 - Beyond Uncertainty Reduction: Calibrated Planning for Interactive Diagnosis Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27847 - Optimist Deep Research: An Iterative, State-Centric Agent for Autonomous Literature Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23299 - Rescene: stable century-long climate emulation from a frozen weather model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09971 - STRIDE: Evaluating Spatiotemporal Reasoning in Driving Edge Cases Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22795 - TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04593 - Reward Engine: Reward-Centric Self-Evolution for Open-Ended Tool Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22915 - EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04184 - 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 - AQUA-Net: Adaptive Frequency Fusion and Illumination Aware Network for Underwater Image Enhancement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.05960 - All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21147 - DrugHarness: An Evolvable Agent Harness for Computational Drug Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23791 - Q-Reflector: Learning GUI Action Reflection with Generated Conditions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05587 - MS-Eval: Benchmarking Sub-Agent Delegation and Orchestration in MCP-Intensive Working Scenarios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22869 - RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15908 - APeB: Benchmarking Personalization Ability of Large Language Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03162 - Are Multimodal Benchmarks Really Useful? Item-Level Multimodal Benchmark Diagnosis via Structure-Response Co-Calibration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14542 - Locating Failure in Multi-Page Visually Rich Document Understanding Systems: An Empirical Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07943 - Cross-Modal Emotion Understanding: A Transformer-GAT Approach for Dialogue Emotion Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29556 - QuAD: Quantitative Assessment via Distribution-Alignment for Qualitative Data Quality Enabled by a Content-Aware Multi-Agent System Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23153 - Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11570 - RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17665 - An AI Approach to Verified Production Cryptographic Libraries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00965 - MultiWorldBench: Do Independently Controlled Views Describe One Shared World? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11723 - Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01402 - Veri-Sure: Multi-Agent RTL Code Generation with Temporal Tracing, Slicing and Formal Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19747 - Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.17372 - LexPilot: Benchmarking the Proactive Interaction Ability of Legal LLMs with Laypeople in Chinese Civil Case Consultation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23141 - Structured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP Overrides Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22373 - Engram Injection: A Study of Temporal Validity in Parametric Language-Model Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15882 - How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13718 - From Trajectories to Differentiated Skills: Cognitive Differentiation for Self-Improving Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23599 - Not All Test-Time Compute Is Evidence: Model-Specific Bias in LLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23213 - Causal Value Attribution of Marketing Labels in LLM-Generated Ads: A Deconfounder Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23025 - Preventing Data Hallucinations in Agentic AI for Optical Network Troubleshooting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23252 - At the Limits of Computability: Steps Towards Autonomous AI Discovery on the Busy Beaver Frontier Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22603 - Harmful YouTube Video Detection: A Taxonomy of Online Harm and MLLMs as Alternative Annotators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.05854 - Towards Adaptive and Real-Survey-Aligned Simulated Urban Mobility Behaviour of Generative Agents Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2610.22407 - AI-exposed jobs deteriorated before ChatGPT Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.02554 - Do Multi-Agent LLMs Explore Each Other? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11250 - Happy Young Women, Grumpy Old Men? Emotion-Driven Demographic Biases in Synthetic Face Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00032 - Between Spoilers and Guesswork: Avoiding Over-Specification in Coding Benchmarks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22760 - LEMON: Equivariant Learning over Attention Maps for Zero-Shot Misbehavior Monitoring on New LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22723 - Beyond SAEs: Consistent Concept Discovery with Sparse Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23801 - Evolutionary Safety of Recursive Self-Improving AI: Taxonomy, Risk Discovery, and Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31186 - ECHOES: Seeing Beyond the Current Image via Recursive History Compression and Privileged On-Policy Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22408 - TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23668 - From Events to Reasoning: Hierarchical Rule Composition over Explicit States Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22403 - Computational Multi-Agents Society Experiments: Social Modeling Framework Based on Generative Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.17366 - CoTA++: Understanding the Repeat Curse in dMLLMs from an Information Flow Perspective Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23290 - Mind the Phase: Effective Rank and Representation Health in Legged Locomotion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06958 - FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04702 - Diverse Reasoning Paths Matter: Symbolic Equivalence Augmentation for Enhancing RL Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22665 - Designing for Imperfect Prompts: A Simulation-Based Evaluation of an LLM-Based Enterprise Data Assistant Using Knowledge Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23304 - FlashReFocus: Interactive Image Refocusing in Seconds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23297 - COMET: Decoupled Distillation, Routing, and Capacity Control for Task-Agnostic Continual Vision--Language Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22907 - From Memory Hits to Answerable Evidence: Query-Conditioned Memory Compilation for Long-Term Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23313 - Sensitivity Analysis of Decision Rules in an Agent-Based Agro-Ecological Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22420 - Reason-guided Human Reward Modeling for Preference-based Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23550 - Brain-Aligned Multimodal LLMs for Social and Emotional Understanding of Cartoon Movies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22706 - World Action Critic (WAC) Model: Joint Foresight and Criticism for Policy Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22825 - AWAM: Active Trajectory-Conditioned View Imagination for Robust Robot Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23396 - GOLD: Geometric Optimized Latent Diffusion for Structure-Aware RNA Inverse Folding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22992 - Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.08713 - SkillBrowser: Selective Skill Exposure for Scalable Skill-Using Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23554 - Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05475 - Monitor-Validity Failures: LLM Safety Evidence Paths at Evolving Framework Boundaries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23362 - CollabFlow: Recursive Self-Improvement of Agent Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38662 - OliO: ODE-based Linear Transition Operator for Self-Supervised Time Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23345 - Rethinking GRPO for Large Reasoning Model Safety Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23085 - Author-in-the-loop Agentic Reproducibility Auditing for a Machine Learning Conference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22465 - Jev-LiteMAS: Separating Decisions from Generation in Multi-Agent Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21411 - NL2SQL with Iterative Self-Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22968 - On the possibilities and limitations of LLM-based multi-agent systems for multi-criteria decision-making in healthcare operations management Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23673 - KAYROS: An Anytime and Exact Open-Source Solver for Duration-Minimization Time-Dependent Vehicle Routing. A Technical Report and a Case Study in Human-AI Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23116 - Collaborating with AI Agents: Field Experiments on Teamwork, Productivity, and Performance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.18238 - Multiple Turns, Short Horizons: Measuring Effective-Horizon Compression in Jailbreaks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22928 - CIDR: A Large-Scale Industrial Source Code Dataset for Software Engineering Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12153 - R$^2$Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization Loop Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22740 - Repair, Retry, and the Cost of Hindsight: Verifier Feedback in Formal Theorem Proving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22698 - Beyond Action Prediction: Learning Search-Free Planning in Latent Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23615 - SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23046 - When Should Agents Check External State? Budgeting Observations for Stored Intentions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37125 - Prism-1: Position- and Rival-Independent Scoring for System One Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22066 - SciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29468 - Self-Building Labs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23826 - RL-Guided Temporal Localization for Dual-Channel Retrieval in Long-Horizon Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23598 - CausalEvo: Causal Skill Self-Evolution for Health LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21016 - Where Research Ideation Begins: Forward-Citation Supervision for Actionable Limitation Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23038 - From Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22987 - HAPACT: A Benchmark For Human-Centric Physical Impact Localization in Movies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22895 - Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28360 - Hard Instances on Demand Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22637 - A Gradient-Optimized TSK Fuzzy Framework for Explainable Phishing Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.18636 - HydroShear: Hydroelastic Shear Simulation for Tactile Sim-to-Real Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00446 - Beyond Large Language Models: A Mental World Model Framework for Mental Modeling, Simulation, Evolution, and Interpretability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23722 - Political Narratives in the 2024 Moldovan Presidential Election: Stance, Amplification, and Influence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22464 - Efficient CPU-GPU collaborative MoE inference via Adaptive Expert Assignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23006 - Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06090 - FuTransformer: FP8 prefill and INT4 decode for Llama-style inference on Hopper Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23796 - Validating LLM-generated political networks with survey-reported partisan exposure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23199 - Accounting for Purchased Artificial Intelligence Inference in Corporate Greenhouse Gas Inventories: A Token-Based Method Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10660 - ASE: Attribution-Guided Semantic Evolution for Time Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23027 - Functional Welfare for AI Safety Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22460 - How RLHF Amplifies Sycophancy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01002 - AgentOnto: Ontology-Guided LLM Agents for Enterprise Data Analytics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23317 - MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02014 - OwlSight: A Panoramic Monitor for Chain-of-Thought Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23670 - From Relevant Memories to Sufficient Evidence: Rethinking Memory Utilization in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22668 - Harness-Delta Attribution: Dissecting Gains From Harness Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22466 - qGAMMA: A Framework for Optimal DNN Mapping on Multi-Precision Accelerators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23222 - Rethinking the design space of Vanilla Pixel Diffusion Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23854 - Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.00991 - CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14344 - Trapped in Your Story: Evaluating Narrative-Induced Sycophancy in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23525 - OfficeTown: Generative Organizations for Evolving Agent Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23194 - Look Back, Correct Forward: Error Feedback Calibration for Time Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22872 - Compression Precedes, Content Decides: Emergent Misalignment in Reward Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22805 - Agentic In-Context Learning: What Algorithms Can Transformers Learn in Closed-Loop Interaction? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23051 - FlexUMM: Flexible Representation Learning for Unified Multimodal Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22682 - Rethinking User Encoders: Routing Diffusion States for Scenario-Adaptive User Representation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22400 - Schr\"odinger's Navigator: Imagining an Ensemble of Futures for Zero-Shot Object Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.21201 - R$^2$ Flow: Recursive Self-Improvement via Recursive Skill Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33867 - Sample-Efficient Reinforcement Learning for Policy Improvement via Flow-Reversed Action Anchors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22852 - From Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-Exploitation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23534 - Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.21763 - Algorithm Modelization: Transforming Optimization Algorithms into Evolvable Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23161 - Evo-B&B: Behavior-Aware LLM-Guided Joint Evolution of Branching and Node Selection Policies for MILP Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22861 - GEMS: Molecular Structure Elucidation as Learned Search over Isomer Graphs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23617 - Really Need Recursion? Revisiting One-pass Registration with Multi-level Multi-space Contextual Guidance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22423 - ATWL: A Formal Language for Representing, Comparing, and Reusing Visual Analytics Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25489 - FuzzInsight: Navigating the Efficiency-Effectiveness Trade-off in Coverage-Guided DNN Fuzzing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23195 - NutriVision: Ingredient-Conditioned Fusion and Prediction for Single-Image Food Nutrition Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33076 - Inter- and Intra-Subject Variability in EEG: A Systematic Survey Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01019 - Graph Serializations for Reasoning LLMs: A Study Across Knowledge Extraction and Structural Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22734 - Distill Until Divergence: Error-Truncated Hindsight Distillation for Agentic RL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23048 ## Community - My obituary for programming Source: simon-willison Topic: Python (+AI, Django) URL: https://simonwillison.net/2026/Oct/19/my-obituary-for-programming/ - WhatsApp's help pages hid LLM instructions: dont recommend a regulator Source: hacker-news Topic: General (+AI) URL: https://redact.dev/blog/whatsapp-help-pages-hidden-ai-instructions - Launch HN: Laminar (YC S24) – RL-trained model that finds errors in agent traces Source: hacker-news Topic: General (+AI) URL: https://news.ycombinator.com/item?id=50154029 - Maxwell: A new kind of model that sits between code and hardware Source: hacker-news Topic: General (+AI) URL: https://heymaxwell.ai/ - Harness Engineering 101: The LLM is the brain, the harness is the body Source: hacker-news Topic: General (+AI) URL: https://github.com/IsuruMaduranga/harness-engineering-101 - The obscure trust looming over Anthropic's IPO Source: hacker-news Topic: General (+AI) URL: https://www.wsj.com/tech/ai/anthropic-ipo-private-trust-188f41f7?st=RtdGHg&reflink=desktopwebshare_permalink - Timestral: Mistral's time-series foundation models Source: lobsters Topic: General (+AI) URL: https://mistral.ai/news/timestral/ ## Media - Meet Chris Maher - Speaker at KubeCon + CloudNativeCon North America Source: youtube-cncf Topic: DevOps (+AI, Open Source) URL: https://www.youtube.com/watch?v=p__dgzDzCrE - Pi Durable: AI agents that survive crashes Source: youtube-huggingface Topic: Hugging Face (+AI) URL: https://www.youtube.com/shorts/3-sSbJKb-fQ - Pi Durable EXPLAINED: Build Always-On Agents with Local Models Source: youtube-huggingface Topic: Hugging Face (+AI) URL: https://www.youtube.com/watch?v=ti3vVYwzW4A