TILens Daily Edition 2026-11-06 Filters: topic=ai-research, github=hidden Stats: 743 articles, 6 sources, 737 research papers Top topics: AI, AI Research, Information Retrieval ## News - NVIDIA’s Plan to Stop AI Agents From Wasting Expensive Memory Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/nvidia-ai-agents-memory-waste/ - 😺 OpenAI released GPT-6 Cyber, a hacking AI Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/openai-released-gpt-6-cyber-a-hacking-ai/ - Trump's New Super Intelligence Task Force Has Two Very Different Jobs Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/doj-super-intelligence-task-force-explained/ - Claude Can Now Read Your Bank Accounts. How Private Is Your Financial Data? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/claude-bank-accounts-financial-data-privacy/ - Everything That Happened in AI Today (Friday, November 6, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-friday-november-6-2026/ - OpenAI's GPT-6 Cyber Can Hack Better. Can It Stay Within the Rules? Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openais-gpt-6-cyber-can-hack-better-can-it-stay-within-the-rules/ ## Research - How to Measure AI Adoption, Performance, and ROI With 12 KPIs Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-measure-ai-adoption-performance-and-roi-with-12-kpis/ - How to Manage Python Environments with uv Instead of venv and pip Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-manage-python-environments-with-uv-instead-of-venv-and-pip/ - Build Your First Multi-Tool AI Agent with Ollama and Python Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/build-your-first-multi-tool-ai-agent-with-ollama-and-python/ - Give Your Python AI Agent Persistent Memory with One JSON File Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/give-your-python-ai-agent-persistent-memory-with-one-json-file/ - Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14494 - Optimal Competitive Ratios for Chasing Convex Functions with Quadratic Growth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08078 - ThermoLLM: LLM-Based Multi-Zone HVAC Control with a Spatiotemporal Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22911 - DictLLM: Post-training Compression of Large Language Model with Dictionary Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08082 - DART: Domain-Agnostic Residual Transfer for Generalist Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08271 - Localization Does Not Imply Steerability: A Mechanistic Study of Sign Errors in LLM Mathematics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07478 - Detecting Weather Fronts from Satellite Observations: What Does Reanalysis Add? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08148 - Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09864 - KG-Neighbor: Knowledge-Guided Neighborhood Construction for Embedding Visualization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07246 - ConvPE: Convolutional Position Embedding Improves Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07749 - Stochastic Dynamics of Generative AI: From Autoregressive Models to Interacting LLM Networks and Neural SDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07065 - Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08493 - Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05558 - TSBPO: Tree-Structured Branching for Policy Optimization in Interactive Language Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41697 - Masked diffusion as random sequential adsorption: an exactly solvable model for parallel decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07845 - Structural Conditional Independence Test via Neural Quantile Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07165 - Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26032 - AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32602 - Inference and Uncertainty Quantification for Streaming $r$-PCA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18374 - Deep Neural Operator Learning for Probabilistic Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.07235 - Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisson-Moreau Drift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07104 - Hybrid Approach for Enhancing Lesion Segmentation in Fundus Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25549 - Continuous Adversarial MeanFlow for Few-Step Generative Adaptation from Any Parameterization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19540 - Transformer-Based Trajectory Prescription for sEMG-Optimizing Robot-Mediated Rehabilitation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08295 - TrustMix: Graceful Degradation for Pretrained Models under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07206 - 4D Point Splatting for mmWave Radar Micro-Doppler Differentiable Rendering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08342 - Population-Scalable Multi-Agent World Modeling across Scene Geometries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.08600 - Interpretable many-body interaction laws for collective motion from few trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08314 - Module-Aware Optimization for Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08379 - USB Gym: A Gymnasium Testbed for Closed-Loop Ultrasound View Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08352 - Depth-Recurrent Attention Mixture (Dreamer): Giving Latent Reasoning the Attention it Deserves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21582 - Write Facts the Way Models Read Them: Lifting the Two-Hop Curse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01519 - PromptOps: Iterative Prompt Optimization for LLM-as-a-Judge Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07123 - Human Responses to Algorithmic Correction: Evidence from Centre Court Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2401.16754 - Measured Coupling for Parallel Decoding in Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08307 - Zero-Shot Quantization via Weight-Space Arithmetic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03420 - Single-stage joint diffusion of sky images and clear-sky index for ultra-short-term irradiance forecasting: what the frame-to-irradiance stage discards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21795 - Invariance before structure: two modes of emergent compression in representation learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07952 - From Siloed Algorithms to Compliance-First Agentic Platforms: A Multi-Layered Architecture for Hospital AI Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06112 - Identifying Neural Dynamics Using Nonlinear Interventional State Space Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08113 - DUEL: Exact Likelihood Reshapes Masked Diffusion Scaling Laws and Beyond Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01367 - The Token Before the Value Is the Key Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15545 - Scientist World: Grow a Research World for AI-Scientists Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08478 - Same Answer, Different Future: Matched Predictions Do Not Imply Matched Belief Updating in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07913 - Geometric Relevance Is Not Sufficient: Evaluating Focused Post-Training Supervision in Diffusion Docking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08249 - Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19969 - Machine Learning Algorithms for Improving Black Box Optimization Solvers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25592 - Joint Modeling of Conditional Mean and Variability in Multilevel Functional Data: Application to Postprandial Glucose Trajectories in the AEGIS Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07937 - Measuring the Marginal Value of Verifier-Based RL Beyond Supervised Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07639 - Unifying Central Flow, Rod Flow, and the Edge Coupling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08358 - Reading a neuron's tuning from its correlations with other neurons Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06927 - FILO: A Unified Fisher-Geometric Framework for Low-Rank Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08734 - On the Rate of Gaussian Approximation for Online Linear Regression Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.14039 - An Assessment of Human vs. Model Uncertainty in Soft-Label Learning and Calibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18648 - HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03012 - Invariant Discovery for Networked Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22944 - From Fixed Defaults to Calibrated Activation Policies for Long-Term Time-Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06559 - Nowcasting of Tropical Cyclone Wind Fields and Intensity from Geostationary Imagery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08255 - Coverage Hides Churn: Auditing and Preserving Conformal Decisions as VLM Label Registries Grow Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07502 - Teaching Agents the "Principle", Not the "Reward" Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07130 - Statistical and Privacy Guarantees for Deep M-Regression via Stochastic Gradient Langevin Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07490 - CLaRE-ty Amid Chaos: Quantifying Representational Entanglement to Predict Ripple Effects in LLM Editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19297 - Decodability Is Not Validity: Evaluating Nuisance Sensitivity in Language Model Concept Probes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07805 - Reconsidering Positional Supervision in Masked Diffusion Language Model Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22947 - Robust Stream Classification using Time Neutralising Decision Trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06991 - Provably Efficient Representation Learning for Low-Rank CMDPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07295 - Bayesian Tensor Train Kernel Machines with Automatic Model Complexity Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07129 - ELF: Embedded Language Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10938 - FRESHPart: Feedback-Reshaped Spectral Embedding for Hypergraph Partitioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05729 - V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37019 - PBPO: Prefix-Block Policy Optimization for Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07783 - Graph Metanetworks for Transformer Based Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18471 - Binding Paraphrased Instructions to Encountered Objects in sLLM Agents under Partial Observability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07599 - Same Behavior, Different Mechanism: What Finite Experiments Can Certify About Integrated Information Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08469 - Gabor Gabor: E-Gaborformer, a Strictly Causal Speech Recognizer with Gabor-Dictionary Convolutions and Delta-Rule Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08092 - Octopus: One Brain, Many Branches for Latent-KV Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.06956 - Global $\mathcal{O}\left(k^{-2}\right)$ Convergence of Multilevel Gradient-Regularized Newton Methods Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35195 - Reproducing Kernel (Quasi-)Banach Spaces with the $\ell^p$ Coefficient Norms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08032 - Reweighting is not Harmless: Understanding the Role of Dataset Characteristics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07258 - When, Where, How: Active In-Context Learning for Tabular Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07886 - Which Signals of Code Correctness Survive Distribution Shift? Hidden-State and Causal Predictors of Program and Verdict Correctness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07876 - VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23504 - EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07909 - Learning to Think from Multiple Thinkers: How Chain-of-Thought Heterogeneity Affects Efficient Learnability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.24737 - TACT-KV: Tri-Axis Cosine Transform for Compressing Volumetric KV Caches in Medical VLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07593 - CoRD: Coupled Rollouts Fill the Blind Spot of On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07959 - Spectral symmetry fingerprints in equivariant representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07410 - Integrating Background Knowledge for Scalable Causal Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10456 - KeHoSu: Keyed Homoglyph Substitution for Authenticated Text Provenance over Copy-Paste Channels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08046 - Neural Compression over Equivalence Classes: Exact Gauges and Functional Rate-Distortion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07233 - Effective pruning of task-trained recurrent neural networks using noisy fluctuations and connection rescaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.05464 - Using Transformers for Teaching and Learning via Symbolic Distillation of Neural A-life Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07254 - Two-stage residual learning for calibrated uncertainty in solar irradiance forecasts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07444 - Spectral Thresholds in Correlated Spiked Models and Fundamental Limits of Partial Least Squares Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.17561 - Optimal Learning in Games with Arbitrary Delays: Best-of-Both-Worlds for Self-Play and Adversarial Opponents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07773 - Does Explanation Correctness Matter? Linking Computational XAI Evaluation to Human Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25251 - Invariant Features in Language Models: Geometric Characterization and Model Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06458 - Benchmarking Large Language Models on Heterogeneous Cognitive and Biomedical Knowledge Graphs: The Role of Graph Grounding in Multi-Hop Reasoning and Hallucination Mitigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08315 - Near-Optimal Decentralized Stochastic Convex Optimization over Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04757 - Knowledge Offloading: Decomposing LLMs into Sparse Backbones and Memory Modules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29075 - WaSP: Wasserstein Data Synthesis Pipeline for Solver-Free Operator Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07646 - CubeDAgger: Interactive Imitation Learning for Dynamic Systems with Efficient yet Low-risk Interaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.04897 - Do sEMG Foundation Models Improve Cross-Subject Generalisation? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08199 - PersonaAgent: Retrieval-Augmented Transaction Anomaly Scoring with Refreshable Multi-Entity Persona Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08094 - How Deep is the Signal? Time-Context up to 30 Years for Colorectal Cancer Prediction in a Primary-Care EHR Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07265 - How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08136 - CacheGraft: Enhancing Retrieval-Augmented Generation via Latent-Space Document Enrichment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07393 - Unified dynamics of training, learning, inference, and reinforcement in neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01345 - Last-Iterate Convergence of Stochastic Gradient Methods for Unbounded Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07334 - Scalable Bayesian Gaussian Process Classification for Cancer Histopathology: Calibrated Uncertainty Under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07127 - CCMP: Class-Conditional Multicollinearity Pruning for High-Dimensional Feature Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.12451 - Manifold-Constrained Initial Noise Optimization for Efficient Generative Model Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00365 - RM-VLM: From Natural-Language Task Descriptions to Vision-Grounded Reward Machines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08308 - Profile-aware diagnostics of discarded parameter-Hessian mass Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01335 - Server-Side Sparse Assignment for Federated Mixture-of-Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07093 - The Quantization Benefits of Residual-Free Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25880 - Extending Reasoning in Typed Decision Models via Looping Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07736 - Neural Stochastic Forecasting for Lateral Molecular Diffusion Simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06157 - MAC-v2: Long-horizon model-based value expansion from pixels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07245 - Data-Driven Modeling of Molten Chloride Corrosion Using Static Test Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07125 - Shaping & Monitoring Models through their Internal Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07071 - Provable Zeroth-Order Safe Exploration for Reinforcement Learning from Human Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07561 - Are We Overthinking One-Step Generation? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20331 - TabPFN beyond Tabular Data: Calibration and Accuracy on Multimodal Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11007 - Estimating Spectrum-Free Information Bounds for Generative Surrogates Beyond Conditional Collapse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07826 - Finite-Time Convergence and Regret Guarantees for Neural Reinforcement Learning in POMDPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07069 - Satisficing as competitive Bayesian weighting: a minimal model of goal-directed choice under an unattained target Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07270 - Towards Multiscale Molecular Representation Learning through Geometry-Based Fragmentation for Polymer Property Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07998 - Teach the Way It Thinks: Guiding LLM Post-training Data Engineering with Sparse Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.27354 - Machine Learning for Live-Birth Prediction After IVF/ICSI From Structured Clinical Data: A Systematic Review, Meta-Analysis, and Critical Appraisal Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07124 - Oracle-Robust Online Alignment for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.20457 - The Last Mile to the Real World: Agent-Native Primitives as Reusable Building Blocks for Solving Real-World Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07461 - Learning Dynamics of On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08016 - Sampling Design and Confidence Tubes for Integral Curves on Riemannian Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00771 - Label-Wording Augmentation in a Typed-Decision Encoder: Gains on Unfamiliar Words, Not on Abbreviations or Codes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08439 - Muir: Linear Attention with Sensitivity-Allocated Gating and Matched-Filter Readout Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08376 - Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09214 - Preference-Guided Adversarial Policy Optimization for Long-Tail Robust Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15221 - Adapters as Data: The Latent Space of LoRAs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07775 - Self-Improving Training & Thinking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21343 - Monotone Viability Learning for Offline Safe Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07616 - Diffusion-Driven State Space Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21036 - Speed limits for information acquisition in stochastic learning dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08219 - Prescriptive Scaling Laws for Data Constrained Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01640 - PROSWIN: Probabilistic Solar Wind Speed Forecasting Using Deep Distributional Regression From Solar Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26683 - Implementing Keyword Spotting on the MCXN947 Microcontroller with Integrated NPU Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.08911 - Understanding Data Influence in Transportation Networks: A Physics-Constrained Influence-Function Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07526 - Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13796 - FADE: Factored Ability--Difficulty Filtering for Online RLVR Scheduling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03625 - StepBack: Step-Level Error-Localized Resampling for Efficient Test-Time Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08403 - Privacy-Preserving Text Inference for Health-Misinformation Classification and Semantic Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20796 - Structured Machine Theory of Mind from Agent Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07208 - OPRD-Imp: a dataset of experimentally observed impurities and side products in multi-step pharmaceutical syntheses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07488 - LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07025 - More accurate behavioral predictions with hybrid Bayesian-connectionist models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22154 - AI-Native Task-Oriented Semantic Communications over a Relay: Benefits and Vulnerabilities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08155 - PPO in the Fisher-Rao geometry Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.03757 - A State-of-the-Art Review of Computational Models for Analyzing Longitudinal Wearable Sensor Data in Healthcare Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.21665 - Accelerating Safe Reinforcement Learning with Massive Parallelism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08273 - Instrumental Variables in Continuous-Time Stochastic Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07674 - When Scores Conflict with Preferences: Pre-Alignment Diagnosis and Adaptive Correction of Constraint Drift in DPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07375 - Unifying and Beyond the Theory of Pervasive Capability Degradation in LLM Post-training SFT from Feature Interference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05003 - ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor Memory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30858 - Corrective Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15596 - Optimistic Hedge in General-Sum Games: Fundamental Limits and Regret Bounds via Temporal Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07078 - Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07586 - Pareto DNN Verification: Fast for Most Queries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20755 - Structure from Collision via Hypothesis-Space Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07900 - Variational Estimators for Node Popularity Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.17783 - Reinforcement Learning for Adaptive Composition of Quantum Circuit Optimisation Passes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21629 - ZipDrift: Generating Multimodal Short-Horizon MPC Costs with One-Step Drifting Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05793 - Fractional physics-informed neural networks to model social media virality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07215 - LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21623 - Orbitol: Crystal Generation on Wyckoff Orbits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30086 - Evolutionary Adaptive Neighborhood Learning: A Genetic Algorithm for Instance-Dependent k Optimization in Nearest Neighbor Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07257 - $O(1/n)$ Convergence Rate for RVI $Q$-Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07676 - Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09258 - GTAFL: Addressing Test-Agnostic Long-Tailed Federated Learning in Medical Image Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08021 - Flux as a Codec: Zero-Shot Lossy Compression with Flux Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07929 - User Embeddings are Superpositions of Interpretable Behavioral Modes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08487 - Comparing Classification and Feature Learning by Analyzing Their Loss Functions in Normalized Spaces with Different Scale Factors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07741 - Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.18639 - Memory before Goal: Role of Pre-History Memory for Humanoid Loco-Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31166 - Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29475 - Using Transformers to Generate 3-Manifold Triangulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07514 - TANGO: RNA Topology and Geometry Co-Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20277 - Simple Meta-Learning for HPO and CASH Using Performance Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07659 - Uncertainty calibration in Bayesian M/EEG source imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06979 - Cross-Asset Knowledge Transfer for Early Fault Detection of Data-Scarce Assets Without Target Fault Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06194 - PeptSol: A Translational Benchmark for Protected-Peptide Solubility in Drug Manufacturing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00749 - Reward Budgeting Reduces Premature Convergence in Reinforcement Learning for LLM Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05942 - Reinforcing What the Student Has Learned: Teacher-Guided On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07722 - Conformal Prediction for Time-Dependent PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08409 - AttnSR: Attention Step Reward for Long-Horizon Agentic RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07932 - Undertone: Personalizing Frozen VLM Aesthetic Judges from Few Ratings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27110 - RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07512 - Online Conformal Prediction via Universal Portfolio Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03168 - English Calibration Erodes Lithuanian in Expert-Pruned Mixture-of-Experts Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07654 - HomID : Benchmarking Intrinsic Dimension Estimators on Homogenous Manifolds with Anisotropic Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.01335 - Physics-Attested Federated Learning: Securing Collaborative Anomaly Detection in Critical Water Infrastructure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34804 - Scaling Recurrence-aware Foundation Models for Clinical Records via Next-Visit Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.24562 - Characterizing universal object representations across vision models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13675 - Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08438 - Multimodal Information Interactions Bottleneck for Multimodal Self-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07718 - Adversarial Robustness of Kernel Machines: A Comprehensive Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07474 - How to Backdoor Image Knowledge Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.21323 - Dynamic Optimistic Constrained OCO with Memory via Delay Equivalence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08302 - Adversarial Multiplicity: Cherry-Picked Models and the Limits of Disclosure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07378 - Empirical Study of Pop and Jazz Mix Ratios for Genre-Adaptive Chord Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04998 - Synthesis of Ovarian Cancer Multi-Omics Datasets: A Biology-Informed Evaluation Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08394 - Test-Time Self-Play: Scaling without a Verifier Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07367 - GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27042 - KVBuffer: IO-aware Serving for Linear Attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.19049 - Latency-Aware Adaptive Best-of-$N$ Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07453 - DISCERN: Distributional Synthetic Replay for Retain-Free Incremental Machine Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07892 - Learning Multi-Agent Orchestration:Higher-Order Interactions in Policy Improvement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07495 - RAYEN: Imposition of Hard Convex Constraints on Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2307.08336 - RLVR$^{2}$: Reinforcement Learning with Verifiable Rubric-based Ranking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.23457 - Data-driven discovery of intrinsic Lie point symmetries of differential equation systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08421 - Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.20687 - scTREAT: Latent Diffusion for Single-Cell Drug-Response Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.11726 - Online Learning with Ordered Experts (via Two-point Feedback) Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07629 - ShapleyOG: Fast Adaptive Shapley Value Estimation with Odd Gaussian Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07173 - FAR-DPO: Feasibility-Aware and Robust Direct Preference Optimization for Cyclic Peptide Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19808 - Persona-Model Collapse in Emergent Misalignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12850 - A Survey of Nonlinear Filtering Methods for Data Assimilation and Recent Advances in Generative AI-Enabled Score Filters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07160 - No Escape from the Quadratic Barrier: Adaptive Attacks on Linear $\ell_2$ Sketches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25008 - Murmur: Efficient Long-Context ASR Inference with Hierarchical Chunking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01483 - EnergyBench: a live, gate-aligned benchmark of day-ahead forecasts for European power markets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07784 - VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02801 - Tell Me What To Learn: Generalizing Neural Memory to be Controllable in Natural Language Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23201 - Ordering Multivariate Time Series by Volatility Memory: A Temporal Convolutional Approach to Volatility Heredity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07746 - Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19065 - Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19246 - ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.02677 - Scaling laws for amplitude surrogates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.13308 - GigaBrain-WBC-0.5: A Behavior World Model for Robust Humanoid Whole-Body Tracking with Environment Interaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18234 - Canonical Correlation Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07212 - Distinguishing Initial-Condition and Model Error Using Machine-Learning Weather Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05592 - Non-Parametric Mutual Information Estimation with Vine Copulas Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07693 - Meta-Frieren: Beyond Single Level Online Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07169 - Selectivity and Shape in the Design of Forward-Forward Goodness Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13081 - Backdoor Containment via Expert Quarantine and Shutdown in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00663 - Detecting Silent Faults at the Environment-Trainer Boundary in Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08144 - Evaluating Language Model Features for Zero-Shot Time-Series Anomaly Detection Under Isolation Assumption Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07720 - ASAP: Attention Sink Anchored Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22372 - Vector Policy Optimization: Training for Diversity Improves Test-Time Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22817 - CytoBERT: A Foundation Model for Cytometry Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14414 - WeightLoop: Weight-Space Programming with Experimental Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07319 - MambaTG: Candidate-Aware State Space Modeling for Future Link Prediction on Temporal Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07569 - BUMP: Brief Unexpected Mid-Interpolation Peak Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08182 - FastWave: Optimized Diffusion Model for Audio Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04122 - Parameter Exploration for RLVR via Variational Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09805 - StrataFlux: Memory-Hierarchy-Native Low-Bit LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08363 - Big Models, Small Gains: Frozen Forecasters as Classifiers on MONSTER Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06988 - Set-Valued Routing for Language-Model Agent Systems: A WildChat Benchmark and Cost-Aware Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28925 - Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach Duality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25807 - VTAM: Efficient Visuo-Tactile World-Action Models for Contact-Rich Manipulation without Tactile Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.23481 - CSI-JEPA: Towards Foundation Representations for Ubiquitous Wi-Fi Sensing with Minimal Supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14171 - Fixed-point neural samplers on discrete spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01739 - Should We Pay This Much for Robustness? Efficient Proxy Certificates with Marginal Guarantees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08035 - Graph Neural Networks for Resource Allocation in Integrated Sensing and Communication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07277 - Learning Rate Transfer for Hybrid Transformer-SSM Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01172 - A Proxy-Based Method for Measuring Racial Disparities in~Text-to-Image~Generators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07132 - QRAE: Query-Relevant Attention Entropy for Context Compression in DeepSearch Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07976 - A Hidden Markov Preference Model for Online Prediction of Adversary Actions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08445 - SHORE: Stability-Hybrid On-Policy Reinforcement Learning for Online Bin Packing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08364 - Best-of-$N$ Guidance for Test-time Diffusion Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05108 - P$^2$-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03953 - Echoes of Error: Residual-Directional Local Rollout Consistency for Timeseries Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07473 - InfMasking: A Unified Variational Framework for Synergistic Multimodal Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07702 - Foresee to Trade: Forecast-Augmented Policy Optimization for Portfolio Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07750 - Sonar-MoE: In-Backward Expert Updates for Memory-Efficient Mixture-of-Experts Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03577 - Learning and Steering in Incomplete-Information Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07589 - Capturing Membrane Dynamics and Spike Timing of Human Neurons at Scale using Neural Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06933 - Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14430 - Beyond Quadratic Attention: Separable Gaussian Operators for ODE Vision Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08236 - An Information Bottleneck for Post-hoc Memorization Mitigation in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07669 - Scenario Augmentation for Rare Financial Events via Multimodal Latent Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07282 - EmboTeam: Asymmetric State Grounding for Heterogeneous Multi-Robot Collaboration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.11063 - Volterra Generative Models via Markovian Lifting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18071 - KOSMOS: Self-scheduling Persistent Kernels for Communication-Compute Overlap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07477 - Credibility Clustering for Experience Rating: An Automated Approach to Risk Group Allocation in Group Life Insurance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07110 - Patch Attention Wisely: Understanding Patch Length in Attention-Based Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08160 - Discovering Learning Rules that Shape Others Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08335 - Hybrid Dual-Batch and Cyclic Progressive Learning for Efficient Distributed Training of Convolutional Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.26092 - Adversarial Training with Large Step Sizes: Implicit Bias, Optimization, and Sharpness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08457 - Explicit 3D Gaussian Models for Fast, Mesh-Free Compression of Structured and Unstructured Volumes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01164 - Structure-aware Reinforcement Learning for Protein Directed Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39048 - Emergent Generalization by Representation Learning in Artificial Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10430 - How Far Can a Trainable Frequency Move? Resolution, Grids and Coupling in Trainable-FrequencyQuantum Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23409 - LatentGym: A Testbed For Cross-Task Experiential Learning With Controllable Latent Structure Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15306 - Calibrated Target Noise Recovers Curvature from the Gradients Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07671 - Visual-Redundancy-Controlled Parallel Decoding for Diffusion-Based Multimodal Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25820 - Multi-objective Hyperparameter Optimization with Expert Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.08371 - Energy Measurement and Optimization of TinyML in Resource-Constrained Embedded Systems: A Systematic Mapping Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07264 - FastAFD: When Does Attention-FFN Disaggregation Pay on Rack-Scale NVLink? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07149 - Unraveling Groundwater Stress: A Model Generalizable Across Space and Time Reveals Co-Declining Water Tables and Recharge Across Bangladesh Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.22771 - TileQuant: Tile as the Precision-Allocation Unit for LLM Mixed-Precision Post-Training Quantization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07217 - The Blindfolded Controller: Decision Model-Guided Training for Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07934 - Acoustic Anomaly Detection for Early Identification of Drill Jamming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07356 - Static Recovery Is Not Dynamic Stability: Dynamics-Aware Benchmarking of Protein Motif Scaffolding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07723 - How do Transformers Perform Low-Level Control In-Context? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07291 - Recursive Sparse Attention: Million-Token Length Extrapolation at Logarithmic Cost Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07232 - Minimal Filling Architectures for Polynomial Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09609 - Synthesizing symbolic models of human and machine reasoning at scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07088 - Goal Revelation as a Bridge Between Information-Theoretic Empowerment and Capability-Based Human Power Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07247 - $D^2$-OPD: Separating Direction and Distance in Extrapolative On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07241 - Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16565 - The Alignment Tax Is Graded: Task-Selective Capability Loss Under Length-Normalized DPO with SFT Retention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06476 - B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.22252 - Genome-Factory: A Library for Tuning, Deploying, and Interpreting Genomic Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.12266 - Muon Sublates the Edge of Stability in LLM Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34915 - Tight Generalization Bounds for Noiseless Inverse Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08866 - DynSHAP: Towards Explainable Dynamic Survival Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13042 - Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06152 - Spectral and Subspace Dynamics of LoRA in Supervised Fine-Tuning and Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08414 - Trust the Mass: Forced Weights in KV-Cache Eviction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25230 - Efficient Kernelized Learning in Polyhedral Games Beyond Full-Information: From Colonel Blotto to Congestion Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.20919 - LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03079 - LAPLEX: The FFT of Learnable Laplace Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24584 - Langevin Monte-Carlo Provably Learns Depth Two Neural Nets at Any Size and Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.10428 - Hybrid Machine Learning for Imbalanced Landing-Phase Safety Event Prediction from Flight Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08386 - Context-Aware Automated NMR Structure Elucidation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07133 - ZYFA: Speed and Accuracy of FP8 FlashAttention on AMD CDNA4 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07496 - Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06207 - On the limitations of molecular representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08420 - AtlasULP: Domain-aware Universal Link Prediction via Relation Atlas Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07347 - Enhanced MRI brain tumor detection using deep learning in conjunction with explainable AI SHAP based diverse and multi feature analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07843 - Depth or Description? When a One-Step Latent Score Replaces Lookahead in Proactive Information Acquisition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07155 - How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07334 - Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.18938 - Computation, not weight access: large language models as auditors of clinical prediction networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07847 - Truncated backpropagation through time induces a two-sided gradient turnpike property Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07415 - FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08240 - Unpacking the Compute Efficiency of Strong-to-Weak OPD against GRPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08453 - Tight Asymptotic Bounds on the Maximum Number of Linear Regions of Piecewise-Linear Kolmogorov--Arnold networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07973 - Extracting Single-Mode Rayleigh--Taylor Instability dynamics from data via SINDy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07666 - Approximating the Euclidean Ball by Polytopes: Surprising Rates in High Dimensions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34651 - ToroFit: Fitting Wedge Sums of Tori to High-Dimensional Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06990 - Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01993 - Rethinking Data Selection: The Importance of Coverage over Difficulty in LLM Fine-Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07323 - UniSD: Towards a Unified Self-Distillation Framework for Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06597 - Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry-Task Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01828 - Deep Barycentric Regression for Optimal Transport Map Estimation and Its Statistical Optimality Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06598 - Interpretable Multimodal MRI-Clinical Fusion for Functional Outcome Prediction After Acute Ischemic Stroke Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08154 - PlayGen2: Learning Real-Time Playable Worlds with Explicit 3D State Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07867 - Twig: Parallel and Memory-Efficient Tree Speculative Decoding for Hybrid-Attention LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01651 - A Behavioural Framework for Predicting and Understanding Loss of Control in Frontier Artificial Intelligence Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07953 - HarmonICA: Quasi-Time-Invariant ICA for Motor Unit Decomposition during Dynamic Contractions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.19581 - IMUDINO: Self-distilled Foundation Model for Inertial Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07437 - AAC: Admissible-by-Architecture Differentiable Landmark Compression for ALT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.20744 - La-JEPA: Compact Robot Policies with Latent World Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08156 - Greedy Alignment Principle for Optimizer Hyperparameter Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.06370 - Stability and Generalization in Looped Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.15259 - A Neural Operator based on Dynamic Mode Decomposition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.01117 - Large Language Models for Cryptocurrency Transaction Analysis: A Bitcoin Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.18158 - One Method Does Not Fit All: A Large-Scale Benchmark of Imputation Methods for Single-Cell RNA Sequencing Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.24626 - Loopback Transformer: Towards a Unified View of Residual Looped Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07226 - BrainPFN: Amortized Brain-Behaviour Prediction via Prior-Data Fitted Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06934 - A Night at the LLM Zoo: Data Conditioned Flow Matching for Generating Pretrained LLM Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07103 - Variable-aware representation, not relation typing, explains the performance of an event-graph model for ICU mortality prediction: temporal and external validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02663 - Scaling Laws for SAE Training Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07756 - Embedding-Space Fingerprinting of LoRA Fine-Tunes: Recovering the Training-Data Domain from the Model Artifact Alone Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07610 - Compositional Unalignment: Auditing Safety in Large Vision-Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07216 - SteelAgent: LLM-Orchestrated, Physics-Informed Steel Property Prediction with Audited Generalization and Calibrated Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06953 - Value or Attention: Investigating Layer-wise Relevance Propagation for Graph Attention Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08088 - Peer-Grounded Counterfactual Path Planning for Chronic Health Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30838 - Can an LLM Actually Reason and Program about Neural Network's Weights or is it just memorization on steroids? Exploring "Weight-Space Programming" Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08070 - CoMPAS3D: A Dataset and Benchmark for Interactive Motion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.19684 - From What Is Used to What Is Missing: Rethinking Dynamic Rank in LoRA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07349 - Series-wise Cross-validation for Global Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08252 - Neural Collapse on Imbalanced Datasets and Open-Set Scenario Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07753 - Implicit Regularization via Spectral Neural Networks and Non-linear Matrix Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.17595 - Equivariant Deep Learning in Direct-Product Space for Electronic-Structure Hamiltonian Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07695 - Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.26942 - Gradient Boosting for Efficient Rank Discovery in Tensor Network Kernel Machines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08093 - Permanent and Transient Representations for Continual Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07327 - The Stability of Online Algorithms in Performative Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.24207 - Improving Context-Shift Robustness of Convolutional Networks via Context-Regularized Cross-Entropy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08157 - Regulating Autonomous Mobility-on-Demand Operators with Fixed and Adaptive Penalties: A Multi-Agent Reinforcement Learning Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07122 - AutoCompress: Automated Hardware-Guided Model Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08290 - Task-Calibrated Random Features via Influence-Based Error Cancellation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07209 - Asymptotic-Preserving Tensor Neural Networks for 3D High-Field Kinetic Equations with Applications to Uncertainty Quantification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07364 - Archetypal contexts in the neurons of language models: an architecture for intelligence? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07234 - Leakage- and Label-Aware Benchmarking of Class-Imbalance Strategies for Multimodal Chest X-Ray and EHR Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07950 - Social Humanoid: Socially Responsive Human-Humanoid Interaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08407 - Mean and Variance Estimation Complexity in Arbitrary Distributions via Wasserstein Minimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.10172 - SAE Interprets MoE: Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08089 - RL Forgets! Towards Continual Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04364 - Mirror Descent-Ascent for mean-field min-max problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.08106 - The Standard Interpretable Model: Design interpretable machine learning methods from elementary symmetries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12289 - Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00685 - XStack: A Benchmark for ML Repo Migration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08472 - Online Budget Allocation with Censored Semi-Bandit Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.05844 - A Locally Tokenized Generative Model for Robust Time-Series Watermarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19727 - Regret Bounds for Profit Maximization in Bilateral Trade: Learning the Best Posted-Price Mechanism Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08173 - Randomized and Oracle-Based Feasible Directions Methods for Nonsmooth Nonconvex Constrained Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07691 - TriAttention: Unified Sparse Mixed-Precision Attention for Long-Context LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07256 - Rigorously Certified Neural-Network Computation of Nonlinear Water Waves at Near-Machine Precision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07395 - The Memory Trap: Language Agents Overgeneralize from Benign Interactions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07554 - Scaling Neural Motor Decoding via Decoupled Behavioral Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08263 - Performance metrics in machine learning: a scenario-based guide from the confusion matrix to calibration, regression and uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08048 - When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41970 - Improving Signals, Declining Encoder: A Known-Answer Test of Label-Free Monitoring in Self-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35766 - The State-Prediction Separation Hypothesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01218 - Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13657 - Towards interpreting any residual stream direction by scaling activation inversion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08465 - Instruction-Tuning Large Language Models with Medical Classification Data Improves ICD Coding of German Tumor Diagnoses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.13624 - Multi-step SWE: Can Coding Agents Keep Building on Their Own Code Over Long Horizons? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07166 - Differentiable Knapsack and Top-k Operators via Dynamic Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21775 - Structural and Representational Agency in LLM-Driven Timbre Generation and Interpolation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12532 - Q-Learning under Finite Model Uncertainty Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2407.04259 - Counterexamples and Sufficient Conditions: Comments on "Optimally-Transported Generalized Method of Moments" Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20260 - When Attribution Patching Lies: Diagnosis and a Second-Order Correction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09899 - Backbone-Informed Adaptation after EEG Pretraining: A Capacity-Controlled Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07192 - ACSeL: Adaptive Configuration Search for Hardware-Constrained LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07570 - Persistent Retrieval for Conversational Agents: A Study of Retrieval Efficiency Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07899 - HGCRS: Hypergraph-Enhanced Generative Conversational Recommender System Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.21987 - Beyond Independent Predictions: Learning the Browsing Journey for Sequence-Level Re-ranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07591 - Domain-specific information retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.08228 - CORE: Coarse-to-Fine Search with Context Management for Deep Research Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07859 - Multimodal Graph RAG for Long-range Visually Rich Document Understanding Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.28780 - ArcadeDB in Python: An In-Process Multi-Model Database Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07971 - OneRanker: Unified Generation and Ranking with One Model in Industrial Advertising Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.02999 - Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.13277 - FloodSQL-Bench: A Retrieval-Augmented Benchmark for Geospatially-Grounded Text-to-SQL Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2512.12084 - MEMOIR: A Training-Free Memory Lifecycle for Long-Horizon LLM Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07631 - Merge and Branch: Efficient Tree-Structured Supervised Fine-Tuning of LLMs for Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.37973 - Generative Retrieval under Real-Time Supply Constraints in Local Commerce Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.06323 - WISE: An Agentic Framework for Whole-page Multimodal Search Experience Attribution Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.06777 - Probabilistic Relevance Decisions for Semantic Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.08014 - EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2605.12887 - GINGER: Spicing Up Graph-Based Vector Search Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.08306 - HyperSU: Corpus-Driven Semantic-Unit Hypergraph for Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.28351 - ZeroRAG: Adaptive Semantic Peer Routing for Decentralized Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07928 - BRIDGE: Bridging the Semantic Quantization Gap for Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07425 - Reducing Representational Interference in Retrieval Embeddings with Trainable Prefix Tokens Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07298 - NEAR: Neighborhood-Aware Residuals for Memory Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2610.13314 - MEvince: Knowledge-Constrained LLM Reasoning for Technique Identification from Malware Reports Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07486 - OptST: Optimizing Semantic Tokenization for LLM-Enhanced Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07523 - Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2609.30467 - What Gets Hacked in a Collaborative Reward for LLM Recommenders: The Part That Does Not Depend on the User Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07588 - Decision Models as Retrieval Gates Against Injection and Pollution Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.08325 - Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07851 - AgentSelect: Benchmark for Narrative Query-to-Agent Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2603.03761 - MapHub: Daily Relevance Heatmaps of New arXiv Preprints for a Research Community Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.07174 - LIBRA: Programmatic Induction of Executable Tool Libraries Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05445 - Two Uncertainties Are Not One: Disagreement versus Decision-Risk in Cheap Structured Content Moderation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33258 - Adapting LLM Judges to Observed Human Annotation Policy through Soft Prompt Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07126 - ProQuant: Progressive Quantization-aware Training for Edge MLLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08216 - Value Over Language Model: Detecting Original Contribution in Writing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00700 - {\tau}-bench-LILT: Evaluating Conversational Agents on Realistic Multilingual Tool-Use Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07203 - Different Corpora, Different Skills? A Paired Study of Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07812 - HyFlash: A Prefix-Memory Prior for On-Device Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07263 - Encoding and Propagation of Grammatical Number in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07283 - Can Statistics Tell Whether an Undeciphered Text Is Language? Calibrated Tests on the Voynich Manuscript Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34499 - SAFE-Teen: Evaluating Chatbot Safety Across Adolescent Mental Health Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07218 - Source-balanced Capped Fisher: Bounded Evidence Aggregation for User Inference in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07228 - Can LLMs Reason in a Legally Meaningful Manner? A Small-scale Study on European Court of Human Rights Cases Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.17168 - Contextual Pictograms for Repairing Multilingual ASR Errors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05637 - TACG: Trajectory-Aware Commit Gating for Diffusion Language Model Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03236 - P2N: Reusing Deep Representations for Greater Effective Depth Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25076 - SPARE: Fast Linear Attention Decoding with Compact Recurrent States Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07552 - LLM-Assisted Label Noise Correction for EEG-Based Sleep Stage Classification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08311 - Recursive Self-Improvement for Long-Horizon Role-Playing Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07469 - Continued Training of Continuous Language Flows with Token Identity Squared Supervision Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07721 - Knowing When to Teach: Learning from Teachable Prefixes in Multilingual Reasoning Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08179 - FINCOSMOS: An Open-World Evaluation Paradigm for Agents in Finance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07464 - Studying word order through iterative shuffling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2109.04867 - Beyond Empathy: Integrating Diagnostic and Therapeutic Reasoning with Large Language Models for Mental Health Counseling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.15715 - JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25240 - FindLink: Learning to Assess Scientific Connections from Source-Grounded Premises Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02545 - Multi-Estimate Elicitation Does Not Uniformly Debias Language Model Judgments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00597 - Automatic keyphrase extraction and annotation: modern theoretical approaches and practical solutions for text and speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08006 - CardioLM: A multilingual suite of small language models for the cardiology domain Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07940 - ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13274 - Towards Foundation Decision Models: Drex Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07854 - "Blind Compliance": Coercive Control in AI Jailbreaking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08226 - EvoDesign: Agentic Editable Diagram Creation via Design Expertise Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.09568 - AutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36980 - ReviewMap: Mapping Evaluative Acts and Automation Boundaries in Peer-Review Comments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07489 - Follow the Policy, Fail the Benchmark: Auditing and Revising Policy-Based Decision Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07042 - Vision-Default, Prior-Override: Causal Mechanisms of Perception-Knowledge Conflict in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28273 - Beyond the Keyword: A Human-Annotated Benchmark for Arabic Anxiety-Related Discourse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07949 - Influcoder: Distilling Decoders' Gradient Influence Rankings into an Encoder for Data Attribution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13668 - StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.01707 - The Judge is Part of the Experiment: Auditing Peer Context Sensitivity in LLM-Based Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2608.04463 - Evaluating Token Probabilities as Confidence Estimators in Human Behavior Simulations: A Case Study in Luxembourgish Next Like Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07735 - Fine-Tuning a Transducer for Impaired Speech: Where the Gains Appear and What They Mean for Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07587 - Reclassification Is All You Missed: Surfacing Variant Reinterpretation Need in Online Health Communities at Population Scale Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07054 - SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07558 - BlockLock: Reproducible LLM Inference with Fixed Batch Geometry Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06977 - SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31145 - Beyond K/V Caches: Cross-Model State Handoff in Hybrid Linear-Attention LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08133 - Coding with the Enemy: Can Human Developers Detect AI Agent Sabotage? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05647 - XBridge: Entity-Grounded Latent Bridge for Heterogeneous LLM Communication Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11676 - Agent-R$^2$: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08219 - Post-Training Large Language Models via Reinforcement Learning from Self-Feedback Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.21931 - Parametric Skills Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30015 - Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08281 - Your Multimodal Speech Model Says I Have a Face for Radio Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30472 - Compression Through a Context Lens: Evaluating Adaptation, Quantization, and Distillation in Arabic Legal LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07988 - Polarity Classification with Multitask Learning Syntax Augmentation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08323 - Interactive Backdoor Attacks in LLM-Based Proactive Dialogue Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06969 - Axis-LoRA: Probing and Adapting Embedding Models for Personal-Memory Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07820 - What Patients Say They Can't Access: Mining Cancer Screening Barriers from Online Communities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07113 - Automated Video-to-QA Pipeline: End-to-End Question Generation and Verification Using Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07755 - Matriarchy Classics: A Computational Approach to Swap Only Gendered Words in Classic Novels Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07134 - Consistent yet Contextual: Learning Author-Level Mixtures of Style for Authorship Attribution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07111 - Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08237 - EnvOpt: Automated Optimization for Agent Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07372 - When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23379 - Do Recommenders Need to Think in Words? Latent Reasoning for Efficient LLM-Based Recommendation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07866 - Linguistic boundaries emerge from pressure-constrained processing dynamics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08085 - Enhancing Repository-Level Code Completion with Reinforcement Learning in Real-World Scenarios Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07510 - Bridging Structure and Semantics: Knowledge Graph Verification via Triple-to-Text Alignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07780 - How Do AI Agents Waste Your Money? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07238 - On the Opportunities and Challenges of Prefill-to-Autoregressive Cross-Model Transfer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06976 - ATHAAR: A Medieval Scientific Arabic Manuscript Dataset for Handwritten Text Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08091 - AraEngage: Interpretable Linguistic Correlates of Engagement in Arabic Facebook News Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07926 - Cultural Adaptation within Repeated Social Interactions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08334 - Sign Language Recognition and Translation for Low-Resource Languages: Challenges and Pathways Forward Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12096 - SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08196 - O$^2$PD: Overlap-Gated On-Policy Distillation on Reliable Prefix Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07731 - Generate-then-Rank: Learning Symbolic Goal Interpretation for Embodied Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07825 - The Male Abstraction Bias in Internet Culture and Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05730 - Dataset Collection and Fine-Tuning of NLLB for German--English Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07797 - MedGraph: Maintaining Patient State with Graph Memory for Long-Term Medical Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08433 - MemForm: Benchmarking Memory Formation Poisoning in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14431 - Soft Token Alignment for Cross-Lingual Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26466 - Each Insufficient in Its Own Way: Calibrating Language Models Across Varying Evidence States Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33237 - Closed-Loop Agent Evaluation: Layered Measurement and Self-Calibration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07051 - How Far Can Lightweight LLMs Go in Intent-to-SLO Translation? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07982 - Screen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2609.30137 - Automated Feedback to Peer Tutors Increases Their Talk Moves and Learner Reasoning but Not the Balance of Talk Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07072 - The Geometry of Simulated Perspectives: Dissociating Representation and Behaviour in a Multimodal Language Model Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08262 - Majority Bit-Aware Watermarking For Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.03829 - The Unsampled Truth: Quantifying Prompt Artifacts in LM Psychometrics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03357 - From Twisted Facts to Rogue Agents: Can LLMs Reliably Detect Multi-Dimensional Hallucinations? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08231 - Unified Hallucination Fuzzing for Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07525 - RouteAlign: Aligning Task Requirements with Model Profiles for LLM Service Selection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08162 - SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35596 - ToolSearcher: Optimizing Tool Selection at Scale via Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30906 - Projection-Free Evolution Strategies for Continuous Prompt Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13786 - SpecCTMC: Exact Speculative Simulation of Diffusion Language Model Continuous-Time Markov Chains Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08362 - TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07962 - HyperGraphPro: Progress-Aware Reinforcement Learning for Structure-Guided Hypergraph RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17755 - The Gating Mechanism of KV Cache Eviction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07605 - Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08269 - The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06989 - MOMASPLAT: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08372 - TraceViT: Grounded Trace Supervision for Visual Abstract Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29586 - When Imperfect Automated Fact-Checking Backfires: Social Learning in the Presence of Misinformation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08053 - A Generative Foundation Model for Multimodal Tokamak Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08153 - The Intrusion Pathway: How Non-Evidential Context Degrades Language Model Performance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07778 - AI-Generated Image Detectors Exploit Global Artifacts: Evidence from Inpainting Exchange Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00192 - Technohybridism: Recursive Semantic Normalization in AI-Mediated Societies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07984 - Robustness of Internal Signals for Hallucination Detection in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27041 - THG-Omni: Traceable Human-Centric Graph Supervision for Video Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07836 - PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.01279 - GAAC: Lossless KV Compression for Bandwidth-Efficient LLM Inference on Personal Devices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38210 - ChemE-as-Code: An Open-Source Platform for Agentic AI in Chemical Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07947 - Circe: Training-Free LLM Self-Evaluation via Component Interaction Consistency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07948 - The Physical Cost of Context: Quality-Constrained Resource Accounting for Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34763 - BabyTheorist: A Benchmark for Learning to Theorize the World from Observation Alone Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08177 - Goal-Branching LaCAM: Temporary Goals as Search Branches in Dense Multi-Agent Pathfinding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07528 - SAVeR$^2$: Reasoning-based Safety Alignment for Large Reasoning Models via Verifiable Rewards Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07482 - VisionSIM: Beyond Idealized Sensors - A Multi-Modal Simulator for Robot Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08368 - Cue-guided dual-path reconstruction with adaptive multi-scale response refinement for low-light image enhancement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16482 - PanoWorld: Geometry-Consistent Panoramic Video World Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.15391 - Align Before Aggregation: Basis-Consistent Federated LoRA under Heterogeneous Ranks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07598 - StreamMemBench: Streaming Evaluation of Agent Memory for Future-Oriented Assistance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14571 - ACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35375 - ActQuant: Sub-4-bit Action-Guided Backbone Weight-Only Quantization for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24011 - Don't Prompt Your Agents. Equip Them: Skillware as a Modular Standard for Sovereign, Auditable, and Deterministic Capability Execution for Logical Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07652 - InnerLogic-Surg: An Open Surgical Foundation Model via Continual Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07883 - How Should Agents See Code? Rethinking Code Representations for Agentic Software Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07286 - Whiel: A Neurosymbolic Platform for Certified Relational Program Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05612 - ASTRA-bench: Evaluating Tool-Use Agent Reasoning and Action Planning with Personal User Context Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01357 - Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08318 - First-Token Attraction in Mamba Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08303 - The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.22818 - What the Middleman Delivers: Answer Behavior, Tool Permissions, and Billed Usage in LLM API Relays Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07650 - FARR: Forecast-Aware Residual Refinement with Matched Endpoint Evidence for Long-Horizon Time-Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07870 - Position: Agentic Evolution is the Path to Evolving LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00359 - CTFS : Collaborative Teacher Framework for Forward-Looking Sonar Image Semantic Segmentation with Extremely Limited Labels Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21071 - Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07342 - ApproxBrain: Certified Sufficiency Frontiers in Connectome-Constrained Neural Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06929 - Vision-Language Models Are Joint Denoisers in Robotic Action Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01215 - AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25667 - PhysTrace: Interpretable Temporal Evaluation of Physical Consistency in Video Generative Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31429 - TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03629 - DelegateEval: Evaluating Platforms for Personal External Service Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07508 - EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26578 - Instantiating the Knowledge Plane Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07827 - Seeing Beyond the Next Step: World-Model-Guided Human-Like Navigation in Multi-Agent Scenes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07730 - Aligning Policy Encoders with a Shape Teacher Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08275 - Value-oriented policy distillation for interpretable wind farm power control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08245 - Worst-Case Discovery and Runtime Protection for RL-Based Network Controllers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04373 - A Generative Model of Contextual Integrity: Appropriate vs. Inappropriate Information Sharing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08284 - Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07640 - MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08327 - Trust Responsive Runtime Authorization for Agentic AI with Empirical Characterization of Policy Behavior and Parameter Sensitivity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06996 - Thalamus-Reasoning: A Multimodal Large Language Model for Multi-Sample Omics Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06728 - NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08369 - Signed but Not Safe: Requirement Integrity in Multi-Agent LLM Handoffs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07483 - Action-Conditioned VLM Monitoring for Autonomous Vehicle Semantic Anomalies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07540 - Evolver: Turning Agent Exploration into Evolving Capabilities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07595 - Who Should Know What? Empirical Information Design for Multi-Agent LLM Economies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07667 - When Bigger Becomes Brittle: Why Compression Hurts More as Language Models Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07891 - When Verification Is Not Agreement: Cross-Agent LLM-to-Dafny Formalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07073 - A minimal dynamical model of human-AI cognitive coevolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06928 - openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27969 - UniGADD: Universal Generator-Agnostic Deepfake Detector Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07647 - Segment What It Can Draw: Querying a Text-to-Image Generator with Its Own Images for Skin Lesion Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07061 - STAG-Net: Structure-Aware Attention over Landmark Groups for Lightweight Head Pose Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07828 - Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05163 - CAMP: Context-Aware Mapping and Placement for LLMs on 3D-IMC Arrays Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07707 - Are LLM Safety Judges Policy-Invariant? A Three-Principle Stress-Test Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06161 - EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06748 - BALD-SAM: Disagreement-based Active Prompting in Interactive Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10828 - MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07689 - Secure Formal Raising: Protecting the Development of AI through Executable Properties Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08042 - Towards Generalist Graph-Level Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07706 - FreePath: Neural Mean Free Path for Image Dehazing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07398 - SOCIA-$\nabla$: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.12006 - More Agents, More Reliable? System-Level Reliability of Multi-Agent LLMs under Operational-Profile Uncertainty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07140 - Resource-Efficient Reinforcement Learning Post-Training through Elastic Expert Parallelism Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06984 - AuroraWorld: Structured 4D World Modeling for Exo-to-Ego Video Generation in Robot Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00177 - KG-AST for Cheaper CI/CD: Budgeted Test Selection and AI Bug Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06950 - Oscillatory Phase Coding Emerges in Adaptive RNNs for Flexible Working Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06932 - Keeping Jerk in Check: Jointly Trained Perception-Gated Experts for Smooth Terrain Transitions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19633 - Who Can Evaluate AI Independently? A Framework for Analysing Evaluation Infrastructure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08134 - RIVER: Evidence-guided multi-agent retrieval for enzyme--reaction discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07757 - WeLM-Image: A Unified Image Generation Model towards Visual Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07392 - LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16675 - Neural Image Compression with Internal-External Prior Fusion and Alignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07644 - Beneath the Surface: What We Overlook When We Talk About Agent Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07624 - SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08483 - Adaptive Test-Time Memory Allocation for Long-Tailed Human-Object Interaction Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.18811 - From Maps to Metabolism: Historical Precedents and a Unified Critique of Computationalism Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06936 - SeVerus: Context-Aware, Gamified Benchmarking for Rust Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07194 - LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.19204 - Polynomial-Time Computation of Extensive-Form Proper Equilibria in Two-Player Zero-Sum Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07089 - Adaptive Experimentation Can Hide Model Error:Detection Limits and Falsification Budget Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07529 - ProCompNav: Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06223 - From Learner Behavior to Reusable Skills for Effective and Efficient Learner Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37157 - PharmAgents2: Towards Autonomous End-to-End Drug Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07653 - Autonomous Driving Research Requires a Community-Driven Data Paradigm Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.08825 - How Finite Brains Generalize Without Bound: Spatial Memory as a Universal Computer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07920 - GuidedWAM: Training-Free Energy Guidance for World Action Models in Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07912 - Event-Grounded Sparse Autoencoders for Vision-Language-Action Policies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17204 - RoboCurate: Harnessing Diversity with Action-Verified Synthetic Data for Robot Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18742 - Batch-Conditioned Semantic Anchors for Robust Transductive Adaptation of Vision--Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06993 - SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07222 - ReproBridge: Building Reproducibility into ML Research Artifacts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08452 - LeanContext: Disentangling Mathematical Resources from Local Formal Context in Lean Whole-Proof Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08277 - Adaptive Semantic Branching: Disagreement-Localized Cross-Trajectory Regeneration for Reasoning Candidate Expansion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07918 - Learning a patient world model for health system simulation in intensive care Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08392 - tok: a textual concrete syntax of BPMN and DMN for humans and AI agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07945 - FacEDiT: Talking Head Video Editing via Facial Motion Infilling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.14056 - Constraining the Commit Boundary: A DIO/ODI-Informed Authorization Guardrail for Agentic Entity Resolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37407 - Human-Centred, Risk-Constrained Evaluation of Financial Document Recognition: Evidence, Critical Errors, and Selective Automation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02775 - ReferClaw: Disambiguating User Intent for Egocentric Assistance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07683 - Signals, Evidence, and Context: User Scrutiny in Real-World LLM Conversations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08232 - Integrating Triaxial IMU Sensors and Ensemble Learning for Effective Parkinson Disease Severity Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28602 - A Cyber Range Evaluation of Inductive Autonomous Network Incident Response Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.16541 - Using Experience Twice: Dynamic Process Rubrics for Privileged Token-Level Credit Assignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06543 - Agentic Abstention: Do Agents Know When to Stop Instead of Act? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28733 - Pediatric ECG foundation model via adult-to-pediatric fine-tuning: downstream tasks and clinical evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07717 - PSGAgent: Enhancing MLLMs' Dynamic Visual Perception for Panoptic Scene Graph Generation via Agentic Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07408 - GraspBench: Execution-Aware Cross-Robot Evaluation of 6-DoF Grasp Generation in MuJoCo Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07651 - Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30344 - 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 - Eigenius: A Typed Knowledge-Graph DBMS with Epistemic Stratification and Institution-Mediated Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04457 - Concertina: Embodying Manipulation and Cognition in One Diffusion Vision-Language Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07513 - Energy-Aware Open-Vocabulary Detection Scheduling for Low-Power Robotic Autonomy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07663 - CST-Bench: Benchmarking Counterfactual Spatial Transition Reasoning with Causal Transition On-Policy Self-Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07541 - The Power of Meta Access in the Software of the Future --- Demonstrated on LLM Chat UIs and Chat AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08428 - Create Your Own Work Stack: Deploying Self-hosted AI and Tooling in a Tech Startup Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.08116 - The Gold Rush in AI4Math, II: What are signatures of AI-assisted Proofs? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08412 - FlashOffloading: Low-Latency KV Cache Offloading for Long-Context LLM Serving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07542 - Randomized Parallel Complexity of Weakly Convex Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07675 - PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08175 - FinMultiHopQA: A KG-Grounded Multi-Hop Financial QA Benchmark for Evidence-Driven Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.02906 - What Does the Effective Dimension of a Hybrid Quantum Neural Network Actually Measure? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.14070 - Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07066 - More: Mode-Optimized Reasoning with Self-Adaptive Effort for Self-Evolving Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33684 - A latent ODE approach to full-cycle biventricular cardiac motion modeling from cine MRI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26718 - Autonomous AI Agents Systematically Diverge From Human Preferences in Proof Formalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06995 - Cognitive Foundations for Reasoning and Their Manifestation in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16660 - Responsible GenAI Use During Active Armed Conflict: Evidence from Sudan's Emergency Response Rooms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07874 - Enhancing Local and Global Structure in Compressed AI Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08341 - Learning Noise Optimization for Reward Alignment in Few-Step Generative Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06255 - Formalizing inverse problems in the age of AI: possibilities, pitfalls, and an invitation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06962 - MOF-VERIFY: A Failure-Aware Agentic Harness for MOF Hypothesis Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03056 - TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22535 - FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08383 - Redacting Personal Data: A Speed and Accuracy Comparison of Regex, Presidio and Hybrid Designs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07633 - Network Effect Decomposition for Causal Effect Estimation under Network Interference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07879 - Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30621 - Towards Scalable Diagnostic-Driven Whole-Slide Image Retrieval for Pathology Archives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07935 - MUSS: A Multi-scale and Sequence-based Model for Single-cell Gene Regulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08086 - Benchmarks as Software: Terminal-Bench and the Case for Continuous Benchmarks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08417 - Adapting the Process of Adaptation: Darwinian, Lamarckian, and Agent-Directed Evolution in AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07048 - ValuSpec: Plug-and-Play Candidate Valuation before Target Verification for Tree-Based Speculative Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31338 - Leveraging ChatGPT's Multimodal Vision Capabilities to Rank Satellite Images by Poverty Level: Advancing Tools for Social Science Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2501.14546 - MOO: A Multi-view Oriented Observations Dataset for Viewpoint Analysis in Cattle Re-Identification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.04314 - KDASO: Knowledge-Data Dual-Driven Automated Skill Optimization for Liability Adjudication Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06972 - Analysis of LLM Vulnerability to GPU Soft Errors: An Instruction-Level Fault Injection Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.19912 - Local-Frame Rotary Attention for Antibody-Specific Epitope Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01092 - Robust Ranking of Port Impacts from Impending Tropical Cyclones: A Two-Stage Recommendation System Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.07296 - Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22599 - Diagnosing and Improving Probabilistic Reasoning in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38005 - FisherDistill: Diffusion Distribution Distillation via Closed-Form Fisher Critics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07604 - WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13977 - World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10630 - OpenNWM: A Generalist Navigation World Model with Latent Action Pretraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01844 - MIND: AI Co-Scientist for Material Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.13699 - Typed Knowledge over Constructive Institutions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07432 - A Trust Layer for Agent Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07274 - Can Linguistic Reasoning Vectors Enhance Multimodal Reasoning Ability? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31140 - Efficient Diffusion Policy Fine Tuning with Latent Noise Representation Bridging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07275 - Failure Prediction and Classification in Vision-Language-Action Models Via Calibrated Latent Probing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08425 - When LLM Routers Overpay: The Cost of Strong-Model Preference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03478 - The Popular Get More Popular: Auditing Brand Bias in Generative Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07614 - SD-LoRA: Training-Time Structural Distillation into LoRA for Few-Shot Vision-Language Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07063 - Hypnos: Learning Generalisable Representations of Sleep Physiology via Next-Token Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09605 - Graph learning-assisted logic-based Benders decomposition for distributionally robust in-station train rescheduling under disruptions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.07520 - NutriVisRAG: Multimodal Exemplar Grounding for Nutrient Estimation with Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08054 - Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00247 - Grounding in the Dark: Text-Only Training for Zero-Shot Video Temporal Localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06149