TILens Daily Edition 2026-11-05 Filters: topic=ai-research, github=hidden Stats: 744 articles, 8 sources, 737 research papers Top topics: AI, AI Research, Information Retrieval ## News - OpenAI’s New Data Center Pitch Starts With Letting Officials Talk Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openai-data-center-reset-no-ndas-public-officials/ - True Positive Weekly #184 Source: true-positive-weekly Topic: AI (+AI Research) URL: https://aiweekly.substack.com/p/true-positive-weekly-184 - OpenAI Found 948 Ways to Get Root Access in Linux. That’s Progress. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/openai-linux-security-bugs-ai-windows-patches/ - 😺 OpenAI launched Images 2.6 with GIFs Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/openai-launched-images-2-6-with-gifs/ - Claude Helped Scientists Investigate a 40-Year-Old Cell Mystery. Here's What It Found Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/claude-anthropic-40-year-old-cell-mystery/ - I Tested ChatGPT’s New GIF Feature. Here's What Happened Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/chatgpt-gif-creation-test/ - Everything That Happened in AI Today (Thursday, November 5, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-thursday-november-5-2026/ ## Research - Detecting signs of hypertension using wearable sensors Source: google-research-blog Topic: AI Labs (+AI, AI Research) URL: https://research.google/blog/detecting-signs-of-hypertension-using-wearable-sensors/ - How to Report for 100+ Clients With One Semantic Model Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-report-for-100-clients-with-one-semantic-model/ - How We Built NASA's Zero-Shot Detector for Gas Leaks from Space Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-we-built-nasas-zero-shot-detector-for-gas-leaks-from-space/ - How GEO, WebMCP, and Bot Paywalls Are Building the AI-Native Internet Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-geo-webmcp-and-bot-paywalls-are-building-the-ai-native-internet/ - Why a Tiny GPT Can Know Two Facts and Still Not Connect Them Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/why-a-tiny-gpt-can-know-two-facts-and-still-not-connect-them/ - Uncertainty-Aware Resource Orchestration for Agentic AI Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05392 - Pathwise-Budgeted LLM Routing: Online Allocation with K-Bit Tail-Cost Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05835 - FedCSGA: Evolutionary Client Selection with Joint Statistical and System Heterogeneity in Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04667 - Do Tabular Foundation Models Agree with Themselves? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06004 - RIDGE: State-Conditioned Reward Blending for Behavioral Coverage in Deep RL Game Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05601 - Online learning of subgrid-scale models for quasi-geostrophic turbulence in planetary interiors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.14581 - Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26516 - Otter Weather: Skillful and Computationally Efficient Medium-Range Weather Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26421 - A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35658 - Aligning Training and Rollout Policies for End-to-End FP4 RL on Mixture-of-Experts LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04376 - Do Language Models Know Which Constraints Belong Together? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05726 - EvoOPD: Evolving Privileged Information Strategies for Black-Box On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06542 - Support Vector Machines Directly Minimise KL Divergence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05557 - MMAP: Multimodal Missing-Aware Pretraining for Longitudinal Alzheimer's Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.26617 - More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26647 - Message-passing graph persistence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06801 - Schr\"odinger--F\"ollmer Actor--Critic: Diffusion Policy Improvement with Finite-Sample Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33239 - From Reconstruction to Imputation: Test-Time Optimization for Missing Time-Series Channels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06612 - Attention to Mamba: A Recipe for Cross-Architecture Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14191 - PatchKV: Weight-Space Compensation of KV Cache Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39329 - Quantum-Inspired Tensor Network Autoencoders for Anomaly Detection: A MERA-Based Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06541 - Sparse Federated Echo State Networks for Time-Series Classification via Smooth-L1 Regularization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21742 - Classical training of conditional instantaneous quantum polynomial-time Born machines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05483 - Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06905 - EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11722 - Teaching Diffusion to Speculate Left-to-Right Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11552 - ConDR: Conservative Reachability through Neural Hamilton-Jacobi Subsolutions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06802 - A Controlled Experimental Evaluation of Configuration and Cache Architecture in LLM Serving Engines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05991 - Reactive Optimizers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33826 - Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06498 - Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06244 - Mitigating Memorization Where It Happens Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08901 - Deep Sets and event-level maximum-likelihood estimation for fast pile-up jet rejection at the ATLAS High Level Trigger Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10819 - Visual Token Routing: Learning to keep tokens that matter Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06854 - Retrieval Supersedes Scale: Efficient Log Level Prediction via Multiplex Socio-Technical Context Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05901 - Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2107.12636 - EEGDash Corpus: A Training-Ready Public Corpus for EEG Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06356 - Symmetry Breaking at the Edge of Stability via Central Flow Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06718 - FlowReconBench: Accuracy, calibration and cost of learned and classical flow reconstruction from sparse sensors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06912 - When Does Risk-Controlled Throughput Forecasting Actually Control Risk? A Reproduction Study on LEO Satellite Link Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06307 - Fingerprinting the Dispatchers behind Distributed Model Extraction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06661 - ENFORCE: Nonlinear Constrained Learning with Adaptive-depth Neural Projection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.06774 - Agentic Literature Extraction Augments Targeted Protein Degradation Databases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11221 - A Bag of Tricks for Defending Deep Learning-based Face Recognition Pipelines against Backdoor Attacks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06412 - MvBody: Multi-View-Based Hybrid Transformer Using Optical 3D Body Scan for Explainable Cesarean Section Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.03212 - TSFM Meets LLM: Context as Covariates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05515 - OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30356 - Quantifying Trait-State Hierarchy in EEG Foundation Model and Signal Processing Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05652 - Adaptive Multi Mode: Budget-Aware Routing of Optimizers By Online Landscape Probes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06879 - Analysis of Local Open-Weight LLM Agents on Vulnerability-Reproduction Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06257 - Text-Only Domain Adaptation for Low-Resource Medical ASR: Shallow Fusion and Density Ratio Rescoring for Hausa Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05744 - TTHE: Test-Time Harness Evolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.08124 - Product Monte Carlo: Expectation Under a Product of Densities Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12702 - Selective Prediction Intervals: Jointly Learning to Predict, Bound, and Abstain Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06158 - Backward-Consistent Diffusion Sampling for Sparsely Observed PDE Inverse Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04624 - Navigating Disagreement Among Criteria for Evaluating Explanation Faithfulness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06846 - Context--Answer Metamodels: Forecasting LLM Activations Before the First Answer Token Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06837 - Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06641 - Loop Before You Leap: What Recurrent Depth Can and Cannot Buy in Data-Limited Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06206 - Batch-Invariant Spectral Intelligence for Robust and Explainable Insect Authentication Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.26757 - Give the Drafter a Second Chance to Guess: Parallel Reconsideration for Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05724 - HLA-Net: A Physics-Guided Skeleton-Based Framework for Automatic Gravitational Arc Detection in Astronomical Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05438 - Learning POMDP World Models from Observations with Language-Model Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13740 - OdorSpaces: Visual-Olfactory Embodied Navigation in 3D Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05738 - BAM: Bivariate Additive Models for Interpretable Tabular Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05940 - Readable Is Not Steerable: Pre-Registered Tests of Physical Structure in Learned Fluid Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05577 - Systolic Linear Attention: Co-Designing Tile-Grouped Gated Delta Attention for TPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06828 - Federated Concept-Based Models: Interpretable models with distributed supervision Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04093 - 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 - Dynamic Quadtree Tokenization and Transformer for Adaptive Mesh PDE Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04044 - FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05546 - FedFiOT: Fisher-Weighted Optimal Transport for Model Merging in One-Shot and Few-Round Federated Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06783 - How Far Can You Steer? Behavior-Capability Frontiers in Contrastive Activation Addition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06001 - Learning Hierarchical Patch Splitting Policies for Faster Vision Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05742 - PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.37381 - From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10485 - Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07108 - A Framework for Context Enrichment and Selective Robustness in LLM Social Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06914 - Large-scale empirical tuning and comparison of default optimizers for variational inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07841 - Hyperparameter Transfer in Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05017 - Where It Breaks: Diagnosing Perception, Memory, and Decision Failures of a Vision-Language Agent in Pac-Man Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06704 - Orthogonal Model Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.05943 - Generalized Hyperrectangular Prediction Sets in Multivariate Conformal Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05543 - A Unified Framework for Training-Dataset Aggregation and Exact Machine Unlearning via Gibbs Probability Measures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05544 - Partially Interpretable Decision Trees Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06428 - Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.09275 - GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05593 - Revisiting data-driven dynamic security assessment with a tabular foundation model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16031 - When Is One Query per Template Enough? Adapting Learned Cost Models to New Hardware Source: arxiv-cs-lg Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2611.05892 - Continuous Adversarial MeanFlow Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.19540 - Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06438 - Attraction-Ranking Mismatch in Out-of-Distribution Detection: Theory and Evidence from Hamiltonian Feature Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06021 - Separating Common and Unique Directions for Model Merging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04108 - Consistent Submodular Maximization with Full Foresight Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06223 - AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.02131 - Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.01470 - GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05369 - Optimal and Efficient Contextual Combinatorial Semi-bandits with General Function Approximation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.13686 - CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08686 - Structural Rationale Distillation via Reasoning Space Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07139 - Domain-Adaptive Small Language Models for Structured Tax Code Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.10880 - Data-Driven and Cycle-Agnostic Covariate Selection for Nonparametric Causal Effect Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06385 - FutureLift: Lifting Trajectory Proposals into Bidirectional Future Graphs for Motion Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22215 - CounterFactual Retrieval for Evidence-Aware Individual Animal Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06864 - Nowcasting Future Performance for Population Pruning in Survival-of-the-Fittest Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06512 - Flexible Intensities Matter: A Comprehensive Re-evaluation of Hawkes Processes and Neural Temporal Point Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06348 - SO(3)-Equivariant Learning on CAD Boundary Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05449 - Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21257 - Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.01558 - Exploring the Privacy--Size Tradeoff for Differentially Private Self-Attentive Variational Autoencoders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05582 - AI-Assisted Classification under Correlation Neglect and Trust Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05870 - Self-Supervised Learning of Universal Latent Spaces for Operator Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05735 - Neuromorphic Decoding and Dynamical Image Reconstruction from Populations of Spiking Retinal Ganglion Cells Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17154 - Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06265 - Neural networks and games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05706 - TRACK: Multiple Instance Learning for Anti-Money Laundering in Transaction Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06035 - Stabilizing On-Policy Targeted Guidance in Agentic Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05266 - Last-Iterate Stationarity of Muon with Finitely Many Newton-Schulz Iterations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34158 - Balancing hierarchical representation and quantization: A performance trade-off in text embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06859 - VenusGenome: Genome-Aware Masked Autoencoding for Microbial Genome Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05405 - GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20757 - MemReward: Graph-Based Experience Memory for LLM Reward Prediction with Limited Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19310 - Population-Aligned Persona Generation for LLM-based Social Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.10127 - Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11746 - Data-Efficient Scaling-Law Discovery for Recommendation Systems via Coupled Hyperparameter Scaling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05643 - LINC: Decoupling Local Consequence Scoring from Hidden Matching in Constructive Neural Routing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06332 - Template Gap Reconstruction for Shell Output Simulation with Small Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06731 - Alignment Myopia in Generative AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06830 - 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 - Factual recall in linear associative memories: sharp asymptotics and mechanistic insights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10795 - A low-rank decoder bottleneck bounds reliability in foundation-model perturbation prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05849 - Kriging and Neural Network models for pressure losses across perforated plates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.29628 - From Handcrafted to Generative: RLVR-Optimized Icon Generation for Alexa+ Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06123 - Learning to Tune with Biased Gradients: Iterative Feedback Tuning of Model-Free Control on Throttle Valves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06338 - Softmax Attention with Any Temperature in Fixed Dimension: Matching the Best Known Maximum-Inner-Product Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06055 - Generative Modeling for Cascading Extremes via Autoregressive Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05728 - How many sorted projections determine n points in k dimensions? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06470 - Understanding Generalization Requires Universal Induction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34458 - Risk-Sensitive Non-Parametric and Kernel Bandits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06489 - All Paths All at Once: A Quantum Monte Carlo and Neural Committor Approach to Reaction Pathway Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03699 - In-Context Black-Box Optimization with Unreliable Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06187 - Evolutionary System Prompt Learning for Reinforcement Learning in LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.14697 - A Rigorous, Tractable Measure of Model Complexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21167 - Tight Lower Bounds under Matched High-Order H\"older Smoothness and Uniform Convexity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05527 - Dynamic Strategy Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2307.04754 - Discovering Phase Space Structure in Learned Hamiltonian Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.23003 - Matched but Not Better: An Equivalence-Tested Benchmark of Quantum Machine Learning on Six Clinical Datasets and the QML-Health-READY Reporting Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05442 - What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06483 - Don't Replace, Complement: A Detector-Agnostic Subspace Signal for Near-OOD Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06688 - FLAG: Flow Policy MaxEnt-RL by Latent Augmented Guidance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30749 - Learning to Incentivize Perfect-Knowledge Agents with Unobserved Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2304.07407 - Medial Axis Aware Learning of Signed Distance Functions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.16512 - Distributed Sketching on Data Partitions for OLS Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07888 - BIOTRAM: Biochemistry-informed Transformer for Relative Abundance via Metabarcoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05418 - Enabling AWS Cloud FPGA Development Using High-Level Vitis HLS Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06829 - RACE: Calibrated Cumulative Scoring for Rollout-Free Robot Policy Checkpoint Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05838 - Practical Estimation of the Bayes Optimal Fairness-Accuracy Tradeoff with Soft Labels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06027 - Diversity-Aware Experience Replay via Statistical Leverage Scores Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05929 - Mass Producing Training Data with Surprising Side Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06324 - Deep-Learning Solvers and Surrogates for Infinity and p-Laplace Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30809 - Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06711 - Revisiting Critic Estimation in Soft Actor-Critic Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05666 - Recasting Visual Language Models as EEG Foundation Models for Clinical Neurodiagnostics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05538 - A Lightweight Multi-View Approach to Short-Term Load Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09220 - GFlowQEC: Generative Flow Networks that Learn to Sample Quantum LDPC Codes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06819 - Unsupervised Neural Operators for Rotating Relativistic Stars: High-Fidelity Equation of State Inference and Pulsar Spin Evolution at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05790 - Decomposing one-class support vector machine into an ensemble of one-data support vector machines Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16002 - Chiron: Cache Management Empowered by LLM Intelligence for AI Workloads Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06179 - Quantifying Error Propagation and Model Collapse in Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16601 - Verifier-Guided Self-Consistency: Test-Time Reasoning with Imperfect Generators and Verifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06606 - Sample-Grained Approximate Unlearning with Provable Per-Sample Bounds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04501 - ElecLoad: Adaptive Electricity Load Forecasting Guided by Multiple Events Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06508 - Bridging the Modality Bottleneck in Pathology MIL through Molecularly Guided Feature Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16392 - Finite-width shift of the edge of chaos in deep neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06582 - FaCoDiff: Factor-Correlated Diffusion for Multivariate Probabilistic Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06166 - Learning vs. Optimizing Players in Budgeted Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05580 - Transforming Integer Grids to Spatial Intuition: Perception, Not Planning, Governs ARC-AGI-3 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06793 - When Are Two SAE Latents the Same Feature? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05655 - Efficient Robust Learning at the Information-Theoretic Limit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17655 - 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 - LongCounsel-8: A Benchmark Suite for Longitudinal Depression Tracking from Multi-Session Counseling Dialogues Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.03507 - Model Merging Does Not Require Uniform LoRA Ranks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06486 - Optimizing Recourse Under Predictive Multiplicity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05774 - Ordinal Credit Assignment: Multi-Step Reinforcement Learning from Comparisons Alone Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06375 - MIGONet: a multiple-input graph neural operator with solver-free discrete manufactured-solution training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05876 - UpSafe$^\circ$C: Upcycling for Controllable Safety in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.02194 - C-GRPO: Conformal Group Relative Policy Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05591 - Conformal Prediction for Distribution-to-Distribution Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06320 - RAGAM-AI: A Hybrid Reinforcement Learning based Agentic approach powered by Generative AI for Edge Resource Management Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06554 - A Definition of Catastrophic Performance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06219 - KolTa: A Physics-Informed Active Learning Framework for Formulation Discovery with Limited Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06394 - PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03068 - Probabilistic Meshless Methods on Manifolds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39855 - Learning When to Think Aloud in Latent Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06108 - Provably Safe, Yet Scalable Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14536 - Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21139 - SurgTransfer: Multi-Step Latent Action Modeling for Action Transfer in Surgical World Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05443 - AssameseLM-E2B: An Open-Weight Assamese Language Model for Efficient Consumer-Grade Deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06170 - Perceptive Humanoid Motion from Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06908 - Robust Successor Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.31016 - Interpretable Cutting Plane Selection for Mixed-Integer Linear Programming Using Genetic Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29311 - Understanding Reasoning from Pretraining to Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16097 - What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.32991 - RESHPart: Feedback-Reshaped Spectral Embedding for Hypergraph Partitioning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05729 - Hindsight Relabeling is All You Need for Reach-Avoid Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.19337 - A trust layer for fast pedestal-stability surrogates: calibrated error bars, out-of-distribution alarms and few-shot recalibration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06597 - ConceptARC at Scale: Studying Conceptual Understanding in Reasoning Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06732 - Pretraining Data Scale Reverses the Muon-AdamW Fine-Tuning Gap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03633 - Robust Policy Optimization via Adversarial Importance Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13044 - SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03201 - High-Dimensional Robust Mean Estimation from Doubly Corrupted and Heterogeneous Batches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.20698 - Testing concept-level audits of melanoma classifiers with diffusion counterfactuals and matched positive controls Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02119 - Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21849 - The Complexity of ReLU Network Synthesis from a Parameter Multiset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04074 - Tactus: Tactile & Pose Sensing Glove for Natural Dexterity Data Collection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39076 - Diffuse AI Control on Fuzzy Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08892 - CoRTeC: A Differentially Private Release for Synthetic Tabular Data, Decodable by Any Generator Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06342 - Within-Family EfficientNet Scaling under Fixed-Resolution Transfer Learning for Spectral-Domain Optical Coherence Tomography Retinal Disease Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06452 - Autonomy and Coordination in Intelligent Manufacturing: A Recursive Autonomous Agent Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05828 - GNNs Meet Sequence Models Along the Shortest-Path: an Expressive Method for Link Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.07138 - On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05609 - KL for a KL: On-Policy Distillation with Control Variate Baseline Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07865 - DTA-GT: Direction- and Topology-Aware Graph Transformer for Neural Network Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16822 - Machine-learned particle flow as a foundation model for collider physics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.14373 - PRISM-AMC: Replay-Free Continual Learning for Automatic Modulation Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06066 - Where Prefill Expert Reduction Hurts MoE Models: A Few Prompt Tokens Carry Most of the Short-Answer F1 Loss Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22454 - Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.11581 - Prediction-Intervention Games and Invariant Sets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16828 - Golden Layers and Where to Find Them: Improved Knowledge Editing for Large Language Models Via Layer Gradient Analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.20207 - NaijaFacts: A Framework for Disentangling Language from Knowledge in Facts about Nigeria Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06504 - Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.06199 - Warp: Structured Output-Space Adaptation for Frozen Robot Policies Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31043 - Decoupling Knowledge and Privacy: Post-Task Self-Distillation Replay for LLM Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.29711 - TestBED: An Open-Source Toolkit for Bayesian Experimental Design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06633 - Short-Term Forecasting of Heterogeneous Wind Power Fleets: Global Temporal Fusion Transformer Leveraging Static Covariates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06130 - LACS: Distribution-Sensitive Label-Agnostic Confidence Selection for Dynamic Data Pruning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05616 - Wave Physics as Representation: Tensor-Structured Neural Reconstruction for Ocean Acoustic Fields Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01680 - NodeSyn: Socially Aligned Synthetic Data for AI Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14381 - Catastrophic Overfitting is Weight Drift the Training Loss Cannot See Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06082 - Estimating Implicit Regularization in Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05436 - Separation Is a Riesz Energy: How Many Environments Does ICA Need? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06228 - NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02102 - Bilevel Learning via Strategically Inexact Stochastic Gradient Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.06774 - Driving Video Retrieval for Complex Queries with Structured Grounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09109 - Sedentary Behavior Classification for Wearable Sensors with a CNN-BiLSTM Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02946 - Act-HiMotif: Hierarchical Daily Activity Schedule Generation via Learned Activity-Structure Motifs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06038 - Multimodal Fusion Methods for Whole-Slide Images and Clinical Data in Inflammatory Bowel Disease Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05579 - The minimal width of universal $p$-adic ReLU neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00064 - Constraint-Preserving Flow Matching for Spectral Graph Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05436 - When the Agent Learns Too: Learning to Incentivize with Unobserved Rewards Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2308.06717 - Shallow Encoding Emits Deep Memories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06084 - WayPOP: A Panoramic Open-Set Panoptic Tracking Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05801 - Does Your Trial Simulator Know What the Drug Does? An Intervention-Blind Test of Interventional Validity on 7,207 Registered Trials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05907 - Dimension-Free Private Mean Estimation is Impossible Without the Covariance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06615 - A latent control model for realistic rodent motion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.27279 - PEARL: Prediction Error-Adaptive Regularized Learning for Selective Forgetting under Partial Preference Drift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05842 - From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy Gradient Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02313 - Multi-Agent Coordination via Support-Preserving Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10087 - OpInf-LLM: Parametric PDE Solving with LLMs via Operator Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01493 - GIST: Gibbs-Targeted Hierarchical Data Selection for Offline RLVR Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06395 - Detecting Silent Action-Interface Mismatch with Calibrated Relational World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06653 - 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 - ESS-Flow: Training-free guidance as Bayesian inference in source space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.05849 - Relevance Propagation as Entropic Optimal Transport on Filippov Neural Networks: Sinkhorn Propagation and Region Relevance in Image Classifiers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05594 - FrameScout: Scouting Query-Relevant Frames for Long Video Understanding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23975 - Lattice Deduction Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.08605 - The Confidence Score: a New Measure on Kernels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05528 - Consistent Geometric Deep Learning via Hilbert Bundles and Cellular Sheaves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06395 - Entity-Aware Evaluation of OCR Systems for Historical Document Transcription Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33004 - Scalable Source Selection for Machine Learning Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.22186 - A Comparative Study of Importance Attribution to Columns in Deep Learning over Relational Databases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05986 - From Grey-Box to Green-Box: When can Physics-Informed Machine Learning Reduce Carbon Footprints in Structural Health Monitoring? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.33387 - Learning From Static Context in Federated Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06064 - PARGAR: Pilot-Aware Graph Attention for Sparse-Pilot Neural OFDM Receivers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06432 - A hybrid quantum-classical neural network for learning to route Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00489 - Ranking Agreement Does Not Reveal Paragraph-Edit Agreement in Two Released Paper Acceptance Predictors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06789 - PAC Learning with Multiple Correct Answers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05133 - Hardwired Distributed Processing Units for Inference: Neural Decisions at the Sensor that Free the Host Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06436 - TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23496 - 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 - A Granular Framework for Construction Material Price Forecasting: Econometric and Machine-Learning Approaches Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.09360 - Adaptive Domain Decomposition for Finite Basis Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05659 - DP-IVON-Gradsq: Differentially Private Squared-Gradient Improved Variational Online Newton Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23649 - Graph Foundation Models Can Become Effective Multivariate Time Series Anomaly Detectors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06441 - Network Intrusion Forensic Detection System with Explainable Artificial Intelligence and Digital Chain of Custody Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06173 - Bridging the Data Gap: Source-Informed Task-Space Transport for Few-Shot Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31323 - Objective-Conditioned Active Preference Learning for Multi-Objective Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05506 - Causal Inference for Sequential Settings under Interference and Latent Confounding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14940 - Manifold-Matching Autoencoders: Embedding Data into Chosen Geometric Structures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16568 - GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12827 - Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11833 - Consistency Learning and Distillation for One-Step MIMO-OFDM Channel Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06271 - Conservative neural posterior estimation via distributionally robust training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28516 - Achieving adaptivity and optimality for multi-armed bandits using Exponential-Kullback Leibler Maillard Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.14379 - Uniform Race: Parameter-Free Approximate Rejection Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34639 - Learning Penalty for Changepoint Detection via Automatic Feature Extraction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.07413 - Pairing Expert Critique with LLM-Driven Refinement: An Iterative Approach for Curating Quality AI Evaluation Datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05749 - Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.08462 - Optimality-Informed Neural Networks for Solving Parametric Optimization Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20270 - Impact of Negative Weights on Performance in Reservoir Computing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06051 - FlyHash for LLM Agent Memory: An Empirical Validation and a New Application Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05791 - Decouple to Reuse: Fine-Grained Knowledge Augmentation for Time Series Foundation Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05993 - Restrained Diffusion Bridges: Targeted Denoiser Training and Refinement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02170 - Agents, Think Only When it Helps Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05709 - SEAR: Sample Efficient Action Chunking Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01891 - When Reviews Are Scarce: Structure-Aware Review Imputation for Recommendation in Realistic Sparse Review Settings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.01128 - Asymmetric On-Policy Distillation Learns In-Context Exploration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30105 - 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 - Clips2Story: Training-Free Video Storyboarding and Editing Using Multimodal Retrieval-Embedded Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05992 - The Behavioral Rate of Fine-Tuning: Compression as a Measure of Useful Information Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06598 - Stabilizing Off-policy LLM Optimization with Prefix Importance Ratio Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22718 - Item Representations Matter: Bridging Hard Semantic IDs and Soft Prototype Mixtures for Generative Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05799 - ALTO: African and Levantine Tech-Facilitated Gender-Based Violence Corpus Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06706 - Information-Matched Auditing of Conversational Emotion-Shift Forecasting: A Leakage-Safe Evaluation Protocol Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05895 - Thermodynamics-Informed Learning Captures Hierarchical Hydrogen-Bond Networks in Deep Eutectic Solvents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06590 - SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06147 - OTAP: Structure-Aware Optimal Transport for Evaluating Planning and Execution in Agent Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.17082 - Power Grid Control with Graph-Based Distributed Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.02861 - Thought-deciphering via hierarchical EEG-to-text alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03623 - Cite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable Evidence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07739 - Interactive World Simulation with Cosmos for Physical AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06627 - Spatio-Temporal Multi-Order Interaction for Video Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05633 - AutoDex: An Automated Real-World System for Dexterous Grasping Data Collection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.23689 - On Convergence of Gradient Temporal-Difference Learning with Regularized Corrections and Eligibility Traces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05869 - Sensor Response-Time Reduction using Long-Short Term Memory Network Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2404.17144 - SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05800 - Dexterous Robotic Hands in the Foundation-Model Era: A Full-Stack Survey of Hardware, Data, Cross-Embodiment Transfer, Learning, and Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06724 - Near-Minimax Sample Complexity for Multi-Objective Reinforcement Learning under Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05562 - Zuse: A Decision Model for European Languages Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06238 - fev-bench: A Realistic Benchmark for Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.26468 - Self-Directed Apple Tasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06677 - Behavior Graphs: Unsupervised Graph Structures for Interpreting Robot Deployment Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00405 - Timing is Everything: Inferring Temporal Membership in Continually Updated Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05781 - Zero-Shot Coordination among LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06409 - CARM: Conformal Adaptive Risk Masking for Reliable Scientific Super-Resolution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06151 - Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.06648 - Benchmarking Sensor-Fault Robustness in Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10822 - Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21325 - Many Pixels, One Composition: Self-Supervised Spectra for Specimen-Level Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06096 - Same Layout, Different Count: What Number Words Do Past Ten in Text-to-Image Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06840 - Discovering Semantic Structures in Psychological Scales: A Response-Free Front-End to Efficient Simplification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12575 - Neural networks become centroid classifiers when trained on heavily corrupted inputs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11319 - D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06425 - 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 - PINR-ESI: Physics-Informed Self-Supervised Implicit Neural Representation Framework for EEG Extended-Source Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06700 - IDSISA: Influence-Distilled Sharded Training for Efficient Machine Unlearning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06519 - Do Search-Augmented Recommenders Use the Latest Search Episode? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06044 - Ctrl-F: Force as an Interface for Humanoid Loco-Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05507 - Routes of Reasoning: Reading and Reshaping Test-Time Compute in MoE Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05919 - Transport along Local Annealing Paths: Wasserstein Geometry and Multimodal Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05605 - Thermally Conditioned Time-Series Forecasting of Grain Growth in Polycrystalline Materials Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06843 - Improved approximation algorithms for capacitated cluster editing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05916 - From hydrological laws to catchment models: A process-based model matches deep-learning accuracy on three continents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06382 - GPUMAP: GPU-Accelerated Progressive Uniform Manifold Approximation and Projection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06191 - Alleviating Limited Effectiveness and Multi-Class Collapse in Deep Graph-level Clustering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06052 - Continual Classification Beyond the Kernel Regime: Harnessing the Sparsity Bias of L2 Regularization in Diagonal Linear Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06759 - Toward an Optimal Configuration for Tree Species Classification from Bark Images: A Leakage-Safe Ablation Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05680 - Adapting Sleep Foundation Models for Dense Sleep Spindle Localization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06546 - EvolveNet: Collaborative Harness Evolution for Agent Self-Improvement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04968 - Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06179 - Revisiting the 16x Pretraining Compute Gap between Diffusion and Autoregressive Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17590 - Anchor PCA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06233 - SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06682 - PREBA: Surgical Duration Prediction via PCA-Weighted Retrieval-Augmented LLMs and Bayesian Averaging Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.13275 - TensorSSM: Memorizing Spatial Position in Dynamic State Space for Tensor Core Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40871 - Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05355 - Do unlearning algorithms learn the right features? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06681 - Noise-regularized training of quantum circuit Born machines under a finite shot budget Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06630 - From Heuristic Selection to Automated Algorithm Design: LLMs Benefit from Strong Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02792 - The Split Protocol Decides the Result: Re-Evaluating Encrypted Traffic Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06290 - Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13133 - AvalancheBench: Evaluating Enterprise Agent-Driven Semantic Query Processing Through Latent World Recovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24183 - Trace2World: Reconstructing App Worlds from Real Interaction Traces for Scalable GUI Agent Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30792 - Regret Bounds for Market Making with Persistent Orders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06159 - Give Up to Get More: Priors, Not Policies, Govern Test-Time Compute Allocation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06372 - Evolutionary Design of Interpretable Spatial Descriptors for Structure-Property Relationship Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06811 - Role-based Effectiveness of an Epistemic Uncertainty Estimate in Training Models for Semantic Segmentation of 3D LiDAR Point Clouds Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05569 - CoReFlow: Consistency-Relaxed Flow Maps for Probabilistic Traffic Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05715 - Challenge-Aware Knowledge Recruitment with Meta-Agent Supervision for Medical Multi-Agent Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05393 - Goal-Oriented Sequential Bayesian Experimental Design for Causal Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.07359 - Learning Noise Optimization for Reward Alignment in Few-Step Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06255 - From Augmentation to Synthetic Evidence: Evaluating Generated Chest Radiographs at Dataset Intake Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.29152 - FedIA: Instance-Aware Cross-Modal Representations for Federated Prompt Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05994 - An Interaction-Aware Decision Framework for FDIC-Assisted Distressed Bank Acquisitions: Empirical Evidence from the FDIC Failed-Bank Panel and the SVB-First Citizens Case Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06514 - Unbiased Open World Regularization for Fair Self-Supervised Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22149 - Turns Matter: Advancing Streaming Video RL via Turn-Level Credit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06728 - On the Design of Hyper-Connections: Simplification, Stability, and Scalability Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05984 - Beyond Accuracy: Information-Theoretic Decoder Evaluation Under Latent Intent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05658 - Learning Implicit Solves for Dynamic Simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05439 - EmoTrack: Clinical-Semantic Modeling for Text-Based Depression Severity Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22286 - Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03899 - S$^{2}$-PINN: Stochastic Separable Physics-Informed Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03303 - Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16952 - Hyper-Dimensional Fingerprints as Molecular Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27810 - Neural Actor--Critic Learning with Minimax Critics and Reflected Langevin Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03352 - Alternatives to Shallow Autoencoders for Collaborative Filtering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06610 - Who Pays for the Knowledge Models Copy? Model Collapse as Rogers' Paradox Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06022 - Coupled Scene Graph Anticipation: When With-Constraint Recall Hides Structural Inconsistency Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06738 - Deep Meets Classical: A CPU-Efficient Decision-Fusion Model for Automatic Modulation Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05937 - Neural Stochastic Forecasting for Lateral Molecular Diffusion Simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06157 - Offline Learning of Reserve Prices from Censored Bids Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06067 - Communication-Efficient Clustered Federated Learning in Non-IID Wireless Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.38970 - Weaver: Weaving Preference Evidence through Incremental Reasoning for Personalized Retrieval-Augmented Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05900 - From Waste to Discovery: Recycling High-Scored Unexposed Candidates in Taobao Feed Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05997 - Combining Relevant Expert Knowledge Using Mixtures of Feedback Fuzzy Cognitive Maps Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05664 - One Basket, Many Experts: Decorrelated Re-ranking for Financial Asset Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05952 - Factorized MLLM Embeddings for Composed Image Retrieval Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05193 - Deliberate Latent Reasoning for Sequential Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.06521 - Optimal Re-Ranking Depth Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05908 - Algorithmic Authority and the Clinical Standard of Care Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2606.00044 - 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 - When Is Complex Chunking Worth It? A Multi-Objective Evaluation of Chunking Methods at Scale Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.16586 - Toward a Compositional Knowledge Architecture for a Shared Organizational Cortex Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05753 - TAGR: Temporally Adaptive Generative Recommendation for Industrial Live-Streaming Advertising Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.24034 - 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 - SciToT: Multimodal Tip-of-the-Tongue Retrieval for Scientific Papers Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05829 - Safety, or Just Capability? A Validity Audit of Agent-Safety Benchmarks Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.28685 - LIBRA: Programmatic Induction of Executable Tool Libraries Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05445 - PMRecBench: A Benchmark for Personalization in Recommendation Agents under Multimodal Queries Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.06349 - Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.21095 - Space efficient implementation of hypergraph dualization in the D-basis algorithm Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2512.06988 - IMFuse: Instance-Aware Multi-Layer Fusion for LLM-Enhanced Sequential Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2607.27002 - RAGCompass: Generalizable Retriever Routing via Reranking Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05596 - Turbocharging PiPNN for Proximity and $k$-NN Graph Building Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.05690 - ArcRAG: Agentic Compositional Retrieval over Knowledge Graphs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.06481 - The Scope Grammar of Natural-Language Rules: Counting and Enumerating Readings modulo Logical Equivalence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01825 - Persona Perspectives: Adopting Viewpoints Reorganizes Representations in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06848 - Observatorio Lazaro: A self-populating database of anglicism usage in the Spanish press Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00713 - Prospective Memory for Proactive LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05731 - Before You Continue: Evaluating Time-Sensitive Safety Awareness in Conversational Assistants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06839 - MD-ProTector: Positioning Multiple Data-Driven Prototypes for LLM-Generated Text Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10459 - Dialect Matters: A Dialect-Aware Baseline for Igala-English Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06517 - SLICEChat: Progressive In-Encoder Token Pruning for Whole-Slide Pathology Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24894 - Phonological Knowledge of Chinese Characters in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05803 - From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07779 - AI-Driven SaaS Platform Integration: AI Express for Unified Generative AI Services with Pay-As-You-Go Credit Systems and Scalable Microservice Architecture Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05389 - EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18489 - When to Ask, When to Answer: Strategic Clarification for Ambiguous Reference Resolution in Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05517 - Corralling AI Risks with Grassroots Contracts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06374 - Editing Large Language Models with Geometry-Aware Regularization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06185 - LibriSpeech-Real-QA: A Benchmark for Streaming Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06496 - Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06043 - ProcessPrefBench: Evaluating Cross-Task Transfer of Individual Process Preferences from Naturalistic Human-AI Interaction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06065 - Robots in the City: Persona-Based Perceptions of Urban Robots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05954 - CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05862 - When Do Summaries Become Instructions? Unsupported Policy in LLM Agents' Self-Written Handoff Summaries Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06545 - CCDWIKI: Decoupling Case Formulation from Response Generation in Longitudinal CBT Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05383 - Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature Proxies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39640 - Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11817 - LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06381 - Token Time Continuous Diffusion for Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14106 - Matching the Training-Time Weight Rule in Inference-Time Expert Deactivation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05804 - TherapyGym: Evaluating and Aligning Clinical Fidelity and Safety in Therapy Chatbots Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18008 - SlackBench: Benchmarking Agents on Collaborative Projects Grounded in Real Code Repositories Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05512 - Where Is the "Self" of a Large Language Model? -- From Self-Index to Self-Reference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16717 - Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15008 - DUP: Detection-guided Unlearning for Backdoor Purification in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.01647 - Accelerating Long-Context Decoding in Large-Scale Hybrid LLMs Without Retraining Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06133 - PAYWORTHY: Can LLMs Predict Which Freelance Jobs an AI Agent Will Complete? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05759 - Unlocking Turing Tensor Cores: A Measured Throughput Account of From-Scratch Pre-training on a Single 22G RTX 2080 Ti Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05419 - Overview of the NTCIR-19 SciClaimEval Task: Cross-modal Claim Verification in Scientific Papers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06090 - Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.19544 - Reasoning over Non-Parametric Memory in Multilingual LLMs: A Cognitive-Based Analysis of Relational Knowledge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06715 - Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10832 - Where Should a KV-Cache Repair Budget Go? Distractor Structure and Contextual Compatibility in Non-Prefix Reuse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06397 - Rewrite, Then Veto: Rewriter-Agnostic Edit Gating for LLM-Based Post-OCR Correction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05539 - Recon: Reconstruction-Guided Reasoning Synthesis for User Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26969 - Iterated creation, grading, and revision of data science projects by language models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05548 - Human-like cross-language generalisation in deep neural speaker embeddings and its acoustic foundations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05384 - In-Context Learning for Diagram Code Generation: What is the Effect on Faithfulness and Quality? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.20476 - Growing One's AI Tools: A Paradigm of Practice-Grown Tools Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06132 - LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06808 - Modality-Aware Expert Pruning for MoE-Based Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05927 - Same Origin, Different Verdicts: Text Production Conditions Confound Machine-Generated Text Detection in Russian Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05385 - SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05721 - Adapting Qwen3 to Tajik from 0.6B to 8B: Lower Text Loss Did Not Mean Better Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06062 - TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04878 - Replicability, Reproducibility, and Robustness in Political and Social Science Research with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06639 - SAUCE: Summary Analysis Using Conversation Entailment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06812 - Labadain-MedQA: A Tetun Medical QA Dataset for Fine-Tuning and Evaluating Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00935 - LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10779 - Principal Trait Analysis: Identifying User Behavioral Traits in Human-AI Collaboration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11460 - LooM: Loop-Invariant Memory for Causal Encoder-Decoder Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06835 - Does Context Compression Preserve Refusal Alignment? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06380 - Combining Determinism and Indeterminism Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2009.03996 - Holistic Parallel Supervision for Expressive Speech to Speech Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06010 - Steer2Edit: From Activation Steering to Component-Level Editing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09870 - Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.09338 - Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03415 - A Dual-Path Architecture for Scaling Compute and Capacity in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30202 - Selective, Risk-Controlled Emotion Forecasting in Conversation: From a Persistence Barrier to Departure Detection with Conformal Guarantees Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05896 - Cognitive Bias Signatures in Search-Equipped LLM Agents: A Stage-Resolved Analysis Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05720 - Familiar letters, not related languages, let unseen languages into a shared space of meaning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06006 - When Does Better Confidence Improve a Knowledge-Graph Audit? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05877 - The Harness Is the Model: Agent Scaffolding Changes a Fixed LLM's Compliance with Banking Conduct Rules, Unevenly Across Models Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.06116 - Agent Harness Awareness: Turning Verified Telemetry into Operational Control for Tool-Using Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05391 - MedConstBench: Benchmarking How Constitutions Steer LLMs in Medical Ethics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.36513 - DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20773 - Computational Phenomenology of Borderline Personality Disorder: A Comparative Evaluation of LLM-Simulated Expert Personas and Human Clinical Experts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.19008 - AGORA: Reliability-Aware Aggregation of LLM Judges via Item-Response Theory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05556 - SpecCompact: Accelerating LLM Agent Context Compaction with Slot-Parallel Semantic Speculative Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06876 - Multi-User Large Language Model Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08567 - Query-Oblivious Coresets for Softmax Attention: Improved Bounds and Efficient Constructions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06327 - Interpretable Text Embeddings Based on Hierarchical Questions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06402 - MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29300 - RefCraft: Benchmarking Visual-Reference-Conditioned Agentic Generation through Web Development Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26826 - AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02602 - SAGE: Stochastic Prompt Optimization via Agent-Guided Exploration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18902 - SRRM: A Retrieval-Reconstruction Benchmark for Evaluating Long-Context Memory in Small Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05386 - PolicyMem: Geometric Policy Memory for LLM Governance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13734 - LLM Agents Already Know When to Call Tools -- Even Without Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09252 - Language Models as AI Research World Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.12235 - Can One Adapted Model Do It All? Fine-Tuning Strategy Selection for Customer Support LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27262 - TandemBench: Benchmarking Decision Models for Multi-Agent Collaboration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05827 - RADIUS: Ranking, Distribution, and Significance - A Comprehensive Alignment Suite for Survey Simulation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.19002 - Discourse Analysis of Legislative Bill Discussions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05381 - Grounded but Not Immune: Confirmation Bias in Agent-as-a-judge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05662 - CRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06501 - Beyond accuracy: what AI assurance needs to establish in public services Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06655 - CyclicJudge: Mitigating Judge Bias Efficiently in LLM-based Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.01865 - Autonomous agents for electricity-system planning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05911 - Digital sovereignty in professional translation workflows: a case study of migrating from Windows to Linux Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41561 - Presentation Sensitivity in Typed Decision Models for Subjective Text Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06384 - When Every Choice Is Correct: A Causal Study of Numerical Preference in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06025 - Measuring Risk, Not Harm: Detecting Psychological Harm Risk Factors in LLM Conversations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06806 - Fine-tuning LLMs for Passive Depression Severity Estimation from AI Mental Health Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17973 - Sparse Reward Subsystem in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00986 - Ruby-OPD: Enhancing Pronunciation Controllability and Accuracy for Flow-Matching Text-to-Speech via On-Policy Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06403 - Breaking Bad Molecules: Are MLLMs Ready for Structure-Level Molecular Detoxification? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.10912 - How Well Can Large Language Models Impersonate Individual Authors? A Comparative Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05771 - 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 - DS@GT ARC at CheckThat! 2026: A Verdict-Anchored Pipeline for Generating Fact-Checking Articles Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05382 - Training-Free Character-Length Control in Summarization with Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06371 - Learning When Human Decisions Matter: Executor-Relative Consultation Value for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05814 - From Representations to Behaviors: Exploring the Person-Situation-Behavior Triad in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.26853 - LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis Source: arxiv-cs-cl Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.06856 - Contextual Pictograms for Repairing Multilingual ASR Errors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05637 - Twists and Turns: A Graph-Based Benchmark and Framework for Long-Term Memory in Exploration Tasks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06414 - EvoGuard: Mitigating Degradation in Online Skill Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06444 - Who Is Your Ideal Companion? Evaluating Emotional Companion Capabilities of LLMs Based on Adult Attachment Theory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13168 - SVGFaith: A Two-Layer Meta-Evaluation of Faithfulness Metrics for Text-to-SVG Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06048 - Reconciling Privacy with Provenance for Language Model Watermarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06100 - MASBench: Benchmarking LLM-based Multi-Agent Collaboration under Partial Observability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04672 - Every finite group admits a just finite presentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10402 - Where Search Agents Go Off the Rails: Graph-Grounded Step-Level Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06662 - UniCompress: From Multi-LoRA Experts to One Compact Model for Edge Intelligence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06075 - X-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21450 - CoSafe: Cooperative Runtime Safety Assurance for Mixed-Traffic Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06204 - Decision Models as Scalable Economic Surrogates that Capture Human Variation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05553 - Local Entropy Fluctuations for Black-Box LLM-Generated Text Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33767 - FPTR: Feasibility-Preserving Transactional Refinement for Deadline-Constrained Joint Beam and Resource Allocation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06491 - Touch\'{e}World tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06061 - Jev with Foresight: Safe Language-Guided Autonomous Driving via a Language World Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05448 - VCoT-SQL: Enhancing Text-to-SQL Generation through Dual Chain-of-Thought Validation Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00815 - Traffic-VL: Reinforced Vision-Language Models for Generalizable End-to-End Traffic Signal Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06353 - Who May Overrule the Agent? Evidence-Gated Authority in LLM Review Institutions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05390 - Ekka: Automated Diagnosis of Silent Errors in LLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04594 - MAIA: Multi-Agent Intent Articulation for Requirement Discovery in Art Commissions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.12097 - Graph-Mediated Large Language Model Systems in the Agentic Era: Reasoning, Knowledge, Retrieval, Execution, and Coordination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05953 - Addition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06553 - Prism: Bidirectional Self-Teaching for Unified Multimodal Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06343 - A.S.E 2.0: Understanding How Repository Context Impacts the Security of LLM-Generated Code Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06294 - Discarded or Unreachable? Diagnosing and Repairing Spatial Relation Failure in Vision--Language Similarity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05565 - MA-Mesh: Resilient Multi-Agent Collaboration via Role-based Self-Healing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06389 - CompressionBench: How can your coding agents compress LLMs? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06858 - Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16725 - CellCanon: An Agentic Cellular World Model for Prediction, Explanation, and Observation-Driven Updating Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05890 - From Type to Token: Petri Nets, Individual Token Philosophy, and Individualized Causal Effects Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05703 - A Financial Brain Scan of the LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.21285 - MEA: A Reward-Driven Multi-Agent System for Faithful Model Explanations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02480 - Certified Circuits: Stability Guarantees for Mechanistic Circuits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22968 - LLM-based NPCs in Video Games: A Systematic Mapping Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05427 - Human Motion Prediction via Continual Prior Compensation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06637 - Reglos: A Self-Evolving Personal Memory Agent with Recursive Self-Improvement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06049 - Do Saliency Maps Fail Dense Breasts? A Chance-Normalized, Confounder-Aware Audit of Explanation Fairness in Mammography Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05909 - CHARM+: Cross-Hardware Attention with Re-Merge Multistream Mechanism Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05906 - ViBench 2.0: A Benchmark for Long-Horizon Software Building Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05620 - Route First, See Later: Enabling Vision Agents to Reason Scientifically by Separating Routing Policy from Action Spaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06760 - An Engineering Reading of the Bounded Halting Problem and Observable Properties of a Universal Machine Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06303 - Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15591 - TACT: A Pragmatic Approach to Qualitative Analysis with an AI Council Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05702 - TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06741 - AS2 -- Attention-Based Soft Answer Sets: An End-to-End Differentiable Neuro-Soft-Symbolic Reasoning Architecture Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18436 - How Do Artificial Agents Make Decisions in Light of Visual Data? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05671 - Microdroplet Generator Surrogate Enhancement and Inverse Design Through an Uncertainty-Guided Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06464 - Ab Initio Accuracy Beyond the Cutoff: Distributed Message-Passing Equivariant Attention at Tens-of-Millions-of-Atom Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06122 - ServerBench: How can your coding agents design specialized LLM serving systems? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06841 - How Finely Can Vision-Language Models See Biology? Bio-VQA: A Benchmark for Taxonomic, Morphological, Spatial and Individual Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05559 - MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21272 - BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06911 - PointRAFT: 3D deep learning for high-throughput prediction of potato tuber weight from partial point clouds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.24193 - Exploiting Textual Semantics for Robust Cross-View Object Correspondence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02356 - Rules, Traces and Routing Statistics: Training and Calibration Data for Open Models on ARC-AGI-2 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06827 - When Disclosure Is Compulsory: Evaluating Ride-Hailing Rebalancing Policies with Self-Interested LLM Driver Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.41132 - Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.00481 - Vision Paper: Why Distributed LLM Post-Training and Decentralized Alignment Are Now Essential Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05841 - Beyond Risk Cues: A Mechanism-Level Benchmark and Verifiable Debate for Scam Video Detection on the Web Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06110 - Route to Remember: Adaptive Memory Selection for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05636 - Patients With Personality: Realistic Patient Simulation through Controlled Diversity and Selective Disclosure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17441 - Can Large Language Models Review the Scientific Literature? A Test Against a 102-Article Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05459 - Quantifying Local and Global Fidelity of Nonlinear Embeddings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00290 - Faces in Things, Faces in Nothing: Probing Face Selectivity in Vision Models with Pareidolia Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03989 - Fast and Memory-Efficient Wavelet Convolutions via I/O-Aware Reformulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10805 - EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06518 - AmbiHTMLBench: A Benchmark for HTML-based Visually Rich Document parsing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06449 - NextGAN: Towards Simple and Scalable GAN Training for Image and Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06270 - Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06273 - DyPSI: Dynamic Physics Sensing via Joint Field and Sensor-Trajectory Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06280 - Do agents need to sleep? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02216 - CAST-Bench: Tracing Every Sound to Its Source in Multi-Shot Audio-Video Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05422 - Mind Control of LLMs via Closed-Loop Stimulation: Out-of-Distribution Robustness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06418 - Tools Need Not Speak in Text: Latent Context Compression for Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06500 - RECAP: Context-Aware Prediction Recycling with Request-Local and Persistent Memories for Multimodal Speculative Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05894 - Predicting protein structures at any folding stage from sequence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04287 - 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 - Towards Robust Long-Lived Agents: Benchmarking Experience Lifecycles in Evolving Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05450 - Consistency Is Not Understanding: Orbit Audits for Neural Field Weight Readers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05798 - Hybrid Spark: Adaptive Speculative Decoding That Lets the Content Choose the Drafter Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05611 - KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09153 - MA-SafeDiffuser: Safe Multi-Agent Planning with Diffusion Probabilistic Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05524 - RoboTryOn: 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 - Bidirectional Centered Score Matching for Discrete Diffusion Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04279 - Time-Division Multiplexing: The Operational Rhythm and Temporal Organization Layer of Digital Life Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06603 - Drift-adaptive Representation Preservation for Domain-Incremental Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06093 - When File Ingestion Misleads Language Models: Measuring and Mitigating Divergences in Office Documents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05806 - Multi-Resident Data Association in Smart Homes via MDP Modeling and Behavior Cloning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06296 - Dull, Dirty, Dangerous? Working Conditions and the Limits of Occupational AI Exposure Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06888 - MESA: An Evaluation Framework for Compositional, Semantic, and Spatial Generalization in Robotics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05567 - FloMo: 3D Scene Flow as a World Action Model Intermediate for Learning from Human Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05062 - Evolving Support Priorities in Empathetic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34249 - Which One Is Sounding? Binaural Sounding Instance Disambiguation for Audio-Visual Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06074 - SPARTA: A Sparse Ternary LLM Accelerator with Adaptive Attention and Unified Datapath for Long-Context Edge Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.34824 - Reasoning-Trace Overflow in Code Generation: An Empirical Study of Explicit Reasoning Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06095 - VIPBench: A Human-Aligned Benchmark for Voice Identity Perception in the Age of Voice Cloning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05638 - RetryBench: Separating Retry Permission from Recovery Outcomes in GPT Tool Use Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15884 - Large-Language-Model Discovery of Quantum LDPC Codes through Structured Concept Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24808 - Designing Benchmarks for Knowledge Work Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23262 - EviSeek: An Evidence-Centric Agentic Framework for Embodied Active Information Seeking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06434 - Signals: Continuous Diagnostics of AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04507 - A Roadmap to Impactful Pluralistic Alignment Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.22305 - Occlusion for Free: Detecting Occlusion from the Disagreement Between Two Monocular Distance Cues Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06899 - AgentTrustCI: Build-Time Policy, Grounding, and Trajectory Tests for Java LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06674 - AEGIS: Preserving Privacy of 3D Facial Avatars with Adversarial Perturbations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.17747 - HyScale: Scaling Long-Context Training for Learned Sparse Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32057 - LifeVal: Evaluating AI Model Performance on Personalized Agentic Consumer Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06687 - EchoKV: Self-Corrective KV Cache Eviction via Iterative Query Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05903 - Just the Facts: How Dialogues with AI Reduce Conspiracy Beliefs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05572 - PersonaCodeBench: Evaluating Coding Agents in Persona-driven Human-Interactive Sessions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05739 - Same Words, Different Judgments: How Preferences Vary Across Modalities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22710 - When Does Sharing Work? Scaling a Shared SigLIP2 Across Image, Video, Audio, and Audio-Visual Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05406 - A Feasibility Condition for Confidence-Gated Tiered LLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05394 - Does Frontier AI Strengthen Cyber Defense? Evidence from Project Glasswing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06629 - 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 - Isharah-Selfie: Continuous Sign Language Recognition Dataset for One-handed Signing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33200 - BrainBind: Bridging Synchronized EEG and fMRI through Long-Form Naturalistic Video Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05581 - Agent Security is a Systems Problem Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18991 - Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05711 - Whose Transparency is it Anyway? Understanding Generative AI Transparency Needs and Gaps Across Stakeholders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05549 - Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02628 - Today's Work, Tomorrow's Workforce: Incentivizing Learning in AI-Assisted Work Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06346 - MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06282 - TraceCAD: Trace-Guided Repair for Agentic CAD Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.03062 - One Scale, Four Texts: Gaps, Overlaps and Silent Repairs in Published Grading Schemes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06569 - Reinforcement Learning in GUI Agents: A Survey Toward Digital Inhabitants Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27955 - PEEK: One-Step-Look-Ahead Exposure Bias Correction for Diffusion Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05407 - STRIDE: Automated Evaluation of Text-to-Trajectory Alignment across Diverse Contexts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34799 - DARE: Difficulty Analysis for Repair Enhancement Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05797 - Investigating Anthropometric Fidelity in SAM 3D Body Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.06035 - Whiel: A Neurosymbolic Platform for Certified Relational Program Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05612 - SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06598 - On Turn-Level Best-of-N Sampling for Scaling LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06868 - ReMoA: Recursive Modular Adaptation via Sparse Latent Refinement in Multimodal Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.25299 - 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 - Risk Control Certifies Rates, Not Magnitudes: An Audit of Selective Fetal Biometry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05851 - Using profiles of cognitive capability to assess AI suitability for workplace tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25623 - Bridging the Morphology Gap: Adapting VLA Models to Dexterous Manipulation via Intent-Conditioned Fine-Tuning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12109 - 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 - Trick-or-Treat: Adversarial Evaluation of Multimodal Medical Reasoning with Synthetic Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06631 - VirtualTrialHarness: Coordinating Agentic Operationalization of Virtual Trial Protocols Across Complex Clinical Schemas Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05551 - Hybrid LLM-Deterministic Pipelines for Enterprise-Scale Code Migration at Bloomberg Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05457 - Auditable Unlearning for LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05866 - Reliability Engineering for AI Systems: Challenges, Methods, and Directions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35316 - COL-Trees: Efficient Hierarchical Object Search in Spatial Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22183 - From Admission to Retention: Predicting Durable Offspring in Quality-Diversity Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06522 - Intra-Architecture Source Attribution for Stable Diffusion: A New Task with Benchmark Dataset and Baseline Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06000 - Smartphone-Aided VR Exergames for HIIT: Gamifying Fitness with Real-Time Pose Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06734 - Learning Soft Robotic Dynamics with Active Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.27428 - Attributing Agent Failures to Their History Needs an Executed Counterfactual: Toward a Reporting Standard Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05650 - Beyond the principle-practice gap: Responsible AI as situated epistemic and ethical practice Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06709 - BobFlow: Towards Human-Agent Collaborative Data Science Using Dataflows Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.05761 - EgoGen: An Egocentric Synthetic Data Generator Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2401.08739 - Autonomous ETL Pipelines for Salesforce M&A Consolidation: A Reference Framework, Jitterbit Mapping, and Reproducible Simulation Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05918 - From Certified Pairs to a Certified Hub: Reasoner-Checked Crosswalks for the Information Exchange Standard Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06628 - Reasoning-Aware Cross-Modal Association Unlearning in Multimodal Large Reasoning Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06168 - ScamWorld: An Interactive Environment for Evaluating Web Agents Against Online Fraud Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04879 - Learning to Learn from Multimodal Experience Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16857 - Variable Bound Tightening for Nash Equilibrium Computation in Multiplayer Imperfect-Information Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25997 - STEK: Structural-Terrain-Enhanced Koopman-Inspired Cross-Channel Regularization for Retrospective Battery Multi-Target Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06299 - Signed, Sealed, Leaked: Trust Beyond Signature for MCP Toolchains Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06585 - CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.02459 - A Hybrid Approach for Automated Security Pattern Recovery Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.05823 - Anduin: A sybil-resistant agentic marketplace reputation system Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05586 - Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.07697 - OS-Wizard: Scaling Computer-Using Agents to Specialized Software via Knowledge-Guided Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33907 - Ray-Tracing-Based Dynamic Channel Sounding With Autoregressive Wi-Fi CSI Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05970 - Generative AI for urban planning: synthesizing land-use maps with satellite imagery via DualControlNet Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05859 - ENACT-Heart -- ENsemble-based Assessment Using CNN and Transformer on Heart Sounds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.16914 - SysPilot: Cross-Library Performance Autotuning via Library Performance Contracts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06078 - How Unbalanced Must a Latin Rectangle Be? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06003 - EnzymeRSI: A dual-loop recursive self-improvement system for enzyme design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06321 - A Training-Free Socket for DNA in Frozen Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05401 - SUMONE: A Simple and Efficient Summarizer for Plug-and-Play Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06445 - Task-Efficient Agent Evaluation Using Cached Traces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06803 - 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 - ModalSearcher: Weaving Visual Evidence into Autonomous Cross-Modal Deep Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06131 - AromaGen: Interactive Generation of Rich Olfactory Experiences with Multimodal Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.01650 - FrontierPhysics: Evaluating Agents for End-to-End Physics Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06910 - Darwin Family: MRI-Trust-Weighted Evolutionary Merging for Training-Free Scaling of Language-Model Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.14386 - Verified but Vacuous: Three Failure Surfaces of LLM-Driven Verified Code Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05590 - AutoBCI: Forecast-Guided Agentic Neural Architecture Discovery for EEG-Based Brain-Computer Interfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35456 - AutoEnergyDesign: An LLM-Driven Agent for Automatic Energy System Design Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35160 - A Systematic Benchmark for Evaluating Multimodal Personalized Reasoning of Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06259 - Assurance-Conditioned Continuous Authorization for Autonomous AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05632 - HarnessFlow: MCTS-Guided Harness Optimization for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06254 - AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.23239 - Scheduling Data to Compute: Hierarchical Data Pipelining for LLM Training on AMD GPUs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05751 - Split-KV: Efficient Context Parallelism for Training Diffusion Drafters Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05926 - GREP: Grounding Generated Room Evaluation in Principles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05802 - AgenticFinBench: Benchmarking Financial Agents on Diverse Tasks from Real-World Requests Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.04813 - Disentangle to create: Architecture-level disentangled diffusion model for few-shot Chinese font generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.18874 - Towards Efficient Whole Page Ranking with One-Pass Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05542 - Learning to Decode Linear Codes with Generalized Belief Propagation Network Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06874