TILens Daily Edition
2026-10-12
Filters: topic=ai-research, github=hidden

Stats: 433 articles, 4 sources, 429 research papers
Top topics: AI, AI Research, Information Retrieval

## News

- How to Learn AI in 2026: The Neuron’s Beginner Livestream Roadmap
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/explainer-articles/how-to-learn-ai-in-2026-the-neuron-beginner-livestream-roadmap/

- Microsoft’s Maia 300 Reveal the Computing Demands of AI Agents
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/news/microsoft-maia-300-ai-agents-computing-demands/

- 😸 White House orders AI incident reporting
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/newsletter/white-house-orders-ai-incident-reporting/

- Could a $3,499 AI Computer End Your Monthly AI Bills?
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/explainer-articles/ghost-core-ai-computer-monthly-ai-bills/

## Research

- We Specified an AI Agent in 2016. We Called It Analytics.
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/we-specified-an-ai-agent-in-2016-we-called-it-analytics/

- I Built a Trap for AI Image Judges. They Walked Into a Different One.
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/i-built-a-trap-for-ai-image-judges-they-walked-into-a-different-one/

- Returning to Development States: When Full Sandbox Snapshots Help Coding Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13841

- Near-Minimax-Optimal Rates for Asynchronous TD Learning with Markovian Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.38880

- Green-Routed Neural Operators: Physics Determines Where the Network Reads
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.05337

- Discovering Phase Space Structure in Learned Hamiltonian Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.23003

- Optimizable Model Averaging for Ensembling Heterogeneous Model Outputs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.21857

- Mixture-Greedy for Online Generative Model Selection: Is UCB Necessary in Diversity-Aware Multi-Armed Bandits?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.21716

- On the Approximation Complexity of Matrix Product Operator (MPO) Born Machines
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.11471

- Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13020

- X-AVDD: Cross-Attentive Audio-Visual Dataset Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13687

- HART: Hybrid Attention-RWKV Time series Foundation Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12883

- Bandits with Anytime Knapsacks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.18560

- DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.03207

- Simultaneous Competitive and Regret Guarantees for TCP Acknowledgment
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13571

- PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.16215

- VQIL: Visible Quantum Interference Learning for Perturbation Response Ranking on Graphs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13689

- A Sampling Complexity-aware Framework for Discrete-time Fractional-Order Dynamical System Identification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.17499

- Model Capacity Determines Grokking through Competing Memorisation and Generalisation Speeds
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.09724

- Revisiting Accent Classification with DistilHuBERT: Speaker-Disjoint Evaluation and Cross-Corpus Generalization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13440

- Behind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational Insights
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12527

- The Limits of Query Monitoring against Distributed Model Extraction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13083

- Locally Private Parametric Methods for Change-Point Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.13619

- Koopman-Based Nonlinear Identification and Model Predictive Control of a Turbofan Engine
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.01730

- Deploying RDMA for Large-Scale Inference and Training Workloads
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12815

- Constructive Bounds for the Topological Expressivity of Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13931

- Amortized Counterfactual Prediction with Graph Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13724

- EmoGavel: Grounding-Aware Reinforcement Learning with Verifiable Rewards for Multimodal Emotion Preference Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13353

- Acoustic Biomarkers for Alzheimer's Disease Detection from Spontaneous Speech
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12500

- Particle-based Generalised Stochastic Optimisation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.02844

- Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13261

- StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo Cameras
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12734

- Finite-Sample Guarantees for Fully Discrete Conditional Diffusion Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13851

- Shortcut Learning in Geospatial Foundation Model Embeddings for Cross-Disaster Damage Assessment
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13766

- Fast Rates for Nonstationary Weighted Risk Minimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.05742

- Double-Take: Improving Capacity, Binding, and Selectivity In Long-Context Within Bidirectional Memory
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13073

- Evolving Hybrid Quantum-Classical Architectures for Image Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.03220

- BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12907

- Deflating the Hessian: Rank-4 W4A4 Quantization for Multimodal Diffusion Transformers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11315

- RanSOM: Second-Order Momentum with Randomized Scaling for Constrained and Unconstrained Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.06824

- DataCupid: Stable Matching Repair for Training Data Acquisition with Delayed Feedback
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12960

- Tabular Foundation Models Are Effectively Shallow
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13253

- Hierarchical Experimentalist Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.29315

- CV-OPD: Contrastive Vision On-policy Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13264

- Private and Distributionally Robust Federated Multiclass Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13631

- BLOKS: Scaling Kernel Solvers with Sketched Block Preconditioning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13382

- Lesion-DDPM: Lesion-Enhanced 3D Diffusion for MS MRI Synthesis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.15457

- Electron-Density-Informed Molecular Property Prediction Using Surrogate Functionals
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13649

- Recovering Irreducible Three-Body Interactions with Lagrangian Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13292

- Reinforcement Learning via Fixed-point Flow Matching
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12848

- NucleoNet: A Nuclear-Aware Determinant Ansatz for Multi-Geometry Neural Variational Monte Carlo
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12985

- Playing the network backward: A Game Theoretic Attribution Framework
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.06212

- Provably Accurate Shapley Value Estimation via Leverage Score Sampling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2410.01917

- Second-Order Optimization with Asynchronous Curvature
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.15714

- Sera: Semantic Representation Aggregation for Reliable and Interpretable Battery Health Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11567

- Algebraic Integer Quantization for Machine Learning Applications
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12494

- SqueezeBench: Saturation-Resilient Evaluation of Mathematical Capability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13461

- Estimating Great Expectations Under Autoregressive Language Models with Potentials
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11399

- DyssomniaNN: Multi-Scale Spiking Neural Modeling of Human Sleep Disorders and Perceived Restedness
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13918

- Matched-Context Group Policy Optimization for LLM Agent Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13755

- Rationally Linearized MLPs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13568

- The Expressive Power of Random-Feature MPNNs Across Graph Sizes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12809

- Optimal Algorithms for Nonsmooth Nonconvex Stochastic Optimization with Constraints
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13787

- First-Order In-Context Shapley: Scalable Data Auditing for LLM Alignment and Evaluation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.22766

- Amortised Inference through One-Step Implicit Sampling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12679

- Robust LassoNet: Enhancing Feature Selection in Neural Networks via Robust Loss Functions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.38263

- State-OPD: State-Grounded On-Policy Distillation for Multi-Turn Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13238

- Monarch-MoE: Structured Experts for Multimodal Continual Instruction Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13215

- Instance-Level Difficulty: A Missing Perspective in Machine Unlearning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2410.03043

- Trajectory Prediction for Autonomous Driving in Road Construction Zones Using Human-in-the-Loop Driving Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12747

- Harmonic analysis and circuit approximation of Sobolev functions on quantum input spaces
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13477

- Hitting-Time Bounds for Asynchronous Q-Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13901

- Graph World Models for Constrained Epidemic Policy Planning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.35545

- Personalized Federated Direct Preference Optimization via LoRA Adapters
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12885

- Machine Learning and Time-Series Foundation Models for Day-Ahead Electricity Forecasting in a University Building
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12638

- Workhorse: Learning Robust Whole-Body Humanoid Loco-Manipulation from Human Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.09117

- QTestBench: A Test Framework for Evaluating LLM-Generated Quantum Code
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13811

- Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.05745

- Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13923

- Product Monte Carlo: Expectation Under a Product of Densities
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12702

- Generalized Determinantal Point Processes for Attraction and Repulsion with Distinct Interaction Kernels
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12894

- Bayesian dynamic scheduling of multipurpose batch processes under incomplete look-ahead information
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.01093

- Rethinking Relative Policy Differences Transfer of On-Policy Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13205

- Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13051

- SBNO : Schr\"odinger Bridge Neural Operator for the Forward and Inverse Problems under Missing Information
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13317

- Rethinking the Roles of Diffusion and Decoding: Predictive-State Flows for Parallel Language Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12898

- TabMF: Learning Dataset Representations with Tabular Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13818

- APEX: Asynchronous Prefix Denoising for Extreme Compression
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12843

- Nonsmooth Optimization via Orthogonalized Momentum
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13677

- What Makes Adversarial Examples Transfer Across Deepfake Detectors?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.10002

- Does Learning Recurrent Networks Matter in Partially Observable RL?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13197

- ReplaySSM: Cache SSM Inputs, Not State
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13778

- MagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data Synthesis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12659

- EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.00986

- Surrogate Graph Partitioning for Spatial Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.07832

- Beyond Pairs: Your Language Model is Secretly Optimizing a Preference Graph
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.08037

- Randomized Momentum Transport with Cheap Predictors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13789

- OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.38345

- Hidden Data Challenges in Clinical Machine Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13350

- A multimodal large language model for evidence-based autism spectrum disorder screening
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.16464

- CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12530

- H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.02592

- Improving Certified Robustness via Adversarial Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.31653

- RLVR$^{2}$: Reinforcement Learning with Verifiable Rubric-based Ranking
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.23457

- Does Location Matter? A Black-Box Causal Audit Reveals Model-Dependent Audio Grounding in LALM Hallucination
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13112

- Enriched Holomorphic Neural Networks for 2D and 3D Laplace Problems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12541

- In-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark Validation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13411

- Stochastic Compositional Optimization via Hybrid Momentum Frank--Wolfe
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.15350

- Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13015

- Scalable Sparse Autoregressive Variational Inference for Non-Gaussian Spatial Fields
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13656

- DAG Structure Learning with Node-Varying Heavy-Tailed Disturbances
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13304

- A Categorical Atlas of Parameter-Efficient Fine-Tuning: Cones, Orbits, and Gauges
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12728

- Zebra3D: Efficient Hybrid Foundation Models For Scalable 3D Reconstruction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12727

- Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12737

- AutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of Edits
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12545

- MIRROR: Learning from the Other View for Multi-Modal Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.21552

- Target-Constrained Pooling for Trajectory Extrapolation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13034

- Designing Protein Structures from Natural Language
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13917

- What Should SFT Learn? Conditional Information Gain for Generalizable Post-Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12995

- Neural expectation-maximization and meta-models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12741

- Vision2Code: A Multi-Domain Benchmark for Evaluating Image-to-Code Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.11307

- Scalable Circuit Learning for Interpreting Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.16939

- Sample-Adaptive Zeroth-Order Post-Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12566

- Quadratic Characterizations for Reachability Analysis of Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.20482

- S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13202

- On the Design Space of Continuous Diffusion Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13834

- Variance-Reduced Policy Gradient is Nearly Minimax-Optimal
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13692

- KL Before and After Mixing: A Round-Complexity Separation in Parallel Sampling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13924

- TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.07767

- When Solvers Get Moody: Quantifying and Predicting Performance Variability in Mixed Integer Programming
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12876

- Neuromorphic Satellite Intelligence: A Formal Framework for Event-Driven Architectures, Spike-Based Algorithms, and Quantitative Energy-Accuracy Trade-offs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12471

- Minimax Rates for Estimating Powered Sliced Wasserstein Functionals
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12740

- TernaryLLM: Ternarized Large Language Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2406.07177

- Sampling-Based Safe Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.19469

- Credit Attribution in Timestamped Soccer Networks Using Multivariate Hawkes Processes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12775

- Decoding Register Tokens Preserves Global Scene Details
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13299

- DuoRate: Two-Rate Per-Expert Precision Allocation for Mixture-of-Experts Serving
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13328

- Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.08015

- Hamiltonian locality testing and certification do not achieve the Heisenberg limit
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.03205

- Why Linear Models Can Still Work in a Complex and Changing World
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13404

- FactoryNet: A Large-Scale Dataset toward Industrial Time-Series Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.09081

- COBALT: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.03806

- Occam's Razor is Only as Sharp as Your ELBO
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.25984

- Vocal Intensity Conversion with Continuous SPL Control via Adversarial Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13608

- When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11523

- Learning to accelerate Krasnosel'skii-Mann fixed-point iterations with guarantees
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.07665

- Reinforcement learning for inverse silhouette design and rapid laser cutting of compact parallelogram quad kirigami prototypes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.08098

- CircuitTree: Composing Circuits into A Syllable Transcriber
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12520

- Some remarks on the connection between generative diffusion and optimal transport
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13614

- On the estimation and validity of AI time horizons---a statistical look at the METR plot
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12466

- Structure-Aware Numerical Stabilization for Half-Precision Proximal Policy Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13306

- CoBe: A Benchmark For Conversational Counterfactual Text Editing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13057

- Critical Mass: Structure-Disjoint Splits Drift With the Libraries They Are Built On
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12694

- Learning Schwarzschild Geodesic Motion with Lagrangian Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13234

- When Should the Teacher Move? Temporal Coupling and Stability in Self On-Policy Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.03532

- Market Impact Estimation via Causal Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12537

- Geometry-Aware Multi-Objective Optimization: Norm-Constrained Oracles with Entropic Weight Updates
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13773

- Sparse Dictionary Learning for Measure-Valued Data via Linearized Optimal Transport: Efficient Algorithms and Sample Complexity
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12924

- Scaling RNA Foundation Models through Iterative Refinement
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13106

- Beyond QAOA: A Review of AI and Quantum Computing for Adaptive Combinatorial Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11759

- Unsupervised Identification and Removal of Spurious Correlations During Fine-Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.27676

- Constrained Probabilistic Numerics: Gaussian Process Solvers for Linear PDEs under Linear Inequality Constraints
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13804

- Data-Driven Stochastic Optimal Control in Reproducing Kernel Hilbert Spaces
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2407.16407

- User Trajectory Prediction Unifying Global and Local Temporal Information
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.02161

- Taking Tokenization off the Host for Agentic LLM Serving
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13325

- CorrFlow: Exact and Permutation-Equivariant Flow Matching on the Correlation Elliptope
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13606

- Cross-View Attention Fusion Net: A Prior-Guided Dual-View Representation Learning for Cardiac Output Estimation from Short-Term PPG Signals
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.19666

- Faithfulness Without Anchors: A Position Paper on the Structural Misalignments of Explainable AI Faithfulness Metrics for Feature Importance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12493

- Asymptotic Analysis of Discrete-Time Self-Attention Dynamics in Transformers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13518

- Preference Elicitation for Policy Optimization and Application to Aligning Heart Transplantation with Human Values
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.28620

- Federated Learning of Nonlinear Temporal Dynamics with Graph Attention-based Cross-Client Interpretability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.13485

- Pretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRM
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13660

- Specialists Learn Faster: Knowledge Organization in Pre-training Shapes Knowledge Update Efficiency
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13835

- Static Gradient Attribution Underperforms a Density-Matched Random Mask on Loss-Based Forgetting Within LoRA B-Matrix
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12744

- Neural Surrogate Modeling of Ultrasonic Wave Propagation in Heterogeneous Media
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13258

- Urban Power Grid Topology and Hierarchy Identification from Open Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.21352

- From Pixels to Privacy-Sensitive Features: An Information-Theoretic Framework for Reconstruction Bounds
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13768

- SynAct: Synergistic Active Feedback Learning for LLM Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12651

- Medical foundation models converge less under label supervision
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.20274

- Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.02626

- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12572

- Meta-Reflective Evolution Effectively Improves Production AI Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12794

- Model-free Bayesian Clustering and Multimodal Posterior Summarisation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13397

- RARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic Manipulation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13578

- Learning by Compression: Risk Estimates Attain the Law-of-Large-Numbers Rate
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13442

- SelectArena: A Modern Benchmark for Feature Selection on Real-world Tabular Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13644

- Machine Unlearning for Federated Socially Fair k-Means Clustering
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13717

- Agents' Last Exam
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.05405

- Desertification Forecasting in Semi-Arid Regions: Using Deep Learning to Probe the Observability Limits of Land Degradation Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13406

- Disentangling Total-Variance and Signal-to-Noise-Ratio Improves Diffusion Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2502.08598

- Convex Optimization of Spiking Neural Networks with Global and Approximation Guarantees
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.08022

- ERIS: Enhancing the Privacy-Utility-Scalability Trade-Off in Federated Learning via Federated Shard Aggregation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.08617

- Recurrent Harness for Agentic Continual Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12668

- Linearized Wasserstein dimensionality reduction with approximation guarantees
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2302.07373

- Preference-Conditioned Multi-Objective Reinforcement Learning for Tactical Decision Making in Heavy-Duty Vehicles
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.18783

- Sonic-AMG: Streaming Human Motion Generation from Spatial Audio
  Source: arxiv-cs-lg
  Topic: AI Research (+AI, JavaScript, React)
  URL: https://arxiv.org/abs/2610.13300

- Fairness-Guided DQN-Based TXOP Control for NR-U/Wi-Fi Coexistence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.00457

- SmolWAM: A Latent World-Action Model for Robotic Manipulation on Edge Devices
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13740

- Transformer-based In-Context Score Operator Learning for Diffusion Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13690

- An all-transistor physical-learning transformer can be trained to perform in-context learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12571

- Planning with Transformers: Chain of Computation and Structured Context Windows
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.17710

- Low-Rank Kolmogorov-Arnold Generator Flows for Interpretable Operator Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13028

- Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.01892

- Probabilistic Forecasting of Electric Vehicle Charging in a Time-varying Hierarchical Infrastructure
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13588

- Spanning Diffusion and Flow-based Posterior Sampling via Exact Gaussian Conditioning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13812

- Tensor-based Fusion of Multi-modal Data for Predicting Cancer Risk Levels
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13221

- Mixture of Many Zero-Compute Experts: A High-Rate Quantization Theory Perspective
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.03151

- VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.21386

- MHR-Router: Multimodal Heterogeneous Retrieval-Enhanced Adaptive Routing for VLM Inference
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13278

- Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00661

- Efficient quadratic entropy with distance sketches
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11976

- WaSA: Wavelet Scattering Autoencoders for Unsupervised Offline Detection of Malicious Clients in Federated Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13186

- SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.20619

- Physics-inspired Generative AI models via real hardware-based noisy quantum diffusion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.22193

- Training Non-Differentiable Networks via Optimal Transport
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.01928

- Differentiable Retrieval-Augmented Generation for Predicting Cellular Responses to Gene Perturbation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.07233

- Does Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASR
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13432

- Two-way Guidance: Simultaneous Learning of Summary Statistics for Generative Bayes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12850

- Learning Transfers: Kan Extensions of Topological Invariants of Learned Representations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.07627

- When Generative Models Act as Simulators
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12847

- Fast Gradient-Based Approximation of Continuous Dynamic Time Warping
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13129

- Prediction-Informed Landing Window Planning for UAV Landing on USV in High Sea States
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13190

- One Thing Leads to Another: The Essentials of Time Series Causal Discovery
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13430

- Erased, but Not Gone: Output Forgetting Is Not True Forgetting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.25001

- Bayesian Nonparametric Mixed-Effect ODEs with Gaussian Processes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.13088

- Sustainable Cloud-Fog-Edge Systems for Smart Buildings: Algorithmic Adaptation under Memory Constraints and Dynamic Orchestration Strategies
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13307

- Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.11849

- On the Rate of Convergence of GD in Non-linear Neural Networks: An Adversarial Robustness Perspective
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.02095

- Towards Understanding the Training of GFlowNets: A Theoretical Perspective
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13711

- How Well Do Prior-Data Fitted Networks Amortize Bayesian Inference?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13764

- Diversity-Aware Ensemble of Quantum-Classical Models via Combinatorial Fusion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13808

- Lightweight Time-Frequency Vibration Sensing for Consumer Device Condition Monitoring
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13040

- SUN: Reaching for Novelty in Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.08642

- Stochastic MeanFlow Policies: One-Step Generative Control with Entropic Mirror Descent
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.21282

- COFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question Answering
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12837

- AgentTune: A Unified Training Lifecycle for Tool-Using LLM Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13335

- TreeHCA: Hindsight-Guided Exploration and Credit Assignment for Multi-Turn LLM Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12828

- Understanding Transformer-based Vision Models through Inversion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2412.06534

- CoGameReg: Cooperative-Game-Based Collaborative Semi-Supervised Regression for Seismic Reservoir Property Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12884

- S-Space: Exploring Spatial Workspace in Multimodal Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13527

- Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matching
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.00530

- EchoTab: Learning Measurement-Grounded Representations for Echocardiographic Diagnosis through Tabular Reconstruction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13599

- $L_0$ Feature Selection via Monte Carlo Tree Search in High-Dimensional Financial Regression
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13574

- FedPCD: Priority-Constrained Federated Aggregation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13508

- EarLog: Opportunistic Ear Physiology Sensing toward Personalized Hearing Risk Awareness
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12501

- Scaling Empowered Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13002

- Accelerating Linear Bandits with Persistent Candidate Sets
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13407

- AgentSWE: Can Coding Agents Build the Agent You Actually Want?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13361

- JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI, JavaScript, React)
  URL: https://arxiv.org/abs/2610.12957

- Heterogeneity-Aware Client Sampling for Optimal and Efficient Federated Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.11304

- Prediction Is Not a Sufficient Memory State
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13881

- Probabilistic Ship Trajectory Forecasting using Transformer Models on AIS Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI, JavaScript, React)
  URL: https://arxiv.org/abs/2610.13557

- Approximation of differential entropy in Bayesian optimal experimental design
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.00734

- PANDA: Prior-guided Attentional Dual-path Architecture
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13635

- Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12711

- REDaCT: Collapse-Free Unlearning in Large Reasoning Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12769

- ThinkNet: Evolutionary Deep Ensembles for Efficient Motor-Imagery EEG Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.33967

- MolP2SBench: Do LLMs Really Reason from Molecular Properties to Structure?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12522

- Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.22593

- Beyond State-Wise Mirror Descent: Offline Policy Optimization with Parametric Policies
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.23811

- Fast localized urban microclimate emulator: wind and temperatures in unseen urban morphologies
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2503.19708

- Why Heavy-Tailed Weight Spectra Predict Model Quality
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13123

- Studying the Effects of Task Diversity Using Small Mathematical Worlds
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13750

- Predicting Social Media Engagement using Machine Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.16082

- Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.19386

- Provenance-grouped protocol for evaluating machine learning in perovskite photovoltaics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12766

- Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13504

- Auditing Prompt Injection Defenses Before They Reach Users: What Strong Adversaries Reveal
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.15738

- Gaussian-Width Bounds for Offline-to-Online Linear Bandits
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12990

- Learning from All-Failed Groups via First-Visit Coverage in Long-Horizon Agentic Tasks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.22724

- JitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot Manipulation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13628

- ABLEIST: Intersectional Disability Bias in LLM-Generated Hiring Scenarios
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.10998

- Weight Clustering Reveals the Importance of Relative Rank in Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.17917

- Partially Informed Stochastic Optimization via Zeroth-Order Residual Tracking
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13871

- The Fourth Quadrant: A Stylized View of Benign Misfitting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.01032

- FORTE: A Production Framework for Feature Evaluation and Deprecation in Industrial Recommender Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13806

- AI Models Can Provably Hide Arbitrary Capabilities
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13928

- CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12514

- The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.05328

- Looking Ahead and Back: Anticipatory Generative Modeling for Road-Network Trajectories
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13131

- Beyond Prediction-Set Size: Quantifying Conformal Uncertainty through Credal Geometry
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.01667

- Dissecting Representation Structure in Vision Transformers: A Rigorous Architectural Study
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11205

- Primal-Dual Flow Matching for Sample-Wise Constrained Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12699

- A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.01028

- Human and LLM Facilitation in Collaborative Design Meetings: A Computational Behavioral Comparison
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13082

- Expert-level detection of low-voltage intervals in EEG as a robust biomarker of neonatal encephalopathy
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12680

- A Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13663

- Structural and Representational Agency in LLM-Driven Timbre Generation and Interpolation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12532

- Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12830

- Lower Bounds for Randomized Linear-Oracle Optimization over Strongly Convex Sets
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13590

- DASC: Decay-Aware State Compression for Hybrid Linear-Attention Serving
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.30386

- CAST: Credit Alignment for Cross-Tokenizer On-Policy Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13257

- PVBRF-ID: Private, Verifiable and Byzantine-Robust Federated Intrusion Detection for Oilfield Enterprise Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12704

- On the Encoding of Calendar Features in Covariate-Informed Time Series Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13676

- Opening the Black Box of Classifier-Free Guidance via Information Bottleneck
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13369

- Scalable Learning of Determinantal Point Processes with Kernel-Structured Interactions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12829

- JEPA-kMMVAE: CSI Prediction for Time-Varying Wireless Channels
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13315

- Measuring and Mitigating Solution Mode Collapse in RLVR
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11064

- Looking Under the Streetlight: Evaluation in Generative Molecular Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12518

- MVNN: A Measure-Valued Neural Network for Learning McKean-Vlasov Dynamics from Particle Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.00333

- DualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13767

- Spatial Context or Memory? Sizing the Inputs of Neural Surrogates for Partially Observed Fields
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12723

- MORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse Design
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13305

- Kairos: Toward a Byte-Level Foundation Model for Every Modality
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12495

- A Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13744

- UniConFlow: A Unified Constrained Flow-Matching Framework for Certified Motion Planning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.02955

- A Distributional Framework for Behavioral Characterization and Risk Management of Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12718

- PPG-Bench: A Unified Benchmark for PPG Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13435

- Verifiable Sampling for Delegated Generative Quantum Machine Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13211

- Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12703

- When Do External Priors Help Low-Resource Structured Prediction? A Ranking-Level Alignment Study
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11146

- SeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow Benchmark
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13730

- Do Prompt Optimizers Break Requirements They Are Not Scored On? A Preregistered Study
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13287

- GlucoPRISM: Protocol-Supervised Pretraining for Cross-Cohort Glucose Transfer
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12528

- Forecasting Corpus-Sampling Disagreement in Masked Text Reconstruction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12987

- CopRoute: Dependence-Aware Conformal Routing for Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13276

- Trainable Quantum-Native Language Models: Dissipative Memory, Capacity Limits, and Hardware Validation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12806

- STAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding Modules
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12599

- RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.00183

- Fly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical Feedback
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12549

- Protocol effects on feature-based hardware-Trojan detection across Trust-Hub families
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.07199

- Understanding Mamba-3 Through Oscillatory Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13341

- Multidimensional Bayesian Active Machine Learning of Working Memory Task Performance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.00375

- Hide and Seek: HIDE Concepts to SEEK explanations for black box models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13935

- Can Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level Labels
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13105

- Neurograf v1: An End-to-End Romanian-First Language Model Family
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13134

- Equality, Equity, and Causality in Fairness Research: A Commentary on Cheng (2026)
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.17679

- Benchmarking Attention for Tabular Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.31306

- asdex: Automatic Sparse Differentiation in JAX
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12336

- Work While They Sleep: Exploiting Evaluation Latency for Fully Bayesian Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.08969

- Your Discrete Graph Diffusion Model is Secretly Memorizing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13786

- Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12586

- TelcoAgent: A Scalable 5G Multi-KPM Forecasting With 3GPP-Grounded Explainability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.19821

- Diffusion Precipitation Generation with Medium-range Weather Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12976

- Decoupling the Declarative from the Procedural in Vision-Language-Action Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.21496

- PDE-PFN: Prior-Data Fitted Neural PDE Solver
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13334

- TTS-Q: Perception-Guided Post-Training Quantization of Text-to-Speech Diffusion Transformers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12474

- Golden Anchor for Video Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13217

- Data-driven Optimal Sensor Placement for Aerosol Monitoring in the UK
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12658

- Universal Bounds for Self-Normalized Kullback-Leibler Estimation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12851

- Polyconvex neural-network surrogates with learned paired directional features for anisotropic hyperelastic homogenization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12801

- RoboMME-Interference: Benchmarking Robot Memory Under Interference
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.22338

- HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.02473

- FactoryBench: Evaluating Industrial Machine Understanding
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.07675

- When Edge Independence Fails: Joint Graph Diffusion with Latent Sociability Priors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13765

- MetaJoin: Adaptive Join Selections for Heterogeneous Tables
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.02444

- Approximating Uniform Random Rotations by Two-Stage Structured Hadamard Rotations in High Dimensions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.23418

- PlacePulse: Learning Transferable Place Representations from Structural Geographic Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13390

- Dynamics as Code: On Model Compression via Dynamic System
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11115

- Infinitesimal Operator World Models: Finite-Sample Guarantees for Offline Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.10383

- Robust Langevin Sampling under State-Dependent Heavy-Tailed Noise with Applications to LLM Fine-Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12865

- Is TabPFN the Silver Bullet for Insurance Pricing?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.22892

- Not All Dimensions Are Equal: Outlier-Aware Attention Linearization with Grouped Quadratic Kernels
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13674

- FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.30376

- Deep End-to-End Survival Analysis with Temporal Consistency
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2410.06786

- Shared Canonical Component Removal Beyond Expert Views
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13819

- Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13330

- Kernel-based External Validity of Experimental Studies
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13625

- Continually Post-training Small Models via Synthetic Self-distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13113

- Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12544

- TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.07043

- Explicit Asymptotic Bounds for Sequential Calibration Beyond $T^{2/3}$
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.07623

- Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2411.02817

- KITE: A Knowledge-Injected Temporal Encoder for Time-Series Event Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12738

- Inference-Time Steering Across Scaffolds and Epitopes for Sample-Efficient De Novo Nanobody Design
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13844

- Efficient Learning of Survival Analysis Models Under Outcome-Dependent Truncation and Censoring
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12538

- GIST: Generator-state-Informed Supervision for Tabular Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12904

- Defence against the dark arts of distillation: Unsupervised discovery of subliminal learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13536

- Towards Easier-to-Tune Training Algorithms: New Results from AlgoPerf
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13036

- Scan-Parallel Variational Inference for event-driven Latent Jump Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12986

- Enhancing Tabular Learners with Context-Aware Semantic Embeddings
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.03565

- Dream to Remember: Continual Steering of Generalist Robot Policies with World Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13816

- SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13737

- Revisiting Tabular Deep Regression: Objectives and the Limits of Global Early Stopping
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13909

- Controlled-Minimax: Stabilizing Adversarial Optimization via Control Theory
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12915

- Minions: A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12970

- TabReliBench: Evaluating Tabular Foundation Models Beyond Predictive Accuracy
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13654

- Useful to Whom? The Easy-versus-Coverage Boundary Moves with the Learner
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.00221

- Coordinate-Free Automatic Differentiation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12776

- From Imbalance to Evidence: Deep Nonparametric Testing for Complex Data under Severe Sample Imbalance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12946

- Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression Proxies
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.19844

- A small cognitive core explains human behavior at scale
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13603

- Smoothing the Top-k Exposure Boundary for Sparse Mixture-of-Experts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.11575

- SpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12596

- Orthros: Phase-Aware Heterogeneous Attention for Efficient Transformers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13735

- Kronecker Product Attention: Memory-Efficient KV Compression via Structured Factorization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12657

- Differentiable Hybrid Modelling for Learning and Optimising Chemical Transport Processes from Experimental Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.04011

- A Theory of the Mechanics of Information: Generalization Through Measurement of Uncertainty (Learning is Measuring)
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.22809

- Equal-Budget Monte Carlo Tree Search versus Randomized-Restart List Scheduling for DAG Workflows: A Controlled Equal-Budget Computational Study
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12542

- VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12813

- Overcoming Data Imbalances with Expert Selection Biases
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13370

- ReSFlow: Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13225

- Simulating Training Spikes of Deep Neural Networks by Layer-wise Random Feature Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13524

- CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Bandits
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13064

- A Scalable Learned Iterative Solver for Nonlinear MPC via Temporal Decomposition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13480

- Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13693

- Constrained Triple-Head Price Optimization (C3PO) Network for Discrete-Choice Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.06941

- An Input-Dependent Readout Phase for Resonant Sequence Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12496

- Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12133

- Adaptive Variance Reduction without Knowing Oracle Smoothness
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13799

- Toward Maximizing Algebraic Connectivity via Density-Dependent Backbone Construction and Reinforcement Learning Completion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12697

- Evidential Multimodal Transformers with Dempster-Shafer Fusion for Emotion Recognition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13013

- Inverse Synthesis of Shock Time Series from Shock Response Spectra Using Ensembles of Conditional Variational Autoencoders
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12820

- Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13708

- The Predictability Bias of Joint-Embedding Predictive Learning in Medical Imaging
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13237

- A Generalizable Machine Learning Framework for Half-Heusler Thermoelectrics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.01149

- A Critical Look at Power Sampling when Test Time Sharpening LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13653

- BiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household Manipulation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.07594

- Probabilistic Multi-Agent Aircraft Landing Time Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.08281

- How Much Computation Does Every Forecast Need? Structured Block Skipping in Two Time-Series Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.13208

- UxSID: Semantic-Aware User Interests Modeling for Ultra-Long Sequence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.09040

- Locate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2610.13128

- SPARQL-LLM in the TEXT2SPARQL 2026 Challenge
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2610.13648

- Access Paths for Efficient Ordering with Large Language Models
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2509.00303

- Can Language Models Play the Wikipedia Game?
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2610.13948

- Tracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query Expansion
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2610.13810

- CRM: Retrieval Model with Controllable Condition
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2412.13844

- NEAR: Neighborhood-Aware Residuals for Memory Retrieval
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2610.13314

- PRIME: Pre-Retrieval Index Modeling Enhancement for Structured Document Retrieval-Real
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2610.13296

- RATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2610.13889

- GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2610.12617

- Democratizing MoE inference on commodity GPUs with CoMoE
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.09424

- NV-Tesseract-AD: Curriculum-Enhanced Conditional Diffusion for Multivariate Time-Series Anomaly Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12754

- Beyond Second-Order Information: Paid Logistic Regression with Noisy Features
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2610.12919

- LLM4Trust: Exploring the Capabilities of Large Language Models for Trust Evaluation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.33521

- Web$hell: A Unified Interface for Agentic Web Access
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2610.13416

- Imagine Before Acting: Prospective Skill Identification for LLM Agents
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.01642

- Claim-Gated Source-Risk Auditing for Generative Search
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.29145

- Beyond the Final Embedding: Retrieving Memories from Token-Level Evidence
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2610.13277