TILens Daily Edition 2026-11-16 Filters: topic=ai-research, github=hidden Stats: 537 articles, 7 sources, 533 research papers Top topics: AI Research, AI, Information Retrieval ## News - 😺 Nvidia reportedly supplied China via Asia Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/newsletter/nvidia-reportedly-supplied-china-via-asia/ - ChatGPT Can Now Buy Things for You. Here's What Happens If a Purchase Goes Wrong. Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/news/chatgpt-wallet-purchase-goes-wrong/ - Everything That Happened in AI Today (Monday, November 16, 2026) Source: the-neuron-ai Topic: AI (+AI Research) URL: https://www.theneuron.ai/digest/everything-that-happened-in-ai-today-monday-november-16-2026/ - AI Weekly Issue #544: AI is now the most-cited risk in the Fed's survey: 87%, up from 50% Source: ai-weekly Topic: AI (+AI Research) URL: https://aiweekly.co/issues/ai-is-now-the-most-cited-risk-in-the-feds-survey-87-up-from ## Research - After 10 Heads in a Row, Small LLMs Bet Up to 82% on an 11th Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/after-10-heads-in-a-row-small-llms-bet-up-to-82-on-an-11th/ - Why Human in the Loop AI Oversight Fails and How to Fix It Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/why-human-in-the-loop-ai-oversight-fails-and-how-to-fix-it/ - How to Avoid AI Replacement as an Analytics Professional in 2027 Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/how-to-avoid-ai-replacement-as-an-analytics-professional-in-2027/ - Local LLMs Handle Textbook RAG but Fail on New Research Papers Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/local-llms-handle-textbook-rag-but-fail-on-new-research-papers/ - Do Mixture-of-Experts Routers Benefit from Ensembling? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17472 - Manifold Approximation leads to Robust Kernel Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.22953 - Fuse-All MoE Inference Kernel with Load Balancing on TPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17857 - Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18409 - Bayesian Transfer Operators in Reproducing Kernel Hilbert Spaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.22482 - WETW: Learning Pair-Specific Weighted Euclidean Distances for Efficient DTW Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17412 - Black-Box Uncertainty Quantification for Large Language Models via Ensemble-of-Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18453 - An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03301 - SA-RAG: Structuring Noisy Conversations for Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24366 - Compiling Specialized GPU-Initiated Networking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18145 - Score-based neural ordinary differential equations for reaction-diffusions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18467 - Adversarially Batched Online Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17500 - Provable Cross-Modal Transfer of Hierarchical Concept Structure in CLIP Embeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17671 - Binarization as an Attack Surface in Weightless Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17646 - When Adaptation Fails: A Gradient-Based Diagnosis of Collapsed Gating in Vision-Language Prompt Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09549 - Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07239 - Identifying Latent Neural Dynamics with Recognition-Parametrised Gaussian Process Dynamical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17487 - BAL: Bidirectional Autoregression in Latent Space for Learning Human Movement Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18559 - Improved Regret via Variance-Aware Policy Optimization in Adversarial MDPs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17469 - Tracing 3D Anatomy in 2D Strokes: Can Projection-Derived Masks Replace 3D Segmentation for Cervical Spine Fracture Recognition? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15235 - Disentangling Forgetting from Utility: Lightweight LLM Unlearning via Orthogonal Null-Space Projection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17864 - Self-Supervised Learning for Robust Resonance Mass Regression in Cascade Decays Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17726 - Online Switching Control as Learning with Experts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18352 - Detection and Classification in Latent Spaces: High-Dimensional Analysis and Validation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18164 - Pruning Extensions and Efficiency Trade-Offs for Sustainable Time Series Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07953 - The Polyak-{\L}ojasiewicz Paper: A 10-Year Retrospective Source: arxiv-cs-lg Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.17745 - Analyzing Learning-Dynamics Across Loss and Prediction Choices for Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17967 - Direction or Magnitude? Learning Scalars over Task-Calibrated Directions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17784 - On numerical issues of divergences between nearly equal distributions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18511 - Learn then Bet: Learning Interpretable Rules for Reliable Agent Intervention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17662 - Training-point consistency of kernel ridge regression with varying correlation scales Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18095 - DRTriton: Large-Scale Synthetic Data Driven Reinforcement Learning for Triton Kernel Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21465 - Training Reasoning Models in Simulation to Natively Use Real Robots Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18562 - Monroe: A Molecular Foundation Model for In-Context Probabilistic Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18982 - Before Words, Beyond Speech: Evaluating Nonverbal Social Reasoning in Early Childhood Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13213 - Reasoning Models Confabulate to Defend Injected Beliefs About Their Own Requests Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17958 - AutoRL: A Multi-Agent System towards Autonomous Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17790 - A Convex-Analytic Reformulation for Poisoning Attacks on Logistic Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17143 - CoPre-MoE: Consolidating and Preserving MoE for Multimodal Continual Instruction Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18417 - Muon Attains $\mathcal{O}(\varepsilon^{-3})$ Iteration Complexity under Shuffling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18124 - ArchSpace: Recording, Reviewing, and Referencing LLM Architecture Research Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17332 - WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17955 - From Chats to Markets: AgenticPay for LLM-Powered Negotiation in Multi-Agent Commerce Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06008 - Finite speed Ornstein-Uhlenbeck-Kac processes and their applications in generative modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17625 - TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22355 - Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.24195 - LACCO: Local Accumulation with Computation--Communication Overlap Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17991 - Adaptive Calibration in Non-Stationary Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11490 - PF-Exec: Large-Scale UAV Relay Load Balancing with an Anchored Potential Direction Decider and a Per-Dimension Gain-Learning Executor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17492 - What Should World Models Forget? Stratified Retention for Continual Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.03713 - Elliptic Sampling: Optimal Interpolant Schedules for Gaussians and Beyond Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18542 - JudgeMix: Judge-Guided Mixed-Rollout Data Synthesis for LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16174 - Profile-Based Auditing of Domestic Violence Survey Selection Across South Asia Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15106 - Structure makes quantum circuits trainable Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18378 - RiverScan: Learning to Accumulate on River Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18005 - Tractable Importance Sampling for Monte Carlo Privacy Accounting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17596 - Agentic-OPD: Recovering Forgotten Agent Capabilities via On-Policy Distillation for Agentic Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12799 - URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04688 - Watch Your Step: Adam's Margin Maximization Bias Depends on the Learning Rate Schedule Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.01929 - Express Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10944 - Disentangling Continuous-Time Latent Dynamics: Identifiability of Latent SDEs via Diffusion Shifts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.28228 - Learning Anisotropic Prediction Targets for Flow Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17767 - STAMP: Manufacturing-Informed Generative Design and Shape Optimization of Sheet Panels Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18144 - When Does Oversampling Help? A Decision Framework for Imbalanced Data Streams Under Label Delay and Concept Drift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17981 - Neural Simulation-Based Inference for Computational Cognitive Models: A Tutorial Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17608 - Toric geometry of ReLU neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.05894 - Conformal Risk Control for QoT-Aware Lightpath Feasibility Under Technology-Driven Domain Shift Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13893 - Interactive Program Induction with Language Model Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18485 - Creating Steering Vectors via Input Optimisation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17481 - Larch: Learned Query Optimization for Semantic Predicates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07923 - Auto-differentiable data assimilation: Co-learning of states, dynamics, and filtering algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.20891 - Contrastive local learning in large nonlinear analog circuits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17561 - A systematic comparison of physics-informed neural networks and mechanistic models for epidemic modeling and forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18389 - ReCo: When to Relocate Sensor Kits under Deployment Constraints -- A NILM Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35075 - Joint World Action Models through Differentiable Trajectory Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17626 - Wavelet Flow Matching for Multi-Scale Physics Emulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16573 - Time series causal discovery with variable lags Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04081 - Brain2Vec: A Self-Supervised 3D Foundation Model for Structural Brain MRI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.28411 - Convergence Properties of PF-Exec: Homogeneous Structure, Anchored Closed Form, and Gain Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17488 - Minimizing classical resources in variational measurement-based quantum computation for generative modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.11578 - Differentially Private Federated Class-Incremental Learning for EEG Mental State Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17944 - Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.04954 - Multifidelity Operator Inference for Dynamical Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17503 - Where Tree Ensembles Decide: Structural Local Explanation with Decision Predicate Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18382 - AMUSE: Anytime Muon with Stable Gradient Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22432 - LaMe: a Joint Latent Mediation Framework for High-Dimensional Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18180 - Right Token, Right Time: From Per-Token Gating to Trajectory-Aware Activation Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18274 - Efficient Poincar\'e Convolutions through Patch-Statistics Factorization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18125 - on\'ona: Twin Embeddings with Tied Unembeddings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10556 - From Local Prediction Error to Final Outputs: A Theory of Expert Sharing in Multi-Step Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17879 - Similarity Pairing with Energy Mover's Distance for Self-Supervised Pre-Training at the LHC Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.17738 - Quantum Graph Neural Networks: Architectures, Trainability, and Applications Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17886 - Mode Dynamics: A Framework for Neural Network Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40143 - Vision-language models lag human performance on physical dynamics and intent reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.01547 - 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 - When a Flatness Proxy Is Not a Function: Robustness Certificates and Training Interventions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38540 - Sample-Efficient Control of Magnetoconvective Flows via Differentiable Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18008 - Why Finite Intelligence Works in an Infinite World: A Mathematical Theory Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18538 - WeightBench: Evaluating Language Models as Weight-Space Programmers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18553 - Vision-Language-Action Models: A Life-Cycle Survey of Design, Training and Deployment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18372 - Benchmarks Don't Talk Back: Learning Through Self-Disagreement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17563 - Graph Your Own Prompt Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.23373 - Model-Free Assessment of Simulator Fidelity via Quantile Curves Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.05024 - FlashSampling: Fast and Memory-Efficient Exact Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.15854 - Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age Biomarkers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.07729 - PATTERN Can Be Solved from Memory: Testing Graph Neural Networks on Unseen Patterns Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15020 - A Generalizable Approach to Safety-Aware Robotic Behavior Planning with an Explicit Constraint Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18026 - Who Pays for the Knowledge Models Copy? Model Collapse as Lossy Transmission and Rogers' Paradox Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.06022 - Neural Classifiers as Error-Correcting Codes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18239 - Denoising the US Census: Succinct Block Hierarchical Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10099 - CastWorld: Benchmarking Context-Aware Agentic Time Series Forecasting Beyond Predictive Accuracy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15262 - Hierarchical Bayesian physics-augmented neural networks for populations of hyperelastic laws: specimen variability and uncertainty from scarce, noisy data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17892 - Contrastive latent representation learning with denoising score matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18469 - LightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17600 - Resolving AdaBoost Cycling with LLMs: A Computer-Assisted Counterexample Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.07055 - Which Model, For Which Variable? Per-Variable Forecast Combination in Sparse ICU Time Series Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18149 - ESENSC: A Polynomial-Time Axiomatic Alternative to SHAP Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00496 - Beyond Embedding Transfer: Architectural Interfaces, Iso-Parameter Scaling, and Preconditioner-Governed Consolidation in Grokking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.18078 - HetCCL: Efficient LLM Training on Heterogeneous Vendor GPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22585 - The State Is Not the Bottleneck: A Paged-State Gated-DeltaNet Tile on a Tri-Mode Multicast Mesh, Bit-Exact from RTL to Silicon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18422 - Classification with Large-Step Gradient Descent: Unifying Self-Stabilization and Convergence Rates Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17459 - The Alignment Illusion in Multimodal Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30210 - JaRS: Contrast-Free Localization of Memorized Regions in Diffusion Models via Jacobian Row Sums Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18024 - Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.02792 - MarathonTS: a benchmark of long synthetic time series from window assembly and long-series generators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18190 - FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18561 - 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 - Federated Physics-Informed Thermal Field Prediction Across Unseen Geometries in Distributed Additive Manufacturing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17794 - Simultaneous Learning and Optimization via Misspecified Saddle Point Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.05241 - Hybrid Quantum-Classical Sequence Models for Sample-Efficient Energy Regression in Simulated Calorimeter Showers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17354 - Local Spike Timing Enables Gradient-based Learning in Neural Microcircuits Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.08070 - Understanding Contextual Bias in Agricultural CNNs Through Hidden-Neuron Concept Induction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18530 - Cross-Benchmark Transfer from RL on Agentic Coding Tasks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.00890 - mlr3torch: A Deep Learning Framework in R based on mlr3 and torch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.18152 - Delayed Effects of Temporary Weight Decay in Muon Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17876 - Enrichment-Oriented Virtual Screening of Perovskite Solar Cells through Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18043 - More Agents, More Samples, or More Thinking? Untangling Coordination, Ensembling, and Test-Time Compute in Multi-Agent LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17610 - Efficient and Practical Clustering of Variables in Causal Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17971 - Learning nonlinear interactions and cross-feature couplings with product-unit residual networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18074 - UltraBench 2: Towards Robust Evaluation of Vision Foundation Models on Ultrasound Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.28610 - Emulating physics-based XCO2 retrievals across OCO-2 viewing modes with compact neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18333 - Hidden not Deleted: How Networks Suppress Entangled Features Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.27593 - Shortcut Mitigation via Spurious-Positive Samples Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13340 - NeoResearch: Literature- and Experience-Guided Autonomous Time Series Model Discovery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18235 - Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19095 - When Copying Is Hard to Beat: A Negative Result in Clinical Assessment Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18142 - A thorough review on Deep Learning approaches to 2D-to-3D Registration in Medical Imaging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17468 - Training Language Model Agents to Find Vulnerabilities with CTF-Dojo Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.18370 - ForeSpark: Joint Draft and Verification Budget Scheduling for Parallel Speculative Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13442 - Can LLMs Write Backdoors? An Empirical Security Study of Weight-Space Programming Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17395 - Graph diffusion transformer for interpretable generation and inverse design of disordered atomic structures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18420 - Diffusion Tree Sampling for Inference Time Adaptation of Crystal Generative Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17462 - AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.12358 - Efficiently Aligning Draft Models via Parameter- and Data-Efficient Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09527 - ERGo: Energy-Efficient Hybrid Graph Neural Network Training on Processing-In-Memory Architectures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17478 - LEGAL-UQA: Testing Constitutional Question-Answering Systems for Urdu Speakers with a Parallel English-Urdu Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.13013 - RaFL: An Empirical Study of Random Filter Losses for Image Reconstruction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17707 - Mapping Seven Decades of Philosophy in Colombia: Dynamic Topic Modelling of Ideas y Valores Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2412.04236 - Domain Adaptation Based Pipeline for Character Classification and Handwritten Text Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17952 - Explanations that Transfer: Interpreting Medical Retrieval with Sparse AutoEncoders Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.18179 - Offline KL-Regularized Reinforcement Learning with Stochastic Transitions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17603 - Deep Latents, Long Memory: Latent persistence explains temporal correlations in transformer activations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18089 - Learning Latent Goal Costs for Visual World-Model Planning with an Expanding Curriculum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17529 - LLM-Guided Cluster Lifecycle Management: Deciding When and How to Evolve Behavioral Clusters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17616 - Stealthy, High-Impact False Data Injection Attacks in Smart Grid Using Physics-Constrained GAN with Limited System Knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15162 - DECODE: Decomposable Environments for COntrolled Sequential-Decision Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18367 - Cyber-Zero: Training Cybersecurity Agents without Runtime Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.00910 - PACT: A Decoder-Confidence-Guided Two-Round Receiver for Joint Channel and Phase-Noise Estimation in Sub-THz OFDM Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18450 - Pairing AIS with RF: Analysis of a Markovian Approach for Maritime Data Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18563 - The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02557 - Retrieval of Coastal Biogeochemical Parameters From Near-Surface Hyperspectral Remote Sensing Reflectance Using Physics-Aware Meta-Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.05623 - Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.18934 - Deep Neural Networks Training Efficiency: Does Grokking Modify its Dynamics? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18396 - Fusion-Free Multimodal Classification with Heterogeneous Deep Ensembles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05019 - Benchmarking AI risk behaviors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16318 - High-Dimensional Online Calibration from Harmonic Weights Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07740 - Time Flies When You Parallelise: Pareto-efficient Time Series Foundation Models with Linear Recurrences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16934 - Rectified Looped Transformer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16265 - GigaEdge Spench: An SDK for Practical Streaming Speech Enhancement Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13243 - Alignment with Reflect-Reasoning: Learning How To Follow Principles Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17398 - Diagnosing and Mitigating Domain Shift in Permission-Based Android Malware Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09028 - Learning Task-Specific Antibody Representations via Function-Aware Masking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.00518 - AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17621 - Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18020 - Evaluating Feedback-Driven Black-Box Processes via Stochastic Modeling and Simulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18477 - On sparsity, extremal structure, and monotonicity properties of Wasserstein and Gromov-Wasserstein optimal transport plans Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16265 - On the Limits of Sufficient Explanations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18163 - Improving Matrix Exponential for Generative AI Flows: A Taylor-Based Approach Beyond Paterson--Stockmeyer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.20777 - Generative Design with Real-time Physics Explainability: Towards Product Definition in the Age of AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17560 - Protection-Oriented Assessment of Machine Learning-Based Fault Detection in Power Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17872 - LuthorSQL: A One-Pass Text-to-SQL Model as System 1 for a Slower LLM Agent Source: arxiv-cs-lg Topic: AI Research (+AI, PostgreSQL) URL: https://arxiv.org/abs/2611.17780 - Logically Consistent Accurate Forecasts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17735 - Beyond Bot Labels: Retrospective Consequence-Grounded Ranking of Attributed Cache Harm in E-Commerce Logs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18027 - Complex Schr\"odinger Bridges Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17746 - Unsupervised Anomaly Detection in Measured Neutron Flux Profiles of the SAFARI-1 Research Reactor Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17351 - Process Mining-Enabled Federated Anomaly Detection for the Industrial IoT Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17869 - Clean Tickets, Wrong Orders: Catching Silent Errors with a Language Model in Your Browser Tab Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18284 - Asymptotic Margins and Feature Confinement in Conic Classification Heads under Softmax Cross-Entropy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18507 - Continuous Cuffless Blood Pressure Estimation Using PPG From Methods to Clinical Translation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17499 - Evidence-Guided Neural Architecture Selection under Uncertainty for Subject-Specific Blood Glucose Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05373 - Pattern-Based Matrix Analysis Under Permutations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17674 - ModHarness-RL: Recasting Harnesses as Learnable and Evolving Programs for Agentic RL Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18533 - Adaptive Power Iteration Method for Differentially Private PCA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11454 - E0: Expressive Fine-Grained Discrete Action Prediction for Vision-Language-Action Models via Tweedie Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.21542 - Kernel-based potential mean-field games with unbiased random Fourier $U$-statistics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29371 - Trajectory Density Ratios under Weak Support: A Survey across the Sciences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11985 - Lipschitz-Constrained Discriminators in Generative Modeling: Asymptotic Behavior and Support Mismatch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18394 - Representational Geometry as a Diagnostic for Adversarial Robustness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17684 - BoostLoRA: Growing Effective Rank by Boosting Adapters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.27308 - Electrocardiographic Imaging via Posterior Sampling under Operator Discrepancy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17851 - TIDE: Reclaiming Lost Performance In On-Policy Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17924 - RL$^{\mathrm{RT}}$: On-Device Reinforcement Learning Runtime Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18035 - PRISM: A Post-Prediction Reliability Framework for Evidence-Guided Correction and Selective Abstention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18127 - An Operationalization of Opaque Serial Depth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17495 - DeltaVisionX: A Low-Cost Vision-Guided Automation System Using YOLOv11 and PLC-Based Actuation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17959 - LazyWeights: Decode-on-Demand Edge LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17108 - Availability-Aware Historical Feedback Learning for Electric Arc Furnace Temperature and Chemical Composition Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17463 - BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.02612 - QVal: Evaluating Dense Supervision Signals for Long-Horizon LLM Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.32034 - Efficient Genotype Classification from 3D MRI in ADPKD via Density-Aware Point Sampling and E(3)-invariance Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17758 - A Synthetic Benchmark for Target-Centric Causal Discovery in Industrial Processes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17556 - Sample-efficient prediction of high-entropy alloy strength through outcome-aware robust sequential learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18462 - Bregman geometry in regular exponential families: dual representations and relative smoothness Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18480 - Flow Matching from Viewpoint of Proximal Operators Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12683 - FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05546 - SURFACE: Preference Distribution Matching on Pareto Fronts via Scalarization Steering Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17484 - Imitation Policies Learn a Proprioceptive Anchor: A Predictive Law for Perception Noise and Its Closed Loop Cost Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17658 - An Invariant Neural-Network Eddy-Viscosity Closure with Iterative Solver Coupling for Molten Salt Fast Reactor Thermal-Hydraulics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17067 - A mesh-free deep energy method for phase-field modeling of thermally driven brittle fracture Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17630 - How Much Is Left Matters: False Positives and False Negatives in Partial-Prompt Contamination Tests Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10307 - f-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18370 - Parameterization method of reservoir properties for ensemble-based data assimilation using intermediate latent space of StyleGAN Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.39626 - Lightweight Semantic EEG Foundation Model for Frozen Cross-Disorder Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.05503 - Learning to Read Out: Unembedding Dynamics in Language Model Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.21025 - Robust Surrogate Modeling for Explainable Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.01925 - From Data to Program: Fast & Direct Generative Program Inference from Empirical Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35348 - Small Is Not Dead: Distance-Aware Cluster Revival for e-means Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18238 - NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.05844 - Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02771 - Waveform-based pulse timing enhanced by self-supervised neural regression models for digital nuclear instrumentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17356 - EmbodiExp: Compositional Experience Transfer for Embodied Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.39180 - Causal-prior-constrained deep learning for rapid-intensification warning of western North Pacific tropical cyclones Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.40304 - ROCKET: Rapid Optimization via Calibration-guided Knapsack Enhanced Truncation for Efficient Model Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.11008 - Antidistillation is Cheap: Lightweight Distillation-Resistance via Stylistic Corruption Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17772 - Robust Long-Tailed Learning under Label Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2108.11569 - Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29788 - WeatherDreamer: Learning a World Model from Multimodal Earth Observations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18393 - Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.11294 - StreamEmbed: Real-Time Indexing from Pixels for Screenshot Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18516 - When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29617 - Performance-Portable Exact Gaussian Process Regression in Python via SYCL and oneMath Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17565 - Beyond a Single Sign: BiTE for Branch-Preserving Binary Threshold Expansion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17576 - LEGIT: Live Eligibility Gating over Identifier Tries for Constrained Decoding of Heterogeneous Pages Source: arxiv-cs-lg Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.10357 - Input Pathways Shape Few-Shot, Not Zero-Shot, Binding in Tiny Transformers: A Fully-Enumerable Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.04926 - Beyond Prediction Gain: LASR as a Metric for Action-Grounded Latents in World Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17775 - Conflict, Feasibility, Faithfulness, Displacement: Four Quantities That Come Apart in Federated Dual-Cone Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18014 - Adaptable Watermarking: Transforming Image Watermarking Models via Lightweight Adapters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18363 - Unfinished-Bench: Measuring Rule Violations by Persistent Agents in Realistic Work Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17460 - Similar Predictive Fit but Different Latent Dynamics: Characterizing Learned Dynamical Structure in Personalized Models of Brain Disorders Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10850 - Condensing Law of Security Information Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17918 - Adversarial Attacks on Downstream Weather Forecasting Models: Application to Tropical Cyclone Trajectory Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.10140 - Interpret Policies in Deep Reinforcement Learning using SILVER with RL-Guided Labeling: A Model-level Approach to High-dimensional and Multi-action Environments Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.19244 - Bias-Optimal Bounds for Stochastic Gradient Descent Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.17965 - Benign Overfitting for Regression with Trained Two-Layer ReLU Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2410.06191 - User-Schedulable Approximations for Quantized Tensor Programs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17526 - CS-54k: A Paper-Grounded Corpus and Benchmark for AI Research QA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.20279 - Detection Is Not Early Warning: Evaluating Token-Level Alarms on Language Model Failures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16803 - Uncertainty-Aware Continual Learning for 2D XRD Interpretation Using Simulated and Experimental Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17547 - Product units in gated recurrent networks enhance prediction of nuclear masses and charge radii Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18066 - Interpreting Coding Agents Through Their Behavioral Trajectories Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17440 - Model Annealing: Data-Efficient Learning through Review and Consolidation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17524 - Multimodal Person Concept Model for Person Identification under Varying Observation Conditions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17802 - Classifier-Guided Latent Diffusion for Small-Molecule Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17650 - Generative sequence modeling for infinite memory processes via predictive states Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38524 - Deep Multivariate Models with Parametric Conditionals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.01953 - Choosing Quantized Code LLMs by File Size and Energy per Solved Task Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17605 - Algorithmic Opacity as a Principal-Agent Problem Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17980 - A Horizon-Specific Attribute-Conditioned Neural Network for Estimating Health-State Transition Probabilities in Irregular Longitudinal Data: The LANTERN Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.13880 - Stochastic Projections and Rank-Aware Learning Rates for Federated LoRA Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13331 - Curvature-Aware Edge Dynamic GNNs for Low-$p_T$ Track Reconstruction at HL-LHC Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17343 - Fair and Efficient Distributed EV Charging Coordination Using Threshold Cryptography and Machine Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17577 - Activation Steering the Nan-Shan in Typhoon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17768 - Callo: Serving Cache-Miss Requests with Speculative Decoding on Invalidated KV under Prefill-Decode Disaggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18459 - ParetoM$^3$: Learning on the Pareto Set under Preference Guidance via Min-Max-Min Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18252 - Generative machine learning for protein design Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.26378 - Recovering the Euclidean Geometry of High-Dimensional Data Under Heterogeneous Noise Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.18520 - MMAO-Cls: Metabolic Multi-Agent Optimization for Joint Feature Selection and Classifier Tuning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.01539 - Enumerating Posterior-Supported Priors: First-Order Error of Finite-Integral Cross-Categorical Measurement Morphisms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17390 - T2ST: Data-Efficient Spatio-Temporal Foundation Models via Temporal Data and Knowledge Transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18199 - Racing the Clock: Teaching VLNs Budget-Conditioned Object Search Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17442 - HARDTESTGEN: A High-Quality RL Verifier Generation Pipeline for LLM Algorithmic Coding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.24098 - RecMem: Recurrent Memory Compression for Long-Sequence Generative Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.17921 - Who Counts as Exposed? Measurement Choices in an Open, Re-estimable Index of Occupational AI Exposure Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.18168 - Prompt-Based Abstention Fails Under Misleading Context: A Controlled Study of Small Frozen RAG Models Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2608.22228 - RACE: Ranking-Uncertainty Aware Capacity-Adaptive Customization for Efficient Sequential Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.18244 - CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2604.14586 - Federated User Behavior Modeling for Privacy-Preserving LLM Recommendation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2604.14833 - MeReader: An Offline, Privacy-Preserving, Progress-Aware AI Assistant for Narrative eBook Reading Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.18513 - Towards High-Performance Multimodal Discovery: Evaluating Retrieval Efficacy and Operational Scalability in Digital Libraries Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.17726 - Federated Vector Retrieval across Heterogeneous VectorDBs Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2611.01514 - Evaluating Chain-of-Thought Reasoning through Reusability and Verifiability Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2602.17544 - ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation Source: arxiv-cs-ir Topic: Information Retrieval (+AI, AI Research) URL: https://arxiv.org/abs/2602.15189 - Fake News Detectors are Biased against Texts Generated by Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2309.08674 - What LLM Agents See and What Users Say Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17639 - AI-Voyager: A Public-Interest System for Human-AI Civic Reasoning to Contest and Shape the Rules That Govern AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17564 - In the Eye of the Beholder: Human Label Variation in Textual and Visual Entailment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17954 - Learning Word-Level Explanations of Text Reuse in Latin Literature with Little Annotation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18319 - AI Reviews Are Biased Towards the Appendix Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17811 - Is Abliteration Getting Harder? Not Uniformly: Refusal Removal by Direction-Based Ablation and ARA in Heretic on the Qwen3.8, Gemma 4, Olmo 3.1 and Mistral Small 3.2 LLMs Versus Their Predecessors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17846 - Comparing Human and Automatic Recognition of Dutch Dysarthric Continuous Speech: A Case Study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.30237 - Investigating LLM Capabilities on Long Context Comprehension for Clinical Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.18691 - BigCodeArena: Unveiling More Reliable Human Preferences in Code Generation via Execution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.08697 - Poetry 'resurrection' from LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17464 - AmbiSteer: Selectively Eliciting Ambiguity-Aware Responses in Vision-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17900 - Folding Language Models into Themselves Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18113 - G-CAST: Governed Continual Self-Training for E-Commerce Agents under Evolving Demands Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17814 - When Simpler Is Better: Evaluating Translation Pipelines for Medieval Latin Manuscripts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03836 - AttentionSwitch: Jailbreak Defense for LLMs via Joint Learning of Sparse Attention-Head Selection and Scaling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08752 - Evaluating Human Sensitivity to Gender Biased AI-Generated Content through Human Assessment of Google's Autocomplete Function Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18371 - On Robustness of Prompt-based Semantic Parsing with Large Pre-trained Language Model: An Empirical Study on Codex Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2301.12868 - Agent-as-a-Judge Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18067 - SPECMEM: Accelerating Agentic Tool Calling via Live Memory Management Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.31840 - Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17939 - Tracing Knowledge and Reasoning in LLM Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17461 - Contagious Fingerprints: When LLMs Inherit Another Model's Identity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18104 - Agentic induction of common data elements and information extraction from sarcoma case report abstracts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18506 - PerfArena: Ranking LLMs by Code Performance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18030 - VEPO: Mitigating Multilingual Hallucinations in LVLMs via Visual Evidence-guided Preference Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18096 - Beyond Trajectory Similarity: Evaluating Surgical Planning by Protocol Adherence Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.10455 - Marimba: A System One Model for Speech Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18330 - Small Open-Weight Language Models for Crowd Decision-Making: Capabilities and Limits of Output-Level Fusion and Linguistic Aggregation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17589 - Superfluid: Local AI Server for Distributed LLM Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17753 - CamSpokenNLI: A Pilot Resource for Cross-Variety Transfer Evaluation in Cameroon Pidgin English and Camfranglais Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17573 - From Reading Code to Reading Spec: A Verified Layer for LLM-Driven Codebase Maintenance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.06383 - A Push Down the Mountain: Framing Effects and Internal State Interventions on Collusive Behavior in a Long-Horizon LLM Agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17515 - RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16411 - Inject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-Correction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.13672 - Rethinking Round-Trip Translation for Machine Translation Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2209.07351 - CarryOn: Learning What to Keep in Context for Long-Horizon LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17808 - Envisioning Agentic Robotics: A New Era of Robotic Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18359 - What Do Multilingual Self-Supervised Speech Encoders Know About Sentence Meaning? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17686 - BLiMP-RO: A Benchmark of Linguistic Minimal Pairs for Romanian Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17836 - All Quiet on the Neural Front: Language Models Do Not Report Injected Pain States Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10123 - SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.21965 - Beyond Gold Standards: Epistemic Ensemble of LLM Judges for Formal Mathematical Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.10903 - Integrate the Reward, Don't Sample It: Window Likelihood for Interruptions and Backchannels in Full-Duplex Speech Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35581 - GDP.xlsx: Benchmarking Frontier Models on Professional Workbooks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17766 - See Every Block Once: Variance-Reduced Post-Training for Masked Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17754 - Some complete $\omega$-powers of a one-counter language in the difference hierarchy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16473 - RAG-FGO: Dynamic Optimization of Query-Rewriting Agents for Generative RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17788 - Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14397 - ABHBench: Evaluating Moral Decision-Making of Foundation Models from an Agentic Perspective Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.09326 - Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18397 - MineralExp: Benchmarking LLM Agents for Experimental Design in Real-World Mineral Exploration Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17931 - Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18514 - UltraBERT-JEV: Encoder models for System One Applications Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17867 - HackWorld: Evaluating Computer-Use Agents on Exploiting Web Application Vulnerabilities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12200 - BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.15877 - Do Verifier Judgments Survive Abstraction? Measuring Verification Transport for LLM Agent Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18471 - NER-D: A cross-domain benchmark for German NER Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18257 - Pluralistic Alignment in Large Language Models: Objectives, Human References, and Preference Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24471 - Deletion Sensitivity Is a Property of the Model: A Three-Condition Measurement over 72 Valid Experimental Cells Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13223 - Screen Before You Interpret: A Portable Validity Screen for Benchmark-Based LLM Confidence Signals Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17714 - FEND: Far-End Detection in Outbound Voice AI Calls Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18050 - Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2401.00788 - From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25693 - A Multi-Layered AI Pipeline for BPMN Generation from Natural Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18157 - PaperCritic: Training AI Reviewers to Assess the Soundness of Papers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17834 - When evaluation becomes intervention in clinical AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18297 - Toward Universal Translatability: On the Statistical Ontology of Generative AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17963 - GT-FENG: General Theory of Factual Evaluation and Normative Grounding in Language Models *Author(s) Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18279 - Indic-Task Gains and Regressions after Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16228 - Characterizing Treatment-Context Medication Evidence Across Clinic Notes and Structured EHR Medication History Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01570 - Securing Multi-Agent Systems by Design Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17883 - LitArc-Bench: Disentangling Text-Specific Reader-Response Dynamics from Position and Lexical Affect Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18412 - Chinese Decision: A Family of Language Models for Single-Pass Probabilistic Decision-Making Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23170 - From Survey Histories to Interpretable Digital Twins: Auto-Discovering Task-Specific Personas and Behavioral Mechanisms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20344 - WaferTetris: Efficient Freeform Mapping on Wafer-Scale Accelerators Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18527 - MamaReason: Unfinished Reasoning and Answer Recovery in Clinical Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18264 - Rethinking Visual Reasoning in Text-to-Image Reward Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17585 - Does the Ranking Hold? A Practitioner-Facing Audit of Hallucination Detectors on Small, Quantized, On-Device LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17339 - Creative Product Design under Brand Image Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17762 - Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM Planners Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17910 - Self-Building Labs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.23826 - Tracing Actual Causes with Counterfactual Witness Maps Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17937 - FlexCast: Flexible Context Learning for Time Series Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17862 - Verifiable pXRD: Hill-climbing pXRD structure determination with LLM agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17539 - Interpretable weight-space programming builds transparent transformers and brain encoding models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18114 - When to Trust Simulated Patient Responses:Support-Gated World Models for Vasopressor Decision Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18458 - Causal AI-Driven Secure mmWave Beam Alignment with Defensive Variational Autoencoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18321 - Agentic AI for Discovering Fault-Tolerant Quantum Circuits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18504 - Comparative Analysis of 3D Convolutional and 2.5D Slice-Conditioned U-Net Architectures for MRI Super-Resolution via Elucidated Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.14667 - Use-case-driven ontology modeling with the NeOn methodology for ambient assisted living Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17466 - Cross-Linguistic Acoustic Biomarkers of Cognitive Impairment Across Interactive and Single-Speaker Speech Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17710 - MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37670 - Tracing Uncertainties of Extreme El Ni\~{n}o Prediction to Mesoscale Ocean Currents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17854 - When Cooperation Must Change: Semantic Strategy Unlearning in Multi-Agent Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17917 - Between Obligations and Evidence: A Participatory Study of Translating the EU AI Act into Technical Requirements Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18439 - Large Language Model-Empowered Intelligent Agent for Adaptive Fast-Charging Control of Lithium-Ion Batteries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18140 - Robustness Evaluation of GPU Cloud Pricing Benchmarks under Incomplete Observations: A Controlled Missingness Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17796 - TransGHOST: Real-Time, Synthesis-Free Reconstruction of Instrument-Occluded Regions in Ophthalmic Microsurgery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13971 - ISLA: Ensemble learning and domain adaptation for generalizable acute ischemic stroke lesion segmentation in diffusion MRI with clinical validation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.08732 - TotalSegmentator Aorta Report: Automated Aortic Diameter Measurement at 11 Standardized Landmarks on CT Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17968 - Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.08269 - ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.06740 - Do Machines Learn Deviance From Their Peers? A Randomized Test of Differential Association With AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18098 - Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.09159 - A Spectral Framework for Universal Proxy Regularization in Model Merging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17728 - Function-Preserving Audits of Visual Weight Readers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05798 - AutoManifold: Agentic Design of Data Visualisation Algorithms via Manifold Embedding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13710 - CARE-Drive: Coupled Alternating Refinement for Ego-trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15360 - Ballad: Bandit-Based LLM Routing for Automated Heuristic Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17241 - Only as Safe as the Weakest Agent: A Break That Appears Only When the System Is Multi-Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17520 - V-JEPA-LM: Video-Language Models That Read Dynamics Beyond Static, Text-Aligned Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17831 - Measured from the feed: the unsustainable growth of AI video generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17938 - Knowledge After Collapse: Context and Wording Shape Factual Accessibility in Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17763 - AI Agents Push Humans Out of the Loop Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23642 - JFinBench: A Continuously Refreshable Japanese Financial Benchmark from the Latest Certification Exams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18130 - Vision-as-a-Tool: Visual Harness for Multimodal Agentic Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17797 - An In-Silico Audit of Topographic Organization in a Multimodal Brain-Response Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18105 - Safety Side Effects of Preventative Persona Steering: An Empirical Audit Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17620 - When Does Less Information Pay? An Exact Finite Atlas of Representation, Payoff, and Cost Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17583 - REFORGE: A Method for Benchmarking LLMs' Reverse Engineering Capabilities in Decompiled Binary Function Naming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07738 - Towards Explainable Sleep Stage Classification using Single-Channel Electroencephalogram Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18434 - TorchTPU - A Hybrid Eager/Compiled Architecture for Native PyTorch Execution on TPU Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24161 - HyBridge: Bridge-Guided Self-Supervised Hyperbolic Hypergraph Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16351 - Towards Seconds-level Video Representation: Quadratically Gated Feature Grid with Adaptive, Prediction-free Sampling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17786 - Aligning AI Teams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17820 - Understanding the limits of snapshot-based fault diagnosis in distribution networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17998 - More Genes, Faster Inference: Efficient Large-Panel Spatial Transcriptomics Prediction from Histology Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17899 - CPM-MultiAgent: A CPM-Grounded Appraisal Framework for Simulating Dynamic Patient Emotional Evolution in Healthcare Dialogue Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07824 - Photogrammetric 3D Model-Based Animal Behavior Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17881 - Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15664 - PhysDox: Benchmarking LLMs on Physical Feasibility Auditing of Physiological Sensing Protocols Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05003 - LoRAWeaver: Directional Adapter Routing in LoRA Representation Space Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17340 - EcoVGGT: Pinned-Key Inference for Efficient and Streamable Feed-Forward 3D Reconstruction from Long Videos Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18099 - ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.16116 - Dancing Tokens on the Vocabulary Network from LLM Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18248 - Experts Across Schemas: Agent-Guided Mixture-of-Relational-Experts for Cross-Database Generalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18315 - ProdPilot: A Layered Model Context Protocol System for Automated Production Readiness and Deployment of Vibe-Coded Projects Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.17381 - CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16613 - Typing Matters: Muscle, Language and Typing Behaviour in Live Keystroke Decoding from sEMG Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18464 - AI for Parameter Selection in Sample-based Quantum Diagonalization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18307 - Personalization of Basic and Moral Values Guiding LLM-Controlled Assistant Robots Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18230 - From Regulation to Implementation: A Critical Evaluation of LLM-Assisted Regulatory Compliance in Industry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21317 - Evaluating Large Language Models for Scientific Paper Search: Retrieval Success and Inference Latency on Mac Studio and NVIDIA A100 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17929 - From AI-Enabled Remote Patient Monitoring Toward Agentic Robotics: Embodiment, Governance, and Care Integration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18484 - MASTARS: Multi-Agent Sequential Trajectory Augmentation with Return-Conditioned Subgoals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17793 - Small Heads, Strong Decisions: A Controlled Study of Typed-Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15592 - TelePhysica: Agentic Reconstruction of Physically Interactive Scenes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18078 - From Images to Grounded Edits: A Real-World Benchmark for Chinese Grammatical Error Correction in Handwritten Essays Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17966 - Agent-written heuristics versus commercial solvers on unsolved job-shop benchmark instances Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17682 - Who Should Be on the Panel? Task-Conditioned Persona Selection for LLM Trading Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18150 - Hybrid Mechanical and Agentic Specification Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10005 - Certified Improvements to Best-Known Thomson-Problem Configurations with a Search Pipeline Built with Large Language Model Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17776 - AI-aided Decision-Making in Education - Uncertainty, Explainability, and Human Responsibility Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17858 - A Variational Latent Equilibrium for Learning in Neuronal Circuits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09600 - When Should LLM Agents Forget? Memory Filtering Under Query-Critical Resolver Errors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17338 - DySENSE: Dynamic Spatiotemporal ENergy Synthesis and Emulation with Satellite Imagery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17878 - ARCHER: From Rationale Imitation to Executable Reasoning in Small Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18494 - MIGRO: A Decoupled and Portable Long-Term Memory System for Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15315 - Courteous Anticipation: Improving Long-Lived Task Planning in Persistent Shared Environments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.20289 - Time-Consistent Evaluation of Hierarchical Code Graphs for SWE Agents Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.17388 - OutfitterBench: Evaluating LLM Agents on Long-Horizon Resource Allocation and Commitment Coordination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17933 - Hallucination-Free GUI Grounding via Regression-Free Layout-Aware Matching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.09654 - TradeGauntlet: Evaluating Compliance Controls for Autonomous Trading Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18493 - SWIFT: Sample-Wise Instance Fine-Tuning of Time-Series Foundation Models for Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17915 - Recursive Belief Vision Language Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.20659 - PrivacyPR: A Dataset of Real-World Privacy Fixes for Benchmarking Privacy-Aware Code Review Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18293 - X-Nav Technical Report: Real-World Long-Horizon Indoor-to-Outdoor Navigation on a Humanoid Robot Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17598 - Advancing Quantization for R&R Models with Microscaling Formats Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17501 - Optimizing Drilling Trajectories in Multi-Material Structures Using Quantum Annealers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18121 - What Balanced Accuracy Cannot Identify in Neural-Signal Decoding under Test-Time Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17925 - Interactive deep-learning based interface for brain tumour segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17983 - PUMA-Former: Uncertainty-Aware Agentic Computation Offloading in MEO-LEO Satellite Networks With Incomplete Information Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18139 - OmniScore-Bench: Evaluating Vision-Language Models on Musical Score Reading Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17870 - Two-Clustering Regime of Token Dynamics in Causal Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18088 - Generated Evaluation Suites as Diversity-Driven Search for Real Agent Regressions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17632 - TimesJev: Thinking Fast on Time Series with System 1 Sufficiency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26002 - DECODE: Diagnosing Interpretability Failures in Automated Interpretation Process Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17856 - GraphScent: Calibrating Directional Relevance Signals for Bounded-Context Code Localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17527 - Sage-Taiyi: A Metacognitive Architecture for Scientific Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12762 - AI-Based Multi-View Echocardiographic Image Synthesis using Dynamic Shape Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18375 - ReForge: Keeping ABR Algorithms Never Finished with Verified Large Language Model Revisions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15138 - Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous Vehicles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17505 - Federated Soft Poly-Level Learning Over a Distributed Network with Guaranteed Convergence Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17722 - Toward Interference-Agnostic RF Source Separation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17950 - Active Learning of Temporal Specifications through Distinguishing Queries Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17866 - SceneAgent: A Multi-Agent Framework for Portable Game Scene Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17821 - Training-Free Acceleration of Multi-View 3D Transformers via Regime-Aware Attention Approximation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17629 - AG-JEPA: Anatomically Guided Joint Embedding Predictive Architecture for Neurodegenerative Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18097 - Probabilities of Causation in Nondeterministic Causal Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18245 - When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.07018 - Programmable Distributions of Semantics-Preserving Variants for Evaluating Code Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18389 - LECAT: Measuring LLM Category Learning from Pretraining Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18419 - Tabular Population Priors as Structured Retrieval for EHR Medication Set Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17341 - An AI-enabled high-resolution chlorophyll-a forecasting model that outperforms the operational global biogeochemical system Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17704 - Causally Constrained and Uncertainty-Aware Cardiopulmonary Risk Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17819 - Co-Sight Harness: Externalized Control Assets and Deterministic Enforcement for Long-Horizon Business Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17696 - VLAN: Vision-Language Accessible Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18346 - The Transformer Paradigm: Dynamic Processing and a New Principle of Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17953 - S1-Evo: Experience-Guided Evidence Competition Attacks on Typed System-1 Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16937 - From Bytes to Behavior: Request-Level Attribution from Live GPU Hidden States Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18272 - Aligned, Conflicting, or Unspecified? A Diagnostic Benchmark for Multimodal Time Series Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17680 - One Offset, Two Directions: Baseline Adjustment via Subgroup Offsets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00782 - ZONOS3-Mini Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16525 - A$^3$: Adaptive Audio Agent Framework for Collaborative Edge Computing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18064 - Proof-Grounded Patient-Specific Clinical Explanations from Knowledge-Graph Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06549 - Multi-Environment POMDPs with Finite-Horizon Objectives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07537 - Exposing and Mitigating Temporal Attack in Deepfake Video Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07398 - Smart Home Agents Make Capable but Unpredictable Grid Operators Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18395 - DeltaBox: Millisecond-Scale Sandbox Checkpoint and Rollback for Stateful AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.22781 - Imitation Bootstrapped Multi-Agent Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18543 - OCTAVE: A Capability-Resolved Benchmark for End-to-End HTML5 Game Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17681 - TReC: Evaluating Move-Induced State Changes in Instruction-Conditioned Go Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17781 - D-VLA: A High-Concurrency Distributed Asynchronous Reinforcement Learning Framework for Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13276 - VelServe: Taming Decode Jitters in LLM Inference with Tail-Calibrated Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18392 - Can Large Language Models Optimize Pretrained Neural Network Weights? A Multi-Phase Empirical Evaluation of Gradient-Free Editing in YOLO26 Object Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17789 - Can LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.30499 - FlashRT-PAI: Fast Kernels Are Not Fast Pipelines for Physical AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.24349 - Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17880 - Can Agents Keep Up with Time? An Empirical Analysis of Temporal Adaptation After a Conversational Hiatus Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17806 - Alignment by Socialization: Learning Tradeoffs Under Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18531 - CoTTAGE: An Explainable Judge for Text-to-Audio Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17644 - From Pen-and-Paper to Machine-Checked Proofs: Lean for System Identification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.18220 - Astrocyte Biocomputing: Astrocytic Contributions to Neural Network Computation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17532 - Operationalizing Governed Agentic Workflows in Regulated Finance: A Customer Zero Case Study using Zafin AIOS Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33253 - Confident and Wrong: Structure Confidence Is a Poor Selection Filter for Protein Function Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17391 - Efficient Test-Time Adaptation through Human-Agent Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.04141