TILens Daily Edition 2026-11-14 Filters: topic=ai-research, github=hidden Stats: 500 articles, 1 source, 500 research papers Top topics: AI Research, AI, Information Retrieval ## Research - Prototypes of the Mind: A Unified Framework for Probing the Visual Brain Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15046 - Flow Reconstruction from Sparse Measurements in Urban Drainage Networks: A Simulation-Based Evaluation of Data-Driven Sparse Sensing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.04556 - Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15449 - Safety as a Budget: Calibrating the Control Channel of Constrained GRPO for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16628 - Effect-Level Validation for Causal Discovery in Interactive Telemetry Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.08340 - Specification-based Security Evaluation of Real-World Agents Tool-Calling under Long-Horizon Context Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.15253 - Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.10437 - A Contradiction Judge Counted Reported Teammate Errors as Hallucinations: An Assertion-Aware Re-Score of One Multi-Agent LLM Harness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21666 - Calibeating Prediction-Powered Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21260 - DAISY: Fault-Guided Assertion Inference for Dafny Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.00125 - Tree-Based Formalization of Multi-Agent Complementarity in Human-AI Interactions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04779 - Shortcuts and Boundaries: Verifiable RL Misalignment and Contextual Safety Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12865 - Knowledge in the Harness, Reliability in the Weights: Teacher-Free Co-Evolution of an LLM Agent Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15268 - Termination Lag: Coding Agents Solve Early but Stop Late Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14960 - SPARC: Accurate Photonic Matrix Multiplication via Representative Vectors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16561 - RMIT-ADM+S at TREC RAG 2026: Research Agents, Retriever Ablations, and Open-Weight Replication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16425 - Graph Label Alignment: A Diagnostic Atlas for Graph Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14760 - Lost in Delegation: Studying the Effectiveness of Task Orchestration in Generative Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16526 - Beyond Named Mechanisms: Economic Institutions as a Design Space for Artificial Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15017 - Recalibrating a Typed-Decision Model in an Afternoon: A Hands-On Recipe for Laya's Confidence Scores Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16499 - DIAGNO: Diagonal Spherical Neural Operators for Heterogeneous Earth Dynamics Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16356 - BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20668 - A Joint LLM and Optimization Agent Solution for Drone Scheduling in Victim Search Missions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16524 - Consistent Video-to-Video Translation via Explicit Correspondences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17298 - The Impact of Large Language Models (LLMs) on Code Review Process Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.11034 - Bug Finding With Agentic Symbolic Execution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15596 - Leaderboard Hacking: Preference-Based Model Evaluations are Vulnerable to Manipulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14769 - Program Learning with Verifiable Rewards: Distilling Expert Traces into Programs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19148 - Contrastive Bootstrap Representation Learning for Label-Efficient Agricultural Image Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15610 - What Roles Do System Prompts Really Assign? Validating and Steering Occupational Role Vectors in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15989 - LLM-Assisted Verification in Dafny Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16886 - ElasticDino: Dense Semantic Features Using Elastic Deformations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16984 - Marginal-Preserving Coupled Diffusion Composition for Long-Horizon Planning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15585 - QSim-Arena: an evolving developer for quantum simulation advantage Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15000 - Speed-to-Power Dominates Energy Costs for AI Data Centers: Technoeconomic Analysis of Powering AI in the Continental United States Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17098 - Learning Low-Latency Action Verification for Frozen Vision-Language-Action Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14834 - OPA-Pack: Object-Property-Aware Robotic Bin Packing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.13339 - Multi-head Quantum Neural Networks: Replacing Transformer Blocks with NISQ Modules inside a 30-Billion-Parameter LLM Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15250 - Discovering Effective Agent Memory Designs through Program Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17068 - SafeOrchestrate: Runtime Checked Intent-Driven Orchestration for Cyber-Physical Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.09364 - Chronocooked: A Benchmark for Interval Timing in Reinforcement Learning Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.16666 - Recursive State-Augmented Language Models: Persistent Latent-State Adaptation of Pretrained Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16375 - SkillEarth: Teaching General-Purpose Agents to Act on Earth via Skill Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15481 - Terms of Care: Designing for Participation in Data Governance by Disability Communities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15720 - Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22510 - Evaluating AI Agents for Industrial-Level Chip Floorplanning: A Framework and Empirical Study Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12048 - Closed-Loop Molecular Design with Calibrated Deference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02618 - KQML-Liver: Interpretable Hybrid Quantum Machine Learning with Kolmogorov-Arnold Networks for Liver Disease Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15241 - Multiple-Choice Secretary Problem with Predictions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14651 - Isotropy Cliffs: The Geometric Signature of Decision-Making in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.00828 - Risk-Aware Joint Inference and Resource Control for Physical AI in 6G Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14696 - Edge-Gradient Augmentation under Reinforcement Learning for Temporal Graph Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16678 - Your Vision Foundation Model Is Secretly an EEG Foundation Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17031 - SwarmSafe-Delta: Isolating Message Effects on LLM Agent Safety Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16123 - Binding Mode Matters: Hotspot-Aware Drug Discovery via Explorative Preferences Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14956 - InertiaMPDD: Multimodal Personalized Depression Detection via Emotional Inertia-Inspired Dynamics Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16647 - An Approach to Hinton's Mother-Child Proposal: Neural Networks Learning and Preserving Care in a Finite World Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15523 - Evaluating Video LLMs' Understanding of Corner Cases in Autonomous Driving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16767 - CRINN: Contrastive Reinforcement Learning for Approximate Nearest Neighbor Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.02091 - How Should Planning Agents ReSHAPE Their Search Space? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16466 - SkinAdvisor: An AI-Driven Decision Framework for Skin Production Planning via Multi-Modal Transformer Sales Forecasting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15023 - Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.15803 - Edge-Native Multimodal RAG: Hardware-Aware Quantization and Architectural Optimization for Consumer GPUs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14924 - TIDE: Token-Level Credit Assignment via Entropy-Gated Bounded Deviation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03327 - Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.10664 - Kezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16933 - MusicRWKV: A Multimodal RWKV Framework for Music Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.16718 - Deep learning-guided discovery reveals the diversity and mutational potential of environmental beta-lactamases Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14568 - Cleaning an Agent's History Hurts When the World Still Holds the Error Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14654 - Care, Human Enfeeblement, and the Existential Implications of AGI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14520 - Towards Robust Vision-Language Reasoning: A Multi-Stage Optimization Pipeline with Masked Diffusion Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15238 - RSI-PDEbench: A Benchmark for Self-Improving Agents in PDE Solving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14949 - IRON-Meme: A Benchmark for Structured Understanding of Identities and Roles in Online Meme Narratives Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.33097 - vSV-ViT: Variable-size SuperVertex Vision Transformer for Cortical Surface Learning in Alzheimer's Disease Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26514 - Can LLMs Fix It Without Code? Toward Automated Verification of No-Code Bug Fixes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11963 - Calibrated selective prediction using deep ensembles for thyroid nodule ultrasound classification under dataset shift Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12075 - From More to Better: Causal Inference and Digital Experimentation in the Age of AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16335 - What Makes a Good Response? An Empirical Analysis of Quality in Qualitative Interviews Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05163 - Read and Ignore: What Self-Directed LLM Agents Do in Public Service Scenarios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15460 - Constrained Bilevel Reinforcement Learning via Approximate Lower-Level Responses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.00282 - JustRUA: A Controlled Study of GPT-6 Robot-Use Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16009 - Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15404 - Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.13171 - DuoJEPA: Cross-Modal Translation Between Unaligned Self-Supervised Embedding Spaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15968 - Self-Supervised Attention-Based Virtual Metrology for CMP MRR Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16172 - DISCERN: Preserve at Write, Resolve at Read for Persistent LLM-Agent Memory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15729 - Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24177 - Thompson Sampling using Prior-fitted Diffusion Transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14656 - PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.09133 - Loyalty Capture: Reporting Relationships and Structural Sycophancy in Frontier AI Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15475 - Lara Mini Base: Language Diversity as a Resource, Not a Trade-off Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16956 - RESYNC: Residual Latent-State Synchronization for Deadline-Bound Streaming Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16523 - Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.14203 - Toward Agentic Retrieval-Augmented Generation for Enterprise Retail Workflows over Heterogeneous Data Sources Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.25096 - TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09323 - What Entropy-Based View Selection Cannot See: An Audit of Test-Time Adaptation for Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14686 - Can an AI Agent Be Epistemically Akratic? Higher-Order Evidence & the Limits of Self-Correction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14889 - A Dual-Branch Graph and Convolutional Network for Interpretable Movement EEG Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16609 - AgentRoom: Concurrent Multi-Agent Coding in a CRDT-Backed Shared Workspace Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23740 - Incentive-Responsive Agents: A Principal-Agent Framework, Metric Suite, and Runtime Architecture for Long-Lived Personal AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15515 - Quantum Recurrent Architectures for Financial Time Series Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15298 - WordInferBench: Can Agents Infer How to Edit from Word Document Context? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15189 - UMER: Unifying Embedding and Ranking via Pair-Aware Discriminative Reasoning for Universal Multimodal Retrieval Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18504 - HyperSkill: Training-Free Omnimodal GRPO via Hypergraph-Indexed Skill-Library Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15178 - CoLaX: Context-Aware Local Explanations for Time Series Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15067 - Lightweight GenAI for Network Traffic Generation: Fidelity, Augmentation, and Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25507 - When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.10552 - Ownership in AI-Assisted Everyday Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20658 - Abstention Is Not Threshold Compliance: Stated Scoring Rules in Open Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14661 - SFL-Net: Dependence-Regularized Latent Pathways for Multi-Contrast MRI-to-tau-PET Synthesis and Component Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.22545 - When Safety Becomes an Attack Surface: Manipulating Abstention in Tool-Using AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14864 - TopoST: Topology-Conditioned Node Specialization for Urban Spatio-Temporal Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15440 - The Value of Thinking: Learning When to Reason in Hybrid Decision Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16961 - AI Search as an Information Intermediary: Clickstream Evidence on Web Traffic Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07652 - When Expert Disagreement Hurts: Prestige and Selectivity in LLM Decision Revision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16694 - Parameter-Efficient Conciseness Adaptation: Differentiable Length Control for Concise Clinical Reasoning in Smaller Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17128 - CARE-Drive: Coupled Alternating Refinement for Ego-trajectories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15360 - Controlling the Probability of Unknown Unknowns in Pre-Deployment Testing of AI Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15835 - The BEATS Dataset: Towards Understanding Music-Physiology Dynamics in Real-World Scenarios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15837 - MemInStream: Memorizing or Merely Recognizing? Rethinking Streaming Video Memory Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15640 - VMonarch: Efficient Video Diffusion Transformers with Structured Attention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22275 - Four conditions for composing plugin-based agents without a host agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.28553 - Reframing Video Inverse Tone Mapping as Blind Posterior Inference via Latent Luminance Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15146 - Wanda-Guided Sparse Perturbations for Efficient Zeroth-Order Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16317 - Small Language Models for Inference-Capability Routing: Effects of Model Capacity and Prompt Optimization on Downstream Quality and Efficiency Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16414 - Are Scaling Laws of Universal MLIPs Universal? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15603 - AGORA: Reliability-Aware Aggregation of LLM Judges on Small Evaluation Sets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.05556 - Audit the Scaffold, Not the Checkpoint: A Stationarity Dichotomy for Recursive Self-Improvement in Agentic Coding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.34924 - SO-Arena: Benchmarking the Capability Spectrum and Reliability of System One Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15777 - Where Autonomy Belongs: A Separation of Powers for Agentic Program Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15309 - Singularity-Bench: Can Agents Build Agents? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16591 - MotionCFG: Boosting Motion Dynamics via Semantic Motion Sharpening Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.14073 - Do More Modalities Always Help? A Geometric Perspective on Missing-Modality Robustness Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.04792 - metalSPARSE: A 2:4 Semi-Structured Sparse GEMV Kernel for Apple Silicon GPUs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14545 - Large Payments Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15814 - LLM4SCREENLIT: Recommendations on assessing the performance of large language models for screening literature in systematic reviews Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.12635 - Legal interpretation and AI: from expert systems to argumentation and LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05392 - AutoQS: Automated Quantization Strategy Design with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11975 - DecArena: Evaluating Large-Scale Decentralized Multi-Agent Collaboration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15521 - MITRA-Swarm: Injecting Explicit Linguistic Structure into Foundation Models for Classical Machine Translation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14675 - Steering Away from Memorization: Reachability-Constrained Reinforcement Learning for Text-to-Image Diffusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.00140 - When AI Classifies: What Counts as Public Administration? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05420 - Honesty Is a Race: Predicting When Verifiable-Reward RL Teaches a Model to Bluff Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15779 - Science Prediction Universe Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15049 - The Limits of AI-Driven Allocation: Optimal Screening under Aleatoric Uncertainty Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.07979 - Large Language Continuous Diffusion Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.02665 - Mach2: Scientific Discovery Platform with Deterministic Execution Constraints Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14777 - Dataset Distillation via Drifting Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16642 - Persona Following Is Not Selective Control: The Neutrality Gap in LLM User Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35036 - Governing Copyright Responsibly in the Era of Generative AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.17002 - Agent MechSuits: Mechanistic Subspace Safety Steering for Multi-Turn CLI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22673 - Beyond the Trial-and-Error Loop: Hybrid Projection and Automated Tuning for Distributed Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.19423 - A Foundation Model for Electrodermal Activity Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16878 - SAGE-QA: Semantic-Aware, Grounded Evaluation for Closed-Context Question Answering on SQuAD 2.0 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16300 - Robots That Talk Too Much and Don't Listen Enough Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16473 - Hint-Informed Self-Distillation for Reasoning Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14931 - A Scaled-Up Empirical Study of Syntactic Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16837 - ReliaGuard: Reconstruction-Aware Watermarking for Source Attribution and Blind Edit Localization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16368 - Finite-Cadence Refresh Equilibria for Streaming Prior-Anchored Ridge: A Closed-Form Forgetting Window and Spectral Correction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14586 - Evaluating Local Language Model Agents for Data Engineering: An Empirical Software Engineering Study of Mobility Workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.11482 - DPA: Decentralized Primal Averaging with Quasi-Global Momentum for Highly Heterogeneous Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16871 - Primer: An AI Framework for Instructor-Centered Educational Simulation Creation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16986 - Outside the Purview of the Reward: Capability Drift in Multilingual Post-Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15717 - Scalable Conversational Assessment: Chat-Based Exams with a Two-Agent LLM Pipeline Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17220 - Robust Task-Aware State Estimation from Pre-trained Perception Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14781 - Where Is Uncertainty Observed? A Mechanistic Understanding of Uncertainty Quantification in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15735 - Bridging GenAI policy and practice: Brief instruction improves learning-oriented prompting in an introductory programming course Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.16033 - HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16487 - Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.09454 - Human Capital in Context: What Employment Survival Reveals About Worker-Firm Match Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16058 - When Chekhov's Gun Fires Anyway: Over-Realization in Text-to-Image Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16630 - GHAgentCI: A Dataset of Coding-Agent Invocations in CI Workflow Histories Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15522 - AgriSense: Vision-Language Decision Support and Robotic Intervention in a Virtual Greenhouse Copy title Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16752 - Fine-Tuned Small Language Model for Synthetic Clinical Data Generation and Predictive Healthcare Analytics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16460 - Where Polanyi Meets Galois: Tacit Knowing as an Algebro-Deterministic Operation, Toward Re-rooting AI-Generated Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16102 - The Rebundling of Freelance Work in the AI Age Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14708 - MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28590 - Towards Accurate UAV Image Perception: Guiding Vision-Language Models with Stronger Task Prompts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.07302 - From Foundation VLM to Versatile Driving VLM: A Triplet Incremental Training Approach Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16727 - VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15789 - A Time-Frequency-Condition Multimodal Fusion Foundation Model for Universal Rotating-Machinery Fault Diagnosis under Multi-Element Heterogeneous Scenarios Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15051 - Rational Alignments of Superintelligences via Debates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16455 - Fine-Tuning Language Models to Know What They Know Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02605 - Unsupervised Candidate Ranking for Lexical Substitution via Holistic Sentence Semantics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.11513 - MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25832 - NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.15015 - Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15118 - Look It Up: Multi-bit LLM Watermarking via Codebook Search Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16890 - RUMI: A Robotiq-Matched Universal Manipulation Interface for Robot Learning with Augmented Reality and Haptic Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15802 - OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17757 - MuEdit: An efficient multi-task editing method towards inter-domain knowledge conflicts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14910 - MLIRBench - A Benchmark and Dataset for Compiler and Hardware-Aware Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14881 - PISim: A Unified Photonic Inference Simulator for Hardware-Aware Cross-Layer Design-Space Exploration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16522 - EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.10498 - ADAPT: Agentic Diff-Aware Patch Testing for Pull Requests Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16114 - ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.18681 - ReShap: Interpretable Reinforcement Learning for High-Dimensional Multi-Action Settings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15507 - SideTaskBench: Measuring Unauthorized Side-Task Delivery in Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14548 - Estimating Image Creativity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15044 - Benchmarking Multilingual Document Understanding in Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14758 - Learning-augmented smooth integer programs with PAC-learnable oracles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02505 - SALA: Semantically Aligned Latent Actions Enable Dual-Axis Scaling of Embodied Foundation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17110 - Introducing Feedback Delays to Non-Delayed Adversarial MDPs: Optimal $\sqrt S$ and $\sqrt K$ Dependencies in Tabular and Linear AMDPs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17214 - Classical Energies Learn to Reason 1,000x Faster than Looped Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17309 - Dual Representation Enhanced Diffusion Policy for Flexible Job Shop Scheduling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15246 - MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.26185 - TraceKV: Policy-Preserving Low-Rank KV Cache Compression for Reasoning Vision-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15569 - Same Task, Different Statement: When and How Reformulation Helps LLM Problem Solving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14997 - 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 - Axion 1.0: Open Agent Foundation Models, Simplified Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03233 - TheoPhysEval: Assessing AI agents at autonomous theoretical physics problem solving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.16733 - Training Computer Use Agents to Assess the Usability of Graphical User Interfaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.26020 - Turning Multi-Agent Communication into Token-Level Credit with On Policy Self Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16206 - From Data to Wisdom: Rethinking AI Through an Epistemic Lens Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16726 - EasyFoam: Skill-Oriented OpenFOAM Agents with Evidence-Driven Evolution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14525 - Designing Institutions for Autonomous AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17114 - From Delegation to Coordination: Learning Efficient Multi-Agent Deep Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17041 - FACE: Few-shot Adapter with Cross-view Fusion for Cross-subject EEG Emotion Recognition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.18998 - Understanding the Effects of Multi-Agent Deliberation for Human-AI Decision-Making Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14901 - $\gamma$-weakly $\theta$-up-concavity: A Unified Framework for Non-Convex Optimization Beyond DR-Submodular and OSS Functions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.13506 - Breaking Bad: "Going Badly" Activations Drive Reward Hacking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14996 - DForkTree: Accelerating Speculative Decoding with Fork-Aware Block Diffusion Draft Trees Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12356 - Guided Generation of Linux Kernel Semantic Patches with Small Local Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16215 - Contain, Conform, Compare (Extended Version): A Red-Teamed Evaluation Kit for Small Coding Agents and the Full Record of Its Experiments Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16485 - Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.11662 - MAC: A Conversion Rate Prediction Benchmark Featuring Labels Under Multiple Attribution Mechanisms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.02184 - AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28655 - SimRec: Learning to Search, Ask, and Recommend from Simulated Interaction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15426 - Sketching Language Models for Context Attribution Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17313 - Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.20910 - AFTER: A World Model with Adaptive Fast--Slow Timescales for Error-Driven Retention Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15215 - Mind the Accuracy-Approval Gap: How Users Evaluate Sycophantic AI in Everyday Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16722 - Studies on Sign Language Retrieval in Low-Resource Dictionary Settings Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16621 - Iris-Z: Scaling One Generative Model Past Specialist Geometry Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16010 - POIROT: Agents as their own auditors for failure attribution in large language model multi-agent systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02282 - Security and Privacy Prompts in the Wild: What Users Ask LLMs and How LLMs Respond Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18062 - CapLite: Prompt-Injection Defense for Small Language Model Agents without Model-Written Security Artifacts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17115 - ReA-Bench: Benchmarking Responsible Agent Auditing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16493 - Submodular Benchmark Selection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.02209 - Data-Efficient LLM Safety Alignment Guided by Interpretable Features Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16183 - Characterizing Scanpath Decoding Pipelines with Perturbation Profiles Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.11632 - Faithful in Steps: Improving Generalization and Citation in RAG via Query Decomposition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15538 - Synthesizing Human Trajectory Anomalies: An LLM-Driven Framework with Map-Constrained Routing and Sensor Noise Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10314 - When Failures Propagate: Causal Failure Attribution in Agentic Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20627 - AVC-Reward: Event-Centric Audio-Video Consistency Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.22321 - Curiosity-0826-4B: Generative Medical Event Sequence Modeling Across Pediatric and Adult Populations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15710 - Stack more levels: how to get general and human-like Mario playing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16175 - Rectified Looped Transformer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16265 - Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.12374 - Folio: Recoverable Multi-Resolution Context Folding for Long-Horizon Language Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16627 - Predicting Ethanol Drinking Status from Nonhuman Primate Liver Histology: A Proof of Concept for Parameter-efficient Fine-tuning in Few-Shot Vision-Language Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17105 - Are We Ready for Snow-tonomous Driving? Challenges Toward Robust Automated Driving in Extreme Weather Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15217 - Tokenized Reward Systems for Federated Learning: The Privacy vs. Fairness Tradeoff Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16065 - Subsurface schematisation from sparse CPT data using the tabular foundation model TabPFN Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16088 - Read Once, Answer Many: Parallel Prompting for Shared-Context LLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15130 - Extrapolation of Periodic Functions Using Binary Encoding of Continuous Numerical Values Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.10817 - SMIC: Shared Multiscale Input-Reference Conditioning across Transformer Layers for Natural Language Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16270 - One Model, Two Precisions: Does Disagreement Between Quantized Copies Tell You When a Small Model Is Wrong? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16478 - LiveGeo: Benchmarking Geographic Agents in Continuously Evolving Worlds Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17267 - Approximate and Weighted Data Reconstruction Attack in Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2308.06822 - Protein Language Models Fail To Capture Contact Predictions Under Invariant Relabeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16881 - 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 - ORCA:Orthogonal Residual Consensus Alignment for Multi-View Clustering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16749 - KernelMosaic: An Open Dataset and Agentic Framework for CUDA Kernel Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14604 - Data-Free Metrics Don't Work: The Missing Invariance Under Functionally Preserving Reparameterisations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15621 - GraphSkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.20455 - ZONOS3-Mini Technical Report Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16525 - Multi-View 3D Reconstruction Using V-JEPA Features Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15143 - Discharge Summary Generation Is Not Just Summarization: A Reality Check for Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14823 - MobileProbe: Adaptive Security Evaluation of Mobile Agents via Trajectory-Aware Injection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16693 - Zugwise: Domain-Aware Game Reconstruction for Digitizing Handwritten Chess Scoresheets Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14544 - Scaling public input on AI policy with pluralistic agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16028 - CFGComposer: Compositional Audio-Text-to-Motion Generation via Copula Score Correction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15101 - Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.22608 - Runtime Analysis of Cartesian Genetic Programming on Max: A Proven Exponential Speedup Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16013 - ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.09009 - Where in the Input Does a One-Pass Decision Encoder Look? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16477 - Anchoring Clinical Events in Time: UID-Preserving Multimodal Reconstruction and Source-Grounded Adjudication Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13062 - Goal Encoding in LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17297 - AskALCF: A Self-Improving Agentic System for Intelligent HPC User Support Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15700 - MALNISI-Infused Graph Construction and Weighted Contrastive Loss based GAT for Unsupervised Representation Learning in HSI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17199 - Moving Beyond the DRW Model: Learning Quasar Variability with Generative Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15040 - MuSeToM: Multi-Sensory Evaluation of Belief Revision with Textual Cues Across Six Senses Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16662 - From Nodes to Pixels: Topological and Structural Two-View Graph Imaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14750 - EvoX: Rethinking the Agent Harness as a Runtime Policy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15006 - A Cardiorespiratory Foundation Model Pretrained on Ten Physiological Signals for Perioperative and Critical Care Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15004 - A physics-constrained deep reinforcement learning method for autonomous mission planning of Titan deep space probes Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15389 - AURA 2.0: From User-Driven Responses to Model-Initiated Conversations in Streaming Video Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17048 - Spec-Driven PBT: Deriving Semantic Invariants from Code Specifications for Agentic Property-based Testing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15920 - Prior-as-Skill: Remember Outside and Read Inside with On-Policy Self-Distillation for Self-Evolving VLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15766 - Reducing Batch Makespan for LLM Agent Workloads through Inference-Environment Coordination Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16661 - Do Large Language Models Show Racial and Sex Bias in Pain Management? A Counterfactual Audit of GPT, Claude, Gemini, Llama, DeepSeek and Qwen Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14935 - GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theory Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.12316 - AI for Biologists: The Knowledge Boundaries of Foundation Models in the Age of Agentic Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17015 - Winfree Oscillatory Neural Network Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.20922 - Joint Learning of Hierarchical Neural Options and Abstract World Model Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.02799 - AI has its own style in mathematical proving Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16527 - A Compact xDAWN-Guided Spatio-Temporal Network with Filter-Bank Convolution for P300 Detection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17101 - Tokenization: Hardness and Bicriteria Approximation Algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15074 - AgroOmni: A Large-Scale Multi-view Agricultural Dataset for Cross-Scale Multimodal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.14342 - Time and Space: A Dual-Axis, Evidence-Grounded Context Substrate for Personal Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16492 - When can an interpretability claim be trusted? Stability and certification of feature dimensionality, ridge leverage and the feature recovery rate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16190 - A model of errors in transformers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.14175 - FoMEMO: Towards Foundation Models for Expensive Multi-objective Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.03244 - Latent Imagination for Parameterized Action Spaces Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15744 - Code as Explanations: Executable and Verifiable LLM Explanations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14704 - Provably Optimal HBT Legalization in Seconds: Certified Optima Reveal Where the Headroom Really Lies Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14928 - "I don't know what I don't know": Exploring the Benefits and Challenges of AI in Interdisciplinary Research Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15121 - RAIN: Region-Aware Inversion Network for Semantic Watermark Extraction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.14856 - Metal Sandbox: Isolated Execution and Command Scheduling for GPU Coding Agents on Apple Silicon Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17294 - Agentic Computational Algebra Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16073 - A Reliability Study of Explainable AI for Freight Mode Classification Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15716 - Don't Blame The Preferences: Examining The Emergence of Sycophancy in LLM Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10045 - Cited but Unused: Parametric Provenance in Retrieval-Augmented Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17161 - Privilege and confidentiality in generative AI workflows Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05479 - OverServe: Resource Amplification Attacks on SaaS Agents via Tool--Prompt Co-Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14808 - Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15348 - AnalogLayoutWorld: An Open Benchmark for Agentic Analog Layout Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16991 - Planning as Dynamics Relaxation: Hippocampal Recurrent Network Realizes Optimal Goal-Directed Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.13219 - MAGIC: Modality-Aware Gini Inspection for Clinical Hallucination Detection in LMMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15530 - Gaussian processes for real-time urban traffic estimation using a fleet of drones Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14536 - HeriKGQA: Grounded Knowledge-Graph Question Answering over Cultural Heritage Sensor Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15904 - Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.06439 - When Can Learned Uncertainty Be Trusted? An Audit of Distributional Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.11607 - Reliability of Claude Code as an Agentic AI Grading System for Handwritten University Exams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13217 - EgoX: Egocentric Cross-Embodiment Manipulation with Embodiment Dreaming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16728 - Speech Tokenizers are Vulnerable: Transferable Semantic Attack and Robust Tokenizer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14929 - Lilith: Developmental Modular LLMs with Chemical Signaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.04575 - Automata from Agent Traces: Failure and Next-Step Prediction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23670 - Fast-dLLM++: Fr\'echet Profile Decoding for Faster Diffusion LLM Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02955 - Pyramidal Columns Acting as Attention Heads Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16057 - Delayed homomorphic reinforcement learning for environments with delayed feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.03641 - WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.06407 - LLM-Enhanced Deep Reinforcement Learning with Human-in-the-Loop Calibration for Real-Time Optimal Power Flow Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15003 - Training Language Models via Neural Cellular Automata Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.10055 - PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16748 - When Both Sides Adapt: The Challenges of Evaluating Interactive LLM Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17239 - SLIDERS: Evidence Synthesis with Autonomous Database Reconciliation for Systematic Reviews Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.22294 - Typed Knowledge over Constructive Institutions: A Proof-Relevant Type Theory for Verified Science Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15108 - Beyond Compressing Everything: Contrastive Memory Learning for Selective Context Compression Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16384 - Matrix-Based Ant Colony Search with Batched Decoding for Hierarchical Replenishment Routing: A Stylized Case Study Based on Korean City Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15338 - Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14912 - Contour-Assisted Evolutionary Computation: Estimating Peaks From the Contour Lines of Evaluated Solutions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15641 - Which Buildings Are Artificial Intelligence-Ready? A Measurement-Based Assessment Framework for AI Question Answering and Actuation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.09119 - Open Challenges and Opportunities in Human-Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14846 - guardscope: Measuring Which Actions Runtime Controls Check in LLM Agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15223 - Automatic Knowledge Graph Construction and Query for Earthquake Catalogs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.24984 - A Modular Framework for ESG Prediction through Domain-Specific Language Modeling and Graph Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16831 - CauProphet: Teaching Agents to Develop Causal Cognition like Humans Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.32477 - FPSRG: Heterogeneous User Simulation First-Person Post-Training and Multidimensional Semantic Response Grids Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16445 - Context Graph: Explainable Multi-Agent Decision Chains in AI-RAN Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16879 - Learning-Based Interpolation of Detector Gaps in Photon-Counting X-ray Imaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15614 - When Is Proof-Step Verification Worth Its Cost? Operating Requirements of Certify-or-Decline Verification for Open-Weight Mathematical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14794 - SoScale: Second-Order Scale Search for FP4 Quantization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16426 - Skill Adapter: Personalized Modification and Online Routing of General-Purpose Skills Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17007 - Synthesis Smuggling: Maliciously Hiding Inferred Personal Attributes in LLM Outputs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17280 - AutoOntic: Automatic Ontology Induction from Text for Knowledge Graph Construction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15467 - Right Answers, Inconsistent Evidence: Source-Level Counterfactual Auditing of Large Audio-Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15463 - Solving Witness Triangle Puzzles Faster with an Automatically Learned Predicate Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2308.02666 - STRATOS: Bridging the Symbolic-to-Numeric Gap in Spatio-Temporal Text-to-SQL for Meteorological Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.03501 - LongReasonArena: A Long Reasoning Benchmark for Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.19363 - Food Critic: An Agentic Visualization System for Auditable Restaurant-Safety Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI, JavaScript, React) URL: https://arxiv.org/abs/2611.15843 - Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07922 - Advancing Weighted Partial MaxSAT Solving via Differentiable GPU Guidance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15091 - Patient-specific rubric-based evaluation of large language models across longitudinal cancer care Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.35847 - WaveFlow-UIE: A Single-Pipeline Wavelet-Domain Flow Model for Efficient Underwater Image Restoration Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15457 - Causals: An Open Knowledge Graph for Research on Causal Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16267 - AI Sandboxes: A Threat Model, Taxonomy, and Measurement Framework Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18532 - CENDRe: Concept Extraction with Natural Domain Representations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.29621 - CastWorld: Benchmarking Context-Aware Agentic Time Series Forecasting Beyond Predictive Accuracy Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15262 - AVA: Agentic Variant Adjudication for Automated, Auditable Read-Level Review in Cancer Diagnostic Sequencing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14560 - DRAMA: Dissecting Attention Redundancy for Accelerating Multimodal Diffusion Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16345 - When Does Learned Constraint Selection Pay in Security-Constrained Optimisation? A Boundary Map from SCOPF to Unit Commitment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15142 - CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.02551 - Eliciting and Mitigating Specification Satisficing in Coding Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16289 - Learning pharmacokinetic dynamics with structured neural ODEs for precision dosing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.03215 - Ballad: Bandit-Based LLM Routing for Automated Heuristic Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17241 - Natural Gradient Learning in Predictive Coding through Lateral Circuits Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16666 - Verify by Doing: Co-Evolving Agent Execution and Evaluation without External Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15276 - Learning Where to Simulate: Generative Active Sampling for Online PDE Surrogate Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09949 - DesignTaste: Benchmarking AI-Generator Visual Design Against Award-Wining Works Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16442 - DrugCoding: A Scientific Programming Agent for Drug Discovery Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.13651 - Compiling Known Rules into Compact Neural Agents: Weight-Space Programming on Unseen Games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16981 - SynthCorp: A Platform for Creating Benchmarks for Data Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14765 - Reasoning Supervision and Capability Retention in LoRA Domain Adaptation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17072 - XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21688 - Cortex-FL: Agent-Mediated Collaboration for Federated Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17186 - Scale-Induced Semantic Shift in Visual Prompt Injection Against VLMs and Web Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16744 - COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17693 - PDO Drug Screening Data for Evaluating and Training AI Drug Response Prediction Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15769 - Low-Cost Assays for Measuring Model Behavior Across Vendors and Releases Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.30012 - Where is My Mug? Training-Free Framework for Personalized Image Segmentation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15216 - EMS-Nav: Embodied Multi-Scale Navigation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15589 - Do people apply different norms to humans and large language models acting on their behalf? Evidence from norm elicitations in two canonical economic games Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15312 - MoralBench: Moral Evaluation of LLMs Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.04428 - Fr\'echetFlow: Flow Matching for Non-Euclidean Data Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15220 - Where Should the Code Go? Locating Foundation-Model Errors in Bitemporal Inventory Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14671 - Sima AIunty: Caste Audit in LLM-Driven Matchmaking Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.29288 - Multi-Task Self-Evolving Harnesses with the Agent as Its Own Optimizer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.38372 - GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02721 - Re-evaluating Heart Rate Variability Biomarkers for Glucose Sensing: The Impact of Age Normalisation and Subject-Independent Validation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.11682 - PhysCapBench: A Cross-Domain Benchmark for Physically Grounded Video Captioning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16424 - Can MLLMs Reason over Surround-View Driving Videos? A Multi-View Autonomous Driving QA Benchmark Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15225 - Theorem-Proving Agent over Abstract Syntax Tree Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.16372 - Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.10982 - GenPFN: An In-Context Tabular Foundation Model Approach for Augmenting Small Datasets in Engineering Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14804 - When Evaluators of AI Agents Disagree: An Empirical Study of Native Scoring, LLM Judges, and Commit-Boundary Checks on tau2-bench Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14581 - Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.20335 - LOLPlay: Benchmarking Real-Time Visual Agents in League of Legends Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.03685 - Rational Use of Time for Social Coordination in Humans and AI Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14766 - HarnessNet: Feedback-driven Hierarchical Joint Harness Evolution for Multi-agent Systems Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2610.15221 - Evaluating AI Musical Creativity: Towards a Quantitative Multi-Dimensional Framework Based on Value, Novelty, and Surprise Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14634 - How many LLM-labelled rows does a decision encoder need, and how wrong can the labels be? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16498 - GuardianAgentFlow: Multi-Agent Coordination for Web Privacy Protection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15097 - PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.16175 - Evidence-Governed Adoption of Self-Generated Updates in Autonomous AI Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16378 - Shared Item-Level Error Limits the Aggregation of Small Language Models in Fermi Estimation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16315 - Early Signals, Strong Decisions: Prefix-Guided Sampling for Parallel Test-Time Scaling Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14965 - Label-Efficient Document-Grounded Factuality Detection via Cross-Paraphrastic Invariance Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16264 - Benchmarking AI risk behaviors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16318 - STEALTH: Steganographic Text Encoding Agnostic to Low-Level Tensor Hardware Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16928 - GingivitisSeg: A Public Dataset and Comparative Benchmark for Gingivitis Segmentation in Intraoral Images Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15184 - CoReMem: Cost-Internalizing Memory for Successive Coding Tasks with Prospective Valuation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17316 - Efficient Knowledge Transfer in Federated Bayesian Optimization through Neural Network Surrogates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15707 - One Fuzzer, Many Reasoners: Adaptive Neuro-Symbolic Fuzzing with Reliability-Calibrated and Context-Gated Guidance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16211 - Emergent Vision-Shaped Thinking in Text-Only Reasoning through Multimodal Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14942 - MechFoundry: An agentic loop that poses and performs engineering analyses and optimization of real-world objects Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14571 - MemCredit: From Relevance to Utility for Decision-Time Memory in Long-Horizon Web Agents Source: arxiv-cs-ai Topic: AI Research (+AI, Information Retrieval) URL: https://arxiv.org/abs/2611.15600 - NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03159 - Indic-Task Gains and Regressions after Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16228 - SkillDuet: Co-Evolving Models and Skills through Response Feedback Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.12109 - FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.25246 - Can Model Answer Probabilities Represent Survey Populations? Conditional Prediction and Joint Validity in Jev Survey Simulation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15576 - Testing Conversation Preservation Across LLM APIs: A Rule-Based Oracle for Detecting Silent Information Loss Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15543 - Fit-LRP: Fitting Linear Relaxations to Polytopes for Neural Network Verification over Non-Convex Regions Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16003 - Al-Ghasali: A Computational Framework for Simulating Islamic Jurisprudential Rulings via Finite State Automata and Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17235 - Expanding the Decision Space of Pretrained Models through Structured Re-Decoding Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15109 - Together Compiler: Continual Compilation for AI Inference Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14681 - Beyond Accuracy: A Geometric Stability Analysis of Large Language Models in Chess Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.15033 - When Should Semantic Priors Enter Partially-Identified Causal Discovery? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14736 - AgentSSL: Can MLE Agents Leverage Unlabeled Data? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17323 - Cross-Organizational SysML Model Integration: A Survey of Challenges and AI-Supported Tasks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.37000 - Between Niti and Nyaya: A Society-Centered Framework for AI Governance Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16173 - RewardFlow: Can Action-Level Reward Be Estimated from State-Graph Topology in Agentic RL? Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18859 - Who Moved the Frontier? Paying Open Frontier Challenges with Free Identities Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14974 - Show Your Work in Swahili: Reinforcement Learning for Native-Language Mathematical Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16104 - SPADE: Soft Prompts for Ai-text DEtection Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16929 - The Oracle and The Prism: A Decoupled and Efficient Framework for Generative Recommendation Explanation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.16543 - Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17167 - HyBridge: Bridge-Guided Self-Supervised Hyperbolic Hypergraph Representation Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16351 - Should There be a Teacher In-the-Loop? A Study of Generative AI-Personalized Tasks Middle School Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15876 - JudgeMix: Judge-Guided Mixed-Rollout Data Synthesis for LLM Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16174 - CADET: Construction of PCB Routing Instances with Executable Demonstrations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16913 - Acoustic Respiratory Phase Detection on Mobile Devices Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16710 - Universal Infectious Disease Forecasting with Mantis 2 Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16935 - World-Model Collapse as a Phase Transition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.31399 - SUMNO: Spatially Unrolled Multigrid Neural Operator for Fluid Flow Surrogates Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16341 - Modality vs. Morphology: A Framework for Time Series Classification for Biological Signals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18483 - Before AI Agents Negotiate for Us: A Competitive Tournament of Rule-Based, Search, Optimization, Learned, and Language-Model Negotiators Under Scarcity Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15838 - Quantifying Subliminal Behavioral Transfer Ratios in Language Model Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.11270 - The Qualitative Laboratory: Theory Prototyping and Hypothesis Generation with Large Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00797 - Auditing AI peer reviewers: a benchmark on real scientific papers Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.17052 - 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 - Fine-Grained Generative Hallucination Detection and Correction for Aerial Image Captioning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15809 - LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03303 - Data-Scarce, Multi-Granular, Multimodal: Benchmark Design for Biosynthetic Gene Clusters Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.02275 - Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25735 - Flexible Flows for Biological Sequence Design Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10543 - Will It Survive? Deciphering the Fate of AI Agent-Authored Code in Open Source Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.16809 - Same-State Pairs Make One JEPA Proof of the Platonic Representation Hypothesis Vacuous Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16182 - When Agents Need to Consolidate Memories: What RRR Consolidation Explains, and What It Does Not Explain, in Conversation ESAA Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15644 - Outcome Over Learning? Evidence from Student Use of AI Code Assistants for Unit Test Writing Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14664 - AstroMemBench: A Benchmark for Memory Systems in Embodied Spacecraft Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16590 - Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.01584 - DataCook: Exploring Anti-Adversarial Fingerprints for Healthcare Data Usage Control Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2403.17755 - Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.35890 - Reward-Driven Collider Physics Challenges for Self-Improving Agentic AI via Reinforcement Learning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15885 - Trained on What Screen Readers Cannot Read: Accessibility Debt in the GUI Corpora Behind Computer-Use Agents Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16107 - AI Alignment via Incentives and Correction Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.01643 - Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23873 - Assessing Per-Sample Membership Inference Vulnerability without Retraining Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.15919 - Effective Teacher Support for Reasoning Distillation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14850 - Shannon observables: A scalable approach to information decomposition Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.15779 - NIBench: benchmarking autonomous AI agents for execution, skill evolution and scientific judgment in neuroimaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15831 - A frontier machine intelligence for human neuroimaging Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.15094 - CAFIN: CUDA-accelerated Adaptive Fisher Information Matrix Network Optimization via GPU-Native Kernel Fusion Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14589 - Large Language Models as Digital Twins: a Distribution-Aware Questionnaire-Based Evaluation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16586 - A hybrid FEM-PINN method for time-dependent partial differential equations Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2409.02810 - The Posterior-Prior Epistemic Gap: When World Model Imagination Fails to Carry Task-Relevant Signals Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14955 - CamChoreo: Benchmarking Temporally Grounded Compositional Camera Motion Understanding for Vision Language Models Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.10932 - Multi-Step Underwater Acoustic Channel Prediction via Dual-Domain Structure Preservation and Pretrained Transformer Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14592 - Early Stopping in Large Reasoning Models: A Survey and Empirical Audit of Efficiency and Reliability Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.00166 - Rare Event Estimation via Iterative Unalignment Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2609.24969 - BunshinRL: Whole-Workspace Forking for Agentic Reinforcement Learning Rollouts Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.10453 - SignRot: LLM Quantization with Massive Outlier-Aware Sign-Adjusted Rotation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16502 - AutoAssumption: Searching over Assumptions Discovers ML-Systems Algorithms Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.14844 - TransXplainRRG: A Radiologist-Evaluated LVLM for Chest Radiograph Report Generation Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16393 - From XXLTraffic to EvoXXLTraffic: Scaling Traffic Forecasting to Sensor-Evolving Networks Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.29768 - From Noise to Diversity: Random Embedding Injection in LLM Reasoning Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.11936 - ORCHID-SAGE: Fully Reproducible CALPHAD Assessment from Evidence to Phase Diagram Source: arxiv-cs-ai Topic: AI Research (+AI) URL: https://arxiv.org/abs/2611.16308