TILens Daily Edition 2026-08-28 Filters: topic=ai-research, github=hidden Stats: 440 articles, 3 sources, 440 research papers Top topics: AI Research, AI, Python ## Research - Human-in-the-Loop Without Killing Throughput Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/human-in-the-loop-without-killing-throughput/ - From One Agent to a Team: Understanding Codex Subagents Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/from-one-agent-to-a-team-understanding-codex-subagents/ - Connecting My LangGraph AI Agent to Postgres Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/connecting-my-langgraph-ai-agent-to-postgres/ - Why Claude Code Time Estimates Are Poor Source: towards-data-science Topic: AI Research (+AI, Python) URL: https://towardsdatascience.com/why-claude-code-time-estimates-are-poor/ - TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21057 - VFA: Empowering Multilingual MLLMs via Vision-Free Adaptation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26155 - MAPLE: Metadata Conditioned LLM Pretraining for Locale-Aware Question Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.15236 - The Limits of Automatic Evaluation of Creativity in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23705 - ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.24279 - Summarization is Not Dead Yet Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08000 - Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.15763 - Reasoning about In-Context Samples for Machine-Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27036 - Investigating the Influence of Prompt and Response Languages on LLM Content Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26186 - SWE-Prime: Fewer Trajectories, Better Performance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27449 - Survival-Guided Length Control for Efficient Diffusion Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26374 - An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.05725 - Do Language Models Follow Occam's Razor? An Evaluation of Parsimony in Inductive and Abductive Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.03345 - Research Design Tracking and Assessment for the Social Sciences Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27049 - Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26480 - Preserving General Capabilities during Domain Specialization with Uncertainty-Calibrated MOPD Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26735 - A Reranker for Orchestrating Heterogeneous Speech and Text Retrievers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26194 - What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.25732 - Evaluating AI Generated Summaries for Cancer Patients Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26154 - Not Truly Multilingual: Script Consistency as a Missing Dimension in VLM Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.17188 - Training-Time Explainability for Multilingual Hate Speech Detection: Aligning Model Reasoning with Human Rationales Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26125 - Mapping Written Words to Spoken Words in a Different Language Using Only Visual Grounding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26925 - Information-Guided Frontier Decoding: Contextual Utility-Driven Commitment in dMLLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26641 - ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25531 - Scaling phoneme-based TTS augmentation for ASR: A unified pipeline and controlled study Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26697 - Boosting LLM Exploration via Weak-Model Guidance in RLVR Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27420 - Said Aloud, Read Different: Cross-Modal Instability in Multimodal Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27135 - Are Large Language Models Effective Knowledge Graph Constructors? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.11297 - Evaluating Language Models in Realistic Conversational Contexts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26131 - DuMateBench: Evaluating Autonomous Agents in Complex Real-World Workflows Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26546 - Compositional Generalization via Structural Identification in a Category-Theoretic Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26465 - WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27454 - RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24275 - Calibrated Enough to Know, Not Calibrated to Act: Fabricated Evidence Makes LLM Agents Commit to the Unknowable Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27167 - Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting Incentives Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26372 - DeflectBench: A Benchmark for Evaluating Rhetorical Fallacy Generation in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26119 - SCIT: Testing Causal Cache Carriers in Latent Chain-of-Thought Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27265 - Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26379 - Your Voice Cloning System is Secretly a Voice Anonymizer Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27360 - Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.06267 - FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24168 - Dependency-Aware Revocable Decoding for Efficient Diffusion Large Language Model Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26574 - TelecomGPT-R1: A Unified Open-Source Reasoner for the Telecom Stack Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26126 - Double Trouble: Bilingual Pretraining Leaves Language-Conditioned Effects in Shared-Language Representations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26576 - MedFabric: Gold Evidence Hides the Difficulty of Word-Level Medical Fabrication Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.04180 - DocTalkBN: A Novel Dataset of Expert Telemedicine Conversations in Bengali Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27110 - Reward-Informed Sparse Autoencoders and the Solution-Completeness Confound Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26136 - How LLMs Distort Our Written Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18161 - KinyaEmbed: Contrastive Sentence Embeddings for Kinyarwanda via Multi-Stage Curriculum Training Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26941 - Position Is All You Need: A Free Lunch Token Compression Strategy for MLLM-based Referring Expression Segmentation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26142 - Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26807 - CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.04778 - Syntax vs. Semantics: How Transformers Learn Deep Dependencies Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26139 - SpeechGym: An Audio-Native Gym for Training Voice Agents via Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26432 - BTS-AgentBench: A Deterministic, Replayable Pipeline from Read-Only Telemetry Logs to Agent Benchmarks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27334 - ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18037 - Case2Flow: Bridging Patient Cases and Guideline Flowcharts through Multimodal Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26414 - BLANC: Discovering Patent White Space via Changes in Normalized Pointwise Mutual Information Between Multi-View Clusters Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26685 - Translation Asymmetry in LLMs as a Data Augmentation Factor: A Case Study for 6 Romansh Language Varieties Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.25489 - Learning the ARTS of Search for Automated Discovery Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.21891 - From Sound to Symptom: Real-Time Respiratory Signal Understanding for Conversational Healthcare Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26163 - Can LVLMs Uncover the Truth Behind Visual Illusions? An Analysis of Perceptual and Reasoning Capabilities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.27747 - ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01979 - Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16105 - RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26832 - Buried in Textual Debt: Context Pruning with Visual Evidence Preservation for MLLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22963 - Beyond Factual QA: Mentorship-Oriented Question Answering over Long-Form Multilingual Content Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.17173 - Why Knowing Both Hops Is Not Enough: Understanding Two-Hop Generalization in Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.07261 - A Multi-Framework Comparison of Outline Stages in Long-Form Generation with LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26177 - Which India Survives Translation? Narrative Homogenisation Across Indian Oral Traditions in LLMs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26123 - Cross-lingual Representation Learning via Centroid Intervention Fusion Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26357 - Beyond Accuracy: A Qualitative Analysis of Vision-Language Models for Hate Speech Detection in Memes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26143 - STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27161 - The BS-meter: Detecting Politics and Labour through ChatGPT's Language Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2411.15129 - DataSTORM: Deep Research on Large-Scale Databases using Exploratory Data Analysis and Data Storytelling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.06474 - Benchmarking Clinical Decision Pathway Adherence in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26592 - SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09215 - Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26168 - SPT: Skills as Pre-Training Data for Agentic Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26563 - Many Dialects, Many Languages, One Cultural Lens: Evaluating Multilingual VLMs for Bengali Culture Understanding Across Historically Linked Languages and Regional Dialects Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21165 - Comparing Chunking and Embedding Strategies for Turkish RAG Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26192 - Addressing the Reasoning Gap: Mechanistic Circuit-Based Knowledge Editing in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.05876 - The Score Granularity Gap in Black-Box LLM Classification: A Comparative Study of Confidence Constructions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.22179 - Stochastic Estimation of Transduced Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27428 - Towards Expert Financial QA via Self-Improving RAG Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26706 - TwinKV: A Composable Repair Pass for KV Cache Eviction via Pairwise Key Redundancy Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27128 - Knowledge Cards: Structured Knowledge for AI Systems Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26176 - Instruction Quality Matters: Refining Instructions for Effective Preference Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26779 - TTPO: Test-Time Policy Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27448 - When Youth Enter The Chat: An Epistemic Shift in the Validation of LLM-Based Measures of Student Talk Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23780 - Decoupling Planning and Control for Instructable Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26788 - GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.25160 - Why Current XAI Is Not Enough for Arabic NLP: A Critical Survey of the Explainability Gap Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26144 - ExecRubrics: Executable Tool-Augmented Rubrics for Verifiable and Efficient Long-Form Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22559 - PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26700 - CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.02502 - Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26511 - How Unlikely Is "Unlikely"? Assessing Verbal Probability Perception Across Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26327 - ITL: Interpretable Document Alignment with Structured Reference Frameworks Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27031 - Natural-Language Policies to Executable Decisions: An Interpretable Large Language Model Framework Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26124 - Difference-in-Differences on a Censored Rating Scale Can Manufacture an Effect: Evidence from a Pre-Registered LLM-Judge Audit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27309 - D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27380 - RCMN: Understanding Misleadingness in Influential Public Discourse Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27358 - VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26013 - Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.11017 - Planting a Latent Variable in Natural-Looking Text: a More Realistic Test of Belief States in LLMs and Their Link to Concept Geometry Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26887 - Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26596 - Using Poly-Encoders for Computationally Efficient Automated Creativity Assessment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26165 - The Thousand-Graph Hypothesis: A Testable Hypothesis of Task-Conditioned Relation Materialization in Repository-Level Code Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26602 - Cross-Lingual Alignment Without Joint Training: Do Monolingual Language Models Converge on Universal Representations? Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27115 - CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.01942 - BALMS: Benchmarking Agentic LLMs for Longitudinal Mental Health Sensing Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27219 - Visual Information-Guided Parallel Decoding for Diffusion Multimodal Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26580 - Aligned Alone, Misaligned Together: Forecasting Adversarial Capture in LLM Agent Populations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22444 - Vagdhenu: A Vrutta (Meter) Aware Shloka-to-Chant (TTS) System for Sanskrit Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26146 - Multi-Expert Conformal Risk Control for Pairwise LLM Judging in Open-Ended Dialogue Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26529 - PACEShop: Evaluating Personalized, Actionable, Compositional, and Evidence-grounded Shopping Assistants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26180 - Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.14104 - C-Unseen: Weak Signal Detection in Dynamic Temporal Knowledge Graphs via LLM Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26870 - Non-binary bottom-up constituency parsing without arity actions Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.10591 - Neuro-symbolic PRM: Enhancing Scientific Reasoning via Structured Traces and Symbolic Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26329 - Forward-Free Diffusion Language Models with BPTT-Free Looped Refinement Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.08357 - Which Metrics Save the Most Human Annotation? Prediction-Powered Evaluation and Meta-Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26638 - Evaluating Confidence-Gated Retrieval with Matched Trajectory Replay Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26846 - Lost in Compression: A Controlled Cross-Lingual Audit of Extractive Prompt Compressors Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26175 - Distinct Profiles of Run-to-Run Score Reliability and Expert-Panel Alignment Across Four LLM Evaluators of Simulated Japanese-Language AI-to-AI Counseling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.02950 - MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26295 - Pair-Level Essay-Scale Republication and Reuse from Fragmented Historical Text Reuse: A Workflow Study on Eighteenth-Century Books and Newspapers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27343 - Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26587 - LLM-Specific Utility for Retrieval-Augmented Generation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.11358 - Why RAGs Hallucinate: Penalty-Aware Evaluation of Retrieval-Augmented Generation Systems with Knowledge-Gap Canaries Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26385 - Prediction of Prediction (PoP): Inter-Layer Activation Fusion for Single-Pass Hallucination Detection in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27165 - Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inference Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26674 - From Atomic to Agentic: Towards Interpretable Evaluation of LLMs' Agentic Mathematical Capabilities Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26950 - SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26550 - Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27397 - Language Chain in Alignment: Cross-lingual Ranking Preference Optimization Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.23149 - TopiCLEAR: Adaptive embedding clustering for interpretable topic discovery from short texts Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.06694 - What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27260 - DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.12979 - Letters hide the truth from our eyes: English homophones have meaningfully different phonetic realizations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26749 - AEScorer: An Agentic Evidence-Grounded Framework for Graded Factuality Verification Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.03605 - Artificial Intelligence Models Can Predict and Collaboratively Modulate Human Memory Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26152 - RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27394 - INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27348 - When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent Memory Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25553 - Recurrence Meets Transformers for Universal Multimodal Retrieval Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.08897 - GUI-Primitives: Diagnosing Spatial Reasoning Failures in Vision-Language GUI Grounding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21832 - Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.05216 - TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative Decoding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26112 - Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26159 - Data Science Approaches to Evaluating Honours Candidates Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26135 - Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10402 - MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.18383 - CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27455 - Agent Seer: Synthesizing Scenarios from Specification Understanding Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26133 - SkillChain: Closing the Loop on Skill Evolution for Image-Based E-Commerce AI Assistants Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.12984 - Cascaded Batch Prompting Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27038 - BrailleBench: Investigating Multi-Criteria Braille Comprehension in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27268 - Unveiling Spectral Mechanisms in Training-Free LLM Text Detection Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25944 - Selective State-Space Adaptation and Retrieval for Language Model Reasoning Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19326 - MoganColBERT-TR: A Late-Interaction Multi-Vector Retrieval Model for Turkish Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26344 - The Cold-Start Safety Gap in LLM Agents Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.07867 - CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26147 - ElementCheck: Complexity-Aware Long-Form Text Factuality Evaluation via Sentence Elements Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26118 - From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27442 - Representing and Parsing Korean Constituency Structure at Different Levels of Granularity Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27035 - SymbolLKG: Towards Verifiable Logical Reasoning via Logical Knowledge Graph and Symbolic Solvers Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26836 - NestedKV: Nested Memory Routing for Long-Context KV Cache Compression Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.26678 - Agents Don't Paginate: First-Chunk Selection for LLM Tool Responses Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26130 - TabuLM: Morphology-Aware Tabular Pre-training for Low-Resource Languages Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26923 - Mutual Debiasing via Dual-Seed Comparison for Probabilistic Sampling in Large Language Models Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26161 - Towards Interpretable Depression Detection: Linking Acoustic Features to DSM-5 Indicators Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26148 - Mitigating Fabrication in Multi-Stage LLM Pipelines for Hiring: An Empirical Evaluation of Prompt Guardrails and Human-in-the-Loop Checkpoints Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26171 - Meta-Learning Where to Allocate Experts: Task-Conditioned Layer-Wise Compression for MoEs Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26650 - Consolidating RLVR Capabilities Across Domains: A Deep Dive into Fusion Paradigms Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27409 - MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.30931 - AraMS-28k: The Largest Publicly Released Line-Level Dataset of Historical Arabic Manuscripts with Margin and Insertion-Anchor Annotations Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26921 - Beyond Reflection: Affirmation as a Promising Behavioral Marker Associated with Quality in Text-Based Counseling Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26689 - Don't Overthink, Don't Underthink: Toward Adaptive Reasoning in Agentic AI Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26442 - JudgeStealer: Extracting LLM Judging Capabilities across Evaluation Protocols Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26982 - AfriSwitch: A Benchmark for In-the-Wild African Code-Switched Speech Recognition Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26434 - Naive Prompt Optimization: Rethinking the Need for Complex Prompt Search Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27266 - CIFQA: A Deterministic Tool-Grounded Multi-Agent LLM Framework for Financial Query Answering Source: arxiv-cs-cl Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26114 - Benchmarking_Fast_Domain_Adaptation_for_Unsupervised_Speech_Units Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26992 - REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.11698 - Diagnosing Conformal Prediction Failures Under Distribution Shift: A COVID-19 Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.00908 - Soft Active Electromyography Interface for Machine Learning-Enabled Silent Speech Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27048 - UCB for Large-Scale Pure Exploration: Beyond Sub-Gaussianity Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.22273 - Learning New Facts with QLoRA: An Acquisition-Retention Frontier Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25677 - Cross-Platform Generalisation Failure in Mental Health Natural Language Processing: A Five-Axis Fairness Audit of Transformer Models on Social Media Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26138 - Hadamard Flattening and Gaussian Pooling Sketch for Least Squares with Coordinate-wise Guarantee Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26552 - Enforcing Dirichlet Boundary Conditions in Operator Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27256 - GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.18475 - Constraint-Aware Physics-Informed Neural Networks for Static Shape Estimation of Co-Manipulative Continuum Robots Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26273 - A Unified Descriptive-Complexity Framework for Model Selection under Correlated Designs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26618 - Neural Renormalization Group Flow for Percolation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26764 - Absolute indices for determining compactness, separability and number of clusters Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.13065 - Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27413 - GameWAM: A World Action Model for Video Games Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26200 - Reinforcement Learning-Based Control of CAV Platoon Joining Maneuvers in Mixed Traffic Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26860 - HALO: A Heterogeneity-Aware Language-Aligned IMU Foundation Model for Open-Set Human Activity Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27233 - A Flexible Empirical Bayes Approach to Generalized Linear Models, with Applications to Sparse Logistic Regression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.21217 - Active Diffusion-Based Inference for Ill-Posed Inverse Problems under Incomplete Priors Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27080 - The Principles of Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.21890 - TEMPLAR Wales: A georeferenced environmental and toponymic dataset of Welsh settlements Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26970 - Cone Extended Rayleigh Quotients for Directed Graph Learning: Minimax Spectral Certificates, Sensitivity, and Adaptive Control Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27122 - SimCast-S2S: An Efficient Generative Model for Subseasonal Precipitation Forecasting via Transfer Learning from Climate Simulations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26594 - Leveraging Code Automorphisms for Improved Syndrome-Based Neural Decoding Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03620 - Scaling Model-Generated Distillation Data Can Make Latent Teacher Traits More Recoverable Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26958 - Selection Bias Correction in Retail Intelligence Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26156 - LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.04438 - Out of Sight, Not Out of Mind: Unveiling Latent Attack in Latent-based Multi-Agent Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.28214 - Pushing the Envelope of LLM Inference with Ultra-Low-Bit Quantized Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.06753 - Recurrent Reinforcement Learning with Memoroids Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2402.09900 - Circuit Condensation: Post-Training that Concentrates a Behavior's Causal Circuit Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27254 - FlavourBench: Executable Culinary Reward Maps for Language Model Evaluation and Post-Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.20574 - Safety by Design: Realized-Cost Constraints for Contextual Bandits with Continuous Actions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26755 - Packora: Systematic Design for Generative Molecular Crystal Structure Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26962 - TraceBench: Controlled Evaluation of LLM Agents for Time-Series Root-Cause Attribution Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27182 - Incremental Recommendation via Causal Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26804 - Universality and sharp thresholds for ellipsoid fitting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27372 - Shared Actors Need Not Share Critics: Effects of Value Mismatch in Parallel Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26481 - ClassVision: AI-Powered Classroom Attendance System Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26173 - NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26222 - Beyond Capability Benchmarks: Learning Operational Fingerprints of LLM Cloud Services from Production Incident Metadata Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26332 - STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.20781 - TRACE: Retrospective Streaming Generation of Physical Fields under Sparse Structured Sensing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26219 - Squeezing More from Limited Data with Recursive Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26973 - Beyond Parallel Blindness: Information Floors and Model Gaps in Block Drafting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27339 - A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25643 - Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.19020 - DataKernelBench: Can LLMs Optimize Database Queries on GPUs? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25061 - Common Geodesics Do Not Guarantee Fisher Consistency of the Structured SVM: Minimal Counterexamples and a Tree-Metric Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27203 - QuantumBoostNet: A Hybrid Classical-Quantum Architecture for Enhanced Accuracy in Cardiac Ultrasound View Identification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27302 - Dynamical phase selection controls compute scaling in looped transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26556 - MOMO: A framework for seamless physical, verbal, and graphical robot skill learning and adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.20468 - GRAS: Guided Reduced-Variance Proposals and Adaptive Selection for Training-Free Reward Alignment in Discrete Diffusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26585 - A Finite Sample Analysis for Quantile Temporal Difference Learning in Distributional Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27313 - Gromov-Monge Flow Matching for Equivariant Graph Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26961 - TRACE-CRC: Trajectory-Adaptive Conformal Risk Control for Multi-Step Channel State Information Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27124 - Gradient-free learning of a closed-loop wall controller for turbulent drag reduction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.12626 - Linear Independence of Polynomial Compositions and Identifiability of Deep Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27113 - Beyond Client Averaging: A Client-Independent Second-Order Stationary-Bias Component in Stochastic SCAFFOLD Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26765 - Can LLMs Accurately Score Medical Diagnoses and Clinical Reasoning? Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.14892 - NRCD: An Open Database of Collegiate Running with Unified Performance Standardization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.14776 - Tabular Deep Learning for Algorithmic Trading: Cross-Regime Bayesian Optimisation for Equity Signal Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27076 - Residual Reward Models: Leveraging Prior Knowledge for Efficient Preference-based Reinforcement Learning in Robotics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.00611 - Grounded Token Initialization for New Vocabulary in LMs for Generative Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.02324 - Leakage-Free Evaluation and Distribution-Robust Spatio-Temporal Graph Learning for Inductive Kriging Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.23631 - ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23478 - Token-Level Advertising Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27382 - A Unified Framework for Fair and Personalized Decentralized Learning under Communication Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26493 - Cross-simulator transfer with foundation model summaries: Towards robust SKA-era reionization inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26354 - Adaptive Inference for Resource-Constrained Dynamic Pricing Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.03736 - Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.21599 - AdaThinking-E: One-Token Entropy Regulation for Adaptive Thinking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26141 - The Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26423 - Active Curriculum Refinement for Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26469 - Guided Data Generation for Understanding Model Behavior Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2502.06658 - LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot Manipulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.25757 - Vowel Signs Are Not Letters: A Pre-tokenization Ceiling on Multilingual Tokenizer Fertility Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26449 - Explainable Artificial Intelligence for Customer Churn Prediction in Telecommunications: A Framework for CRM Integration Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26151 - Physics-Informed Stochastic Configuration Machine: A Backpropagation-Free Neural Network with Fast Training for Nonlinear Differential Equations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26549 - District-Level Food Environment Indicators and Social Vulnerability in S\~ao Paulo Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26299 - Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.18325 - Bayes with No Shame: Admissibility Geometries of Predictive Inference Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.05335 - The Rashomon Effect for Visualizing High-Dimensional Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.00485 - Co-Evolving Structured Knowledge and Reasoning in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26386 - Learning a Continuous Sepsis Severity Score Without Hour-by-Hour Supervision: A Two-Site Retrospective Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27421 - Daydreaming: Stealing Hidden Agent Skills through Black-Box Task Interaction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26733 - Chart2SVG: Editable SVG Generation from Raster Chart Images Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26544 - FoldPipe: Bounded Remote Streaming of Native Molecular Shards with Asynchronous Prefetch Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27029 - Understanding Evolution Strategies for LLM Reasoning: Broader Reasoning Coverage than GRPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27351 - Can a Model Catch Its Own Hallucinations for Free?: Label-Free Doubt Signals Hold Their Own Against a Labelled Dataset for Abstention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26121 - Recipes for Steering and Scaling LLMs via Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26120 - FIRSTPASS: A Multi-Domain, Multi-Round Peer Review Dataset Grounded in Real Editorial Outcomes Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26129 - COFM: Consistent Optimal Transport Flow Matching via Partially Input Convex Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2511.06042 - Graph-Based Modeling of Financial Volatility Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26127 - Toward Equitable Low-Carbon Mobility: Fairness-Aware Demand Prediction for Expanding Bike-Sharing Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26451 - When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismograms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.10868 - Hierarchical Channel Stacking: A Structured Decision Framework for AI-Generated Image Detection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26648 - MCCE: A Framework for Multi-LLM Collaborative Search in Discrete Spaces with Similarity-Filtered Preference Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.06270 - From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2505.22203 - Technical Comparative Benchmarking Study: Advanced AI Hybrid Methods for Renewable Energy Farm Optimization and Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26613 - How Language Models Organize and Structure Moral Knowledge Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27402 - High Probability Derivative Bounds for Random tanh Neural Networks on a Hypercube Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26526 - Active Preference Learning over Latent Preference Archetypes for Many-Objective Bayesian Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.28410 - Predicting Quantifiability from Primary Screens to Prioritize Dose-Response Profiling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26538 - A Real-Time Tsetlin Machine-based Non-intrusive Load Monitoring System on MCUs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18780 - Mitigating Strong-Modality Collapse in Multimodal Learning via Inverted Asymmetric Fusion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26879 - Tensorion: A Tensor-Aware Generalization of the Muon Optimizer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.25975 - Beyond FLOPs: Benchmarking Real Inference Acceleration of LLM Pruning under a GEMM-Centric Taxonomy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.09080 - Affix Cache for Diffusion Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26140 - SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26132 - Ultra Low-Power, Lightweight, Probabilistic RSS-Based Path Reconstruction: A System for Landscape-Scale Bee Tracking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27152 - Over-The-Air Extreme Learning Machines with Nonlinear Stacked Intelligent Metasurfaces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27137 - Curating Same-Family Neural Networks for LLM-Guided Model Improvement: A Controlled Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.05704 - The Attribution Contract for Generative Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23080 - Learning to Predict, Discover, and Reason in High-Dimensional Event Sequences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.16313 - J-Zero: Unified Challenger--Solver--Judge Co-Evolution from Zero Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26582 - Towards a universal meta-optics solver via large language models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26417 - ClusterAttention: A training-free speedup of bidirectional attention Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26965 - Neural Regression with Embeddings for Numerical Attribute Prediction in Knowledge Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26729 - Disentangling Optimization Scale from Preference Scale in DPO Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27032 - Profit based evaluation of machine learning for nitrogen recommendations in winter wheat Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27205 - Auditing Invisible Weight Updates with Reference Traces Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.09800 - Inductive Correlation Clustering with Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27153 - When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.07050 - Keeping the Index Open: The Recommendation-Side Cost of Shared Search and Recommendation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24079 - Distributed Training using an Intelligent Network Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26453 - TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.23838 - VQC-ZTI: Variational Quantum Control for Zero Trust Protection of the Tactile Internet Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.18572 - Rethinking Expressivity and Efficiency in Test-Time Training Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21308 - Algebraic Multigrid Acceleration for Efficient Label Spreading Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26309 - A Dynamic Likelihood Approach to Filtering for Advection-Diffusion Dynamics Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.06837 - Adversarial Training Without Input Gradients via Low-Rank Householder Expansions Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26963 - Robust Neural Stimulation Response Modeling Through Meta-Learning and Pretraining Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26649 - ReLATE: Accelerating Tensor Decomposition via Safe and Efficient Learning of Sparse Encodings Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.00280 - MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.13463 - Systematic Literature Review of Machine Learning Models and Applications for Text Recognition Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26500 - AirLLM: Diffusion Policy-based Adaptive LoRA for Remote Fine-Tuning of LLM over the Air Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2507.11515 - A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26926 - A unified convergence theory for adaptive first-order methods in the nonconvex case, including AdaNorm, full and diagonal AdaGrad and Muon Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.17423 - Generative Semantic Scene Completion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26737 - Equal Ranking Quality, Different Decisions: Training Order-Consistent LLM Scorers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26762 - Account Consistency from Gameplay Traces: Same-Player Verification in Counter-Strike 2 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24893 - Prompt Sensitivity of Generative Agents: Evidence from an Epidemic Model Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26221 - Toward all-optical unsupervised Hebbian learning in deep photonic neuromorphic networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.22300 - Modular Expert Merging for Biomedical Retrieval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.04731 - CAT-GS: Balanced Multimodal Learning via Calibrated Gating and Fusion Surgery Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24947 - Diffusion Policies for Short-Horizon Planning in Robot Crowd Navigation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27158 - A causal graph-informed temporal convolution architecture for interpretable retail electricity price forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26234 - PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.23390 - SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26683 - Methodological and Conceptual Framework for 5D Multi-Table Analysis: A Unified Approach for Complex Data Reuse Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26149 - A Very Big Video Reasoning Suite Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.20159 - Invocation-Level Reliability of Tool-Using Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26189 - Quantitative mapping from conventional MRI using self-supervised physics-guided deep learning: applications to a large-scale, clinically heterogeneous dataset Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2601.05063 - Cartan flow matching Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.03588 - Terrain signatures in Welsh settlement names Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26978 - Provable one-poison backdoor attacks on linear models and ReLU neural networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.05600 - Unsupervised Post-Training of Foundation Models: A Survey Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24982 - MM-Spectrum: Multimodal Multi-spectral Molecular Structural Elucidation with a Stable MoE Framework Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27286 - Representation Measurements Under Function-Preserving Reparameterizations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27020 - How AI Experiences Art: Emergent Aesthetic Structure in a Self-Supervised Multimodal Embedding Space Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27121 - Performance Foundations of Parallel & Distributed Reasoning Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27046 - SAGA: Score-Weighted Adaptive Generation Alignment for Low-Resource Nordic Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.06179 - Hyperspectral Diffusion Equivariant Imaging (HyDiff-EI): A Self-supervised Framework for Hyperspectral Image Inpainting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26812 - A Survey of LLM Prompt Datasets: Taxonomy, Linguistic Patterns, and Practical Uses Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.09316 - Clinically Aligned Geometry Constraints for Robust IVUS Vessel Boundary Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.18723 - Private and interpretable clinical prediction with quantum-inspired tensor train models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2602.06110 - Privacy Without Regret: Differentially Private Inference-Time Alignment Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26324 - Decoupled Physical Modeling and Execution for Physics Reasoning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22126 - Diff Mining: Logit Differences Reveal Finetuning Objectives Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26462 - Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27066 - When Interference Graphs Evolve: Doubly Robust Estimation of Dynamic Peer Effects Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27187 - CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27391 - Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26069 - LLMs Can Design Near-Optimal OR Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27296 - On the Indistinguishability of Human v/s AI Generated Text Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26797 - Emotional Preferences as Goal-Priority Regulation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27072 - Activation Outliers Matter: Robust Recovery for Quantized Multimodal LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26581 - Self-Augmented Diffusion Guidance for Physics-Informed Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26748 - HINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.17873 - A Framework for Low-Effort Training Data Generation for Urban Semantic Segmentation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2510.11567 - CG4AI: A Column Generation Framework for Training AI Models Under Constraints Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26375 - Stable but Wrong: When Learning Stabilizes Away from the Truth Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.21491 - On Scope Classification and Current Knowledge-Editing Benchmarks: A Negative Result, with INLAY as a Gradient-Free Case Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26292 - Subgraph Filtering for Fair Graph Neural Networks Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26437 - LLM Analysis of 150+ years of German Parliamentary Debates on Migration Reveals Shift from Post-War Solidarity to Anti-Solidarity in the Last Decade Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.07274 - You Don't Need to Run Every Eval Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2606.24020 - Dose-PlanNet: Physics Based Radiotherapy Dose Prediction with Deep Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26901 - Arrive and Survive: Scaling Safe Goal-Conditioned Policy Learning from One-Bit Failure Signals Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26571 - Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.24977 - A Point-of-Prescription Safety-Check System for Adverse Drug Reactions in Rural Bangladeshi Hospitals: A Feasibility Study Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27239 - Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness Bugs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26209 - NeoTriFuse: Reliability-Aware Multimodal Fusion under Missingness Heterogeneity for Neonatal Mortality Risk Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26436 - Sharp Minimax Regret for Infinite-Memory Logistic Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26515 - Sequential Additivity in Distributionally Robust Ranking and Selection Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2509.06147 - SynthCharge: An Electric Vehicle Routing Instance Generator with Feasibility Screening to Enable Learning-Based Optimization and Benchmarking Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.03230 - SAGE: Variate-Wise Semantic Augmentation for Vision-Language Time Series Forecasting Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26829 - Global universality via discrete-time signatures Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2603.09773 - SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27108 - Neural Non-Equilibrium Hamiltonian Monte Carlo for Corrected Boltzmann Sampling Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2607.15682 - Data-efficient crack quantification in lithium-ion cathodes using foundation model transfer Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27162 - Stack Trace-Based Crash Deduplication with Transformer Adaptation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2508.19449 - Multi-Dataset Inverse Problem Solving with Distributed Generative AI Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26283 - Importance Scoring of Transformer Attention Heads in Learning Tabular Data Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27241 - Refusal Is Not Robustness: Auditing Confident Fabrication in Large Language Models on a Provably Uninformative Clinical Pain Speech Transcript Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26167 - Algorithmic Principles For Multiclass Learning Are Hard To Come By: Limits of Regularization and Proper Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26516 - Real-time virtual circuits for plasma shape control via neural network emulators: integration and testing in the MAST-U PCS Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26216 - Unifying Detection and Adaptation in Task-Free Continual Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27070 - Bregman Linearized Augmented Lagrangian Method for Nonconvex Constrained Stochastic Zeroth-order Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.09409 - Why not to use the Gaussian kernel Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26974 - When the Canonical Completion Is Wrong: Formalizing and Measuring the Jump in Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26187 - Learning Generalizable Behaviors for Terminal Agents Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22631 - Gaussian Processes and Reproducing Kernel Hilbert Spaces: Connections and Equivalences Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2506.17366 - When Is the Sharp Covariance Envelope Tight? Feature-Only Geometry for Volume-Sampled Least Squares Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26877 - Decentralized Multitask Learning over Learned Task Graphs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26989 - When Does Latent Communication Pay? A Causal Audit of Relayed KV Caches in Multi-Agent LLMs Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.04893 - CollaFuse: Collaborative Diffusion Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2406.14429 - Interpretable, Fairly Evaluated Automated L2 Speaking Assessment that Beats the Single-Human Ceiling and Why Pause Encoding Does Not Change LLM Fluency Scores Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26137 - Rethinking Message Passing as Retrieval for Text-Attributed Graph Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26732 - Domain-Specific Self-Supervised Representation Learning for Retinal Fundus Classification Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26686 - When Is Noise Response Universal? Tokenization as the Hidden Variable in Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26319 - MambaCSP: Hybrid-Attention State Space Models for Hardware-Efficient Channel State Prediction Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.21957 - Complexity Induction: Compositional Generalization via Structured Training Distortion Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.21464 - MODIS: Multi-Omics Data Integration for Small and unpaired datasets Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2503.18856 - Muon with Finite Newton-Schulz: The Smoothing Benefit in Nonsmooth Nonconvex Optimization Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26288 - $p1$: Better Prompt Optimization with Fewer Prompts Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2604.08801 - A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26506 - FOCUS & RePAIR: Mitigating Text Degeneration via Token-Level Guidance for Pruned Large Language Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26676 - Bridging short- and medium-range weather forecasting with machine learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26822 - Federated Adversarial Training with Transformers Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2206.02131 - Simple Actors and Deep Critics for Scalable Reinforcement Learning Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26659 - From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.23955 - When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27176 - Generative Monte Carlo Sampling for Constant-Cost Particle Transport Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2512.13965 - Interpreting Latent Protein Language Model Features with Geometric Annotations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26419 - LowRankArena: A Standardized Evaluation Platform for SVD-Based LLM Compression Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26389 - Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.22642 - Making Latent Evolution Explicit: Operator-Structured Transitions for World Action Models Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27259 - Data-driven Koopman mode approximation: A neural power iteration algorithm Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26943 - Pruning Binarized Neural Networks: A Dedicated Framework and Globally Weighted Algorithms Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26233 - Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26355 - Classical and Hybrid Quantum Machine Learning for Trigger-Like Event Selection on CMS Open Data: An Eight-Qubit, PCA-Constrained Benchmark Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26224 - hoBIT: A Profile-Aware Retrieval-Augmented Chatbot for University Academic Advising Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26604 - Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090 Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27370 - When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacy Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26655 - Plain Transformers Can be Powerful Graph Learners Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2504.12588 - Recovering Expert Critic-Sourced Network Adjacency between Musical Artists from Acoustic Distributions: A Construct-Validity Approach Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.27291 - FedCMAPSS: A Benchmark for Federated Learning in Remaining Useful Life Estimation Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26433 - Bayesian methods and Markov chain Monte Carlo algorithms for curve reconstruction and point cloud data analysis Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26490 - Aitchison Embeddings for Learning Compositional Graph Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2605.00716 - Graph-Based Pseudo-multimodal Contrastive Learning for 12-Lead ECG Representations Source: arxiv-cs-lg Topic: AI Research (+AI) URL: https://arxiv.org/abs/2608.26964