TILens Daily Edition
2026-09-14
Filters: topic=ai-research, github=hidden

Stats: 378 articles, 5 sources, 372 research papers
Top topics: AI Research, AI, Information Retrieval

## News

- U.S. AI Leaders Want to Slow Down. China Offers No Such Promise.
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/news/us-ai-slowdown-china-response/

- AI Is Turning Intelligence Into Infrastructure. Who Owns the Pipes?
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/news/ai-intelligence-infrastructure-who-owns-the-pipes/

- AI Safety’s New Paradox: America May Need a Bigger Lead to Slow Down
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/explainer-articles/ai-safetys-new-paradox-america-may-need-a-bigger-lead-to-slow-down/

- AI's biggest rivals agree: slow down
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/newsletter/ai-s-biggest-rivals-agree-slow-down/

- OpenAI’s IPO Can Wait. Can Its Investors?
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/news/openai-ipo-delay-ai-safety-investors/

- Can AI Companies Afford to Slow Their Own Progress?
  Source: the-neuron-ai
  Topic: AI (+AI Research)
  URL: https://www.theneuron.ai/news/can-ai-companies-afford-to-slow-down/

## Research

- Your Model’s MSE Is Lying to You
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/your-models-mse-is-lying-to-you/

- When to Use One Model and When to Use a Team of Agents
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/when-to-use-one-model-and-when-to-use-a-team-of-agents/

- Graph Engineering for AI Agents: From Prompts and Loops to Workflows
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/graph-engineering-for-ai-agents-from-prompts-and-loops-to-workflows/

- From Static to Dynamic Skills: A Different Model for Agent Knowledge
  Source: towards-data-science
  Topic: AI Research (+AI, Python)
  URL: https://towardsdatascience.com/from-static-to-dynamic-skills-a-different-model-for-agent-knowledge/

- I Am No One: Style-Aware Paraphrasing for Text Anonymization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12341

- PACIFIC: Can LLMs Discern the Psychometric Traits Influencing Your Preferences? Personality-Driven Preference Alignment in LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.07181

- Beyond ID Embeddings: Process-Grounded Language Modeling for Cognitive Diagnosis
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12403

- CueMem: Cue-Guided Context Reconstruction for Long-Term Conversational Memory
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12354

- ORQA: An Occupation-Realistic Question and Answer Framework for LLM Professional Knowledge
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12366

- From Bench-to-Bedside: A Review of Clinical Trials in Drug Discovery and Development
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2412.09378

- MedSNIP: Building and Benchmarking Snippet-Level Granularity for Medical Fact Verification
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12884

- HypoKG: Evidence-Disciplined Biomedical Hypothesis Generation Beyond Endpoint Knowledge
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12260

- Continue, Adapt, or Yield: In-Turn Adaptation to Overlapping Speech in Full-Duplex Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13117

- Measuring Pragmatic Influence in Large Language Model Instructions
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.21223

- SteerDuplex: Steerable Duplex Speech Dialogue Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12623

- Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11987

- Doc2FRC: Length-Consistent Document-Level Machine Translation via Fixed-Range Chunking
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12674

- SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13141

- When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document Contamination
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.09696

- Agent as Policy for Robotic Manipulation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12541

- Can LLMs in Draft-Verify-Revise Pipelines Resolve Deictic Ambiguity?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12162

- False positive bias in AI-powered speech-based cognitive screening for multilingual English speakers in the UK
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.13047

- The Cost of Compression: A Rate-Distortion Limit on Factual Hallucination
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12111

- Quantifying Consonant Contributions to Word Intelligibility via Acoustic Masking
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12122

- Expert-Space Exploration in MoE Reinforcement Learning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13058

- Diverse Minds, Divided Networks? Personality Composition, Polarization, and Collective Intelligence in LLM-Based Social Simulations
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12444

- Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.23989

- When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.21203

- Repair Before Reinforce: Context-Augmented Knowledge Graph Reasoning for Multi-Hop Question Answering
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12230

- Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.23189

- Is Bash All You Need? An Empirical Study of Tool Interfaces for Enterprise Digital Worker Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11999

- Is Multilingual LLM Watermarking Truly Multilingual? Scaling Robustness to 100+ Languages via Back-Translation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.18019

- Residual Vector-based Reconstruction as Long-Context Recall Regardless of Context Window Size
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12686

- Confidence-Gated Transductive Test Generation for Code Reranking
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12489

- Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12475

- MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13076

- Closed-Loop Bayesian Molecular Inverse Design with Semantic LLM Surrogates
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.22967

- Representation-based Masked Diffusion Model
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12382

- AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.19363

- Statistical Mechanics of Semantic Compression
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2503.00612

- Automated Detection and Structuring of Social Tipping Point Evidence in Climate related Documents: A Modular AI Framework
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12254

- LLM-Enhanced Dual-Branch Learning for Large-Scale Multi-Label Text Classification
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12915

- Creating an Atomic User Model for Personality-Aware Large Language Model Interaction
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12086

- Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based Moderation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.22230

- LLM-BabyBench: Can Language Models Plan in Worlds They Can Simulate?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.12135

- Meddies-PII: A Multilingual Framework for Personally Identifiable Information Extraction in Clinical De-identification
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12544

- SynthSentry: Detecting Synthetic Data Contamination in Language Model Training Data
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12353

- LifeMem: Enabling Lifelong Experience Reuse for LLM Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12655

- DuplexDrama: A Synthesized Dialogue Dataset with Scenarios, Full-Duplex Behaviors, Expressive Speech, and Sound Events
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12872

- A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.08644

- Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.10410

- The House with a Million Windows: Interactive Fiction for Narrative Restorying
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12537

- UrduFactCheck: An Agentic Fact-Checking Framework for Urdu with Evidence Boosting and Benchmarking
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.15063

- Kraken: LLM-based Speech-to-Speech Translation via Low-bitrate VQ and Dual-path Source Conditioning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13045

- MMGR: Multi-Modal Generative Reasoning Benchmark and Evaluation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.14691

- Language Models for Portuguese: A Systematic Mapping Study
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18138

- ReasoningFlow: Discourse Structures for Understanding LLM Reasoning Traces
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.05402

- On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.12234

- Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.22660

- From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.08899

- Calibrated Ambiguity in Multimodal Language Models: Humans reach for cultural references, while models describe the picture
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12575

- Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12446

- AMDKernelVault: Large-Scale Datasets and Agentic Training for AMD GPU Kernel Optimization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12471

- NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.01971

- What Counts as a Mistake? Annotating Recitation Events in Quran Memorization Transcripts
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12085

- Translationese as a Rational Response to Translation Task Difficulty
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.12050

- Do Multimodal LLMs See Before They Read? Diagnosing Contextual Sycophancy
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.00067

- GeoSense-AI: Fast Location Inference from Crisis Microblogs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.18225

- Investigating Temporal Motion Features for Pose-to-Text Indian Sign Language Translation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12993

- NSIDDx: A Design Framework for Neuro-Symbolic, Practitioner-First Differential Diagnosis in Low-Resource Settings
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.00256

- KoSimpleQA: A Korean Factuality Benchmark with an Analysis of Reasoning LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.18368

- Earth-Agent-Pro: Towards Real-World Full-Chain Earth Observation with Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12533

- Not All Speech Is Intent: Adaptive Self-Correcting Inference Layer for Post-ASR False Wake-Up
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12469

- Information Specialization and Constrained Synthesis in Multi-Agent LLM Forecasting: A Prospective Live-Study of the 2026 FIFA World Cup
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12495

- LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.10531

- Fewer Words, Not Fewer Tokens: Measuring the Sanskrit Tokenization Penalty per Proposition
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12960

- UrduMMLU: A Massive Multitask Benchmark for Urdu Language Understanding
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.07167

- GraphProfiler: Source-Linked Sensitive Attribute Inference via Personal Knowledge Graphs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12448

- PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11559

- Parameter-Efficient Retrievers for Polish and European Languages
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12913

- EvoHarnessBench: Can Your Agents Keep Pace with an Evolving Harness?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.04280

- All Entities are Not Created Equal: Examining the Long Tail for Ultra-Fine Entity Typing
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2410.17355

- Local Edits, Global Ripples: Replay-Informed Policy Adaptation for Workflow Synthesis
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12127

- Text-to-SPARQL Generation with Reinforcement Learning: A GRPO-based Approach on DBLP
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.20066

- Population-level measures of perceived food access reveal barriers beyond geographic proximity
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12132

- SWARM: A Multilingual Human-Annotated Dataset for Russian Propaganda Detection in Search Engine Results
  Source: arxiv-cs-cl
  Topic: AI Research (+AI, Information Retrieval)
  URL: https://arxiv.org/abs/2609.12653

- Chopthin-Consensus Power Sampling: A Diversity-Preserving Approach to LLM Decoding
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12243

- Expert-Level Crisis Detection in Mental Health Conversations
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.10380

- Tasks over Application Manuals: Revealing Gaps in Long-Horizon Procedural Reasoning for Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI, JavaScript, React)
  URL: https://arxiv.org/abs/2609.13005

- ShadowPEFT: Shadow Network for Parameter-Efficient Fine-Tuning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.19254

- SeDeM: Selective Decompression of Hidden-State Memories for Long-Context Question Answering
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.00311

- Type Diversity Enables Transformers to Generalise Compositionally
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13144

- Recommendation Retrievers Need Verifiers: Universal Generative Reranking for Sequential Recommendations
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12270

- ChronicleRec: Pre-training Temporally Anchored Tokens for Lifelong User Modeling
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12375

- InitGen: Candidate Generation for Interaction Initiation in Intelligent Assistants
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.11953

- MIMA: Multi-Interest Recommendation via Multi-Positive Exclusive Assignment
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12842

- Extracting Dataset Mentions in Forced Displacement and FCV Documents: A Weakly Supervised Framework with LLM-Based Label Refinement
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12107

- EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12268

- Membership Inference Attacks on Recommender System: A Survey
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2509.11080

- Cognition on Graph: Navigating Massive Knowledge Space via Cognitive Cycles and Bidirectional Graph-Text Synergy
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12791

- OneLA: Scaling Linear-Attention Decoding to Large Beams in Generative Recommendation
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12399

- Guaranteeing Faithful Evidence Extraction in Speculative Retrieval-Augmented Generation
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.10046

- Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2606.10388

- Total Recall QA: A Verifiable Evaluation Suite for Deep Research Agents
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2603.18516

- Personalized and Trust-Aware Health Recommendation Policies for a Construction Workplace
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12679

- A Historical Corpus Is Not a Historical System: Auditing Hindsight Leakage in Stateful Data Discovery
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12766

- Preference-Drift-Aware Subsequence Learning and Hierarchical Context Fusion for Long-Sequence Generative Recommendation
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12556

- Who Are We Recommending To? Recommender Systems in the Agentic Web
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.11945

- Position: Recommender Systems Should Move Beyond Platform-Centric Ranking toward Personal Agent-Mediated Recommendation
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.11942

- Cortex: Content Analysis Support Software, a Resource for Qualitative Research
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.11970

- MemRetriever: Learning to Search, Reflect, and Retrieve from Long-Term Memory
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research, JavaScript, React)
  URL: https://arxiv.org/abs/2609.11951

- Learning the Lake: Reliable Experience for Adaptive Data Product Discovery
  Source: arxiv-cs-ir
  Topic: Information Retrieval (+AI, AI Research)
  URL: https://arxiv.org/abs/2609.12754

- GUIDE: Generative Utility Inference and Decision Engine
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12137

- Patient-Reported Survey Data Improve Prediction of Opioid Use Disorder
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12224

- GRACE-DS: a Guarded Reward-guided Agent Correction Environment in Data Science
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.16000

- UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.16696

- Tight Sampling Complexity with stochastic gradient oracles in Fixed Dimensions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12590

- Geometric-to-Semantic Spherical Transfer Learning for Cortical Sulci Labeling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12627

- Multi-Modal Time Series Prediction via Mixture of Modulated Experts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.21547

- On Universality of Non-Separable Approximate Message Passing Algorithms
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.23010

- Performance, Efficiency and Collapse -- Advantages and Challenges in Offline Post-training of Code LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11956

- A Differentially Private Federated Proximal Optimization Framework for Customer Churn Prediction in Heterogeneous Federated Telecom Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12470

- Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.07357

- Very Exciting: Zero-Shot Model Predictive Control of Buildings via Excitation-Based Generalized Transfer Learning Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12853

- Language Is an Insufficient Substrate for Quantitative Reasoning, and Consequential Domains Need Large Quantitative Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12105

- FRIST: FMRI Representation Informed Shared-space Training Improves EEG-only Individual-Finger BCI Decoding
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12298

- Theoretical Guarantees for One-Shot Magnitude Pruning and Compute-Adaptive Early Exit
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12337

- The BatchNorm Illusion: Diagnosing Normalization Artifacts in Machine Unlearning Evaluation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.08901

- Protect Your Score: Contact Tracing With Differential Privacy Guarantees
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2312.11581

- PA-CDM: Position-Aware Character Detection Matching for Evaluating Handwritten Mathematical Expression Recognition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12917

- A unified self-supervised framework for single-frame Fresnel CDI and overlapped ptychography
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.21361

- Space as an Interventional Invariant: Cross-Modal Predictive Geometry for Stratified Cities and Em-Spaced Intelligence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11959

- Diffusion Models and Concept Formation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13047

- Inverting Self-Triggered Control: Adversarial Reinforcement Learning for Sparse Denial-of-Service Attacks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12016

- A Unified and Constrained View of Regularization-Based Robust Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13050

- Nonlinear Dimensionality Reduction Techniques for Bayesian Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.15435

- On-Device Language Models for Privacy-Preserving Stress Prediction: A Multimodal Evaluation on Mobile Health
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11961

- What an odour descriptor corpus can and cannot measure: valence, attenuation, and the ceiling of the public record
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12875

- Learning Interaction Kernels from Collective Steady States
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12004

- Distortion of AI Alignment Revisited: RLHF is a Decent Utilitarian Aligner
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12651

- Write on Paper and Get the Online Digital Trace:\newline A New Era for Handwriting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12702

- Physics-enriched neural solvers for transient ice-flow simulation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12900

- Classical and quantum kernel fusion for two-sample testing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.20941

- QTrans: A Quantum Transformer for Sentiment Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12011

- Offline Reinforcement Learning for Wind Farm Control: A Wind Tunnel Study under Dynamic Wind Directions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12905

- Transformers as In-Context Samplers: From Closed-Form Diffusion to Estimation-Free Sampling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.08981

- R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence Calibration
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11955

- GenOR-Twin: A Semantic Middleware for Integrating Operational Discourse with Mathematical Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12863

- UltraQuant: 4-bit KV Caching for Context-Heavy Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.20474

- Physics-Guided Synthetic High-Frequency Ultrasound Generation for Skin Layer Segmentation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12735

- Denoising as Projection: Constrained Optimization with Gradient-Guided Diffusion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.29507

- Information-Induced Training Geometry: Exact Reduction, Canonical Completion, and Structured Expressivity
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12991

- Deep learning methods for inverse problems using connections between proximal operators and Hamilton-Jacobi equations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.23829

- Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at Best
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.07627

- Quality-Constrained Routing over a Fixed Pool of Quantized Mixture-of-Experts Instances
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12550

- Explaining Time Series Forecasting with Horizon-Resolved Attribution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12639

- Affective Agent: On-Device Personalized Intervention Reasoning for Wearable Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12322

- Explanations-Driven Active Feature Acquisition for Algorithmic Recourse
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12179

- Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12277

- Agentic TCAD Calibration Workflow for Oxide Semiconductor Transistors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12184

- RunningTensor: Generalizing Linear Attention to Higher-Order Recurrent States
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12814

- One Simple Trick for Improving the Performance of Energy-Limited Local Inference and Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11936

- Rank-Efficient LoRA via Joint Tangent-Space Optimization under Isotropic Curvature
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12123

- An Empirical Markov Chain Car-Following (MC-CF) Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.27909

- From Information to Delegation: Mapping Human-AI Financial Decision Making
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.02100

- The Rank the Task Demands: A Causal Rank Law for Matrix Memories Trained on Group Composition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12259

- The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devices
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11940

- Learning-Augmented Optimization for Strategic Two-Echelon Spare Parts Network Design
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12524

- Beyond Solver Verdicts: Generative Reward Models for Autoformalization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11085

- When Connected Does Not Mean Similar: Charting the Homophily Boundary of SNAP-KG for Streaming Entity Integration
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12356

- Robust Policy Optimization via Adversarial Importance Sampling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13044

- Behavior Quotient Learning for Low-Rank Adaptation of LLM Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12896

- Satisficing Regret Minimization in Bandits: Constant Rate and Light-Tailed Distribution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2406.06802

- FINESSE: An Agent-Based Simulator and Benchmark Dataset for Multimodal Financial Event Sequences
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11993

- Explainable Prediction from Mobile Sensing Data through LLM-guided Concept Integration
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11995

- Machine Learning-Based Classification of Jhana Advanced Concentrative Absorption Meditation Using 7 Tesla Functional Magnetic Resonance Imaging
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.13008

- Amortized Low-Rank Adaptation for Model-Based Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12278

- Membership Inference via Pairwise Likelihood Ratios
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12367

- Are We Really Doing Few-Shot Learning? A Critical Examination of Pre-Training Assumptions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.10851

- Decomposing Discrimination: Causal Mediation Analysis for AI-Driven Credit Decisions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.27510

- Split Conformal Prediction with Label-Shift-Adjusted Bayesian Scores
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12386

- LLM Compression by Block Removal with Constrained Binary Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.00161

- Limits of LLM Text Detectors in Education
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.08096

- Evidence-Aligned Local Composition of Discrete Experts for Sequence Restoration
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.05801

- Impact of Multiple Non-Invasive Biosignals on Cardiovascular Biomarker Estimation via Simulation-Based Inference
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11969

- Towards Sustainable Hydrogen Systems: Supply Chain Optimization with Model Predictive Control and Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11933

- On the Residual Scaling of Looped Transformers: Stability and Transferability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.18524

- Fast BIB simulation at a future Muon Collider with generative machine learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12054

- ESTS at WMT26: Routing-Informed Expert Pruning for Model Compression
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12310

- ProactiveBench: Can Streaming Video Models Really Interact Like Humans?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12658

- CRFCAN: A Complex-Valued Cross-Domain Residual Network for Joint Channel and Phase Noise Estimation in Sub-THz OFDM Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12244

- What Did the MLLM Hear? Token-Level Spectro-Temporal Grounding for Audio MLLM Explainability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12663

- Byzantine-Robust Federated Fire Detection with a Rotating Coordinator
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.10647

- PEARL: Structural Privacy-Utility Control in Human-Centric CPS via Personalized Early-Exit Deep Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2403.05864

- Beyond Accuracy: Uncertainty-Guided Boundary Refinement for Reliable Biomedical Image Segmentation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12892

- DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.11265

- LoRA-RC: Reservoir Computing with Low-Rank Adaptation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12327

- Improving Energy Efficiency of Oil Platforms Through Optimal Loading of Diesel Generators Using Machine Learning and Search Algorithms
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.22076

- Inferring Dislocation Microstructures from X-ray Diffraction via Cross-Modal Contrastive Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12713

- A Multi-Vehicle Dataset with Camera, LiDAR, and Radar Sensors and Scanned 3D Models for Custom Auto-Annotation using RTK-GNSS
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12871

- SCOPE-OPSD: Fisher-Conditioned Privileged Subspaces for On-Policy Self-Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12579

- BRIDGE-EEG: Bridging Self-Supervised Pretraining and Efficient Deployment for Cross-Dataset EEG Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12218

- Fundamental Dynamical Units for Physics-Informed Structural Inference from Perturbation Time-Series in Networked Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11934

- Efficient Vision-Language-Action Management and Serving for Robot Factories
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12075

- Certifying Concept Unlearning in Text-to-Image Diffusion Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12163

- AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2507.01663

- Trainability-Oriented Hybrid Quantum Regression via Geometric Preconditioning and Curriculum Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.11942

- 3D Digital Twin Visualization of Multiclass GRF-Based Gait Disorder Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12442

- Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.04269

- Estimating Pedestrian Volumes from GIS-Derived Built-Environment Features: A Machine Learning Framework
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12173

- Dissecting GPU Utilization for LLM Inference on Nvidia Hopper
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12923

- State-specific respiratory signatures for affective and stress recognition: Interpretable respiratory markers, autocorrelation lags, and compact CNN models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.26723

- 4D Parallelism Unlocks Exascale Bayesian Neural Networks for High-Fidelity Atmospheric Modeling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12815

- Surrogate Modeling of 3D Rayleigh-Benard Convection with Equivariant Autoencoders
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.13569

- Improving precipitation forecasts in an AI weather model using observational data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.03210

- Breaking the Token Ceiling: Distilling Smaller, Stronger Byte Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12303

- Hidden in Rounds: Predicting the Time Cost of 802.11 Contention in Federated Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12903

- Hurdle-RMIL: Addressing Zero Inflation and Long-Tailed Imbalance in Infrared Rainfall Retrieval
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.20486

- Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.08335

- MCRL2: Multi-resource Cross-attention-based Representation Learning-augmented Reinforcement Learning for Cloud Microservice Scheduling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13048

- $\text{GSF-}\chi$: Global Stereochemical Fields for Chiral Graph Transformers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12532

- A Generalized Tangent Approximation based Variational Inference Framework for Strongly Super-Gaussian Likelihoods
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2504.05431

- When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.07318

- Beyond the Query: Do Retrieval Signals Improve Adaptive Multimodal RAG Routing?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12437

- Diffract: Spectral View of LLM Domain Adaptation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10850

- Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.15015

- A Full Adam Theorem for Spectral Heavy-Tail Onset
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12996

- AnyView: Synthesizing Any Novel View in Dynamic Scenes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.16982

- Accelerating battery research with an interoperable interface between FINALES and Kadi4Mat
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.00909

- Almost Free State Prediction Separation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.03807

- Curriculum-Based Adversarial Heterogeneous Agent Reinforcement Learning for Autonomous Quad-Copter Landing in Maritime Settings
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12758

- Learning the Geometry of Collider Events with Metric-Aware Deep Sets
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12024

- Decoding Mixture Perception through Computational Modeling of Component Interactions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11958

- SAGE-Loop: Reliable Closed-Loop LLM-Driven AutoML with Trial-and-Correction and Adaptive Ensembling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12455

- Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12454

- In-Hospital Stroke Risk-State Classification from PPG-Derived Hemodynamic Features
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.09328

- Dual-guided Hierarchical Edge Localization for Large-scale Optimal Transport Across Dimensions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13010

- Robust Prototypical Networks for Few-Shot Sensor Fault Diagnosis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12287

- Observation-Anchored Selective Assimilation for Longitudinal Tumor-State Proxy Forecasting in Post-Treatment Glioma
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12435

- DynSHAP: Towards Explainable Dynamic Survival Analysis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13042

- Scaling Online Complex Event Detection with Synthetic Supervision and Mamba-Based Neural Algorithmic Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2502.07250

- CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13060

- On Identifying Adversarial Intent Injection in AI-Native 6G Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12144

- A Dataset and Benchmarks for Atrial Fibrillation Detection from Electrocardiograms of Intensive Care Unit Patients
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.18031

- Inference for Newton Methods with Accelerated Sketch-and-Project via Random Scaling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12421

- QuPAINT: Physics-Aware Multimodal Reasoning for Quantum Material Characterization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12202

- Scenario-Independent Criticality Assessment and Prediction for Vulnerable Road Users in Autonomous Driving
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11947

- Almost Sure Convergence Analysis of Stochastic Gradient Methods with Clipping and Additive Noise
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12119

- Fast Convergence for High-Order ODE Solvers in Diffusion Probabilistic Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.13061

- Physics-Informed Conformal Prediction: Embedding PDE Consistency into Distribution-Free Uncertainty Quantification for Neural Operators
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11935

- Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12002

- Clustering-Based Balanced Sampling and Allocation with Data Parallelism for High-Performance Fine-Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12584

- MAxBench: A Multinomial Concept Recovery Benchmark
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13072

- LatentVerse: A Framework for Understanding Shared and Modality-Specific Information in Multimodal Latent Representations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12364

- VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.26105

- Direct Topology Tracking in Continuous Implicit Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12157

- VertexCBF: Improving Neural Control Barrier Functions via Vertex-Restricted Control Search
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12831

- HuRo: Robotizing Human Videos for Scalable VLA Pretraining
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.10706

- Anomaly-Preference Image Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.02439

- TDDM-Melatt: A Decoupled Memory and Diffusion Framework for Generalizable Encrypted Traffic Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.30745

- Representation Before Training: A Practical Benchmark for Generative Medical Event Model Tokenization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.16775

- Representing and Detecting Label Ambiguity in IMU-Based Exercise Evaluation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.04842

- GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18234

- Same Encoder, Different Winner: A Paired-View Framework for Cell Painting Encoder Evaluation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12761

- Aligning Language Models with Observational Data: Opportunities and Risks from a Causal Perspective
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.00152

- Exact ReLU realization of binary affine refinement iterates via reflection folding and cone switching
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11962

- Bias-Corrected Data Synthesis for Imbalanced Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.26046

- HoliBench: A Cross-Platform Benchmarking and Deployment Toolkit for Foundation Models in CPS-IoT Applications
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12412

- Are Independently Estimated View Uncertainties Comparable? Unified Routing for Trusted Multi-View Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.09288

- A Ranking Approach for Measuring Calibration
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13100

- When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.24077

- When Minute-Resolution Monitoring Meets Session-Level Injury Labels: Landmark-Based Discrimination in Elite Women's Football
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.03790

- SaFeR-Steer: Evolving Multi-Turn MLLMs via Synthetic Bootstrapping and Feedback Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.16358

- Certified AI Triage of ICU Alarms
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12365

- The C-index illusion: discrimination without calibration in published survival models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.19526

- A Splitting Method for SDE Terminal-Law Estimation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12513

- A False Average: Pooled CoT-Monitor Accuracy Conceals a Reasoning-Dependent Fragility
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.00583

- Class-wise Contribution Estimation via Logit Maximization for Federated Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.18892

- ExpertHTR: Unified Handwritten Text Recognition with Multi-Task Learning and Sparse Mixture-of-Experts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12705

- The General Theory of Localization Methods
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.20635

- The Vienna 4G/5G Drive-Test Dataset
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.02638

- PinDCO: Whole-Page Aware Dynamic Creative Optimization at Scale
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11943

- High-Probability Convergence of SGD via Batched Updates
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12765

- IMPLY: Physically Anchored Consistency for World-Model Rollouts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12441

- Musical Attention Transformer: Music Generation Using a Music-Specific Attention Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.21081

- Code-to-Harness: Distilling Black-Box Optimizers from Self-Play
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.09468

- Transfer Learning for Evolving Domains
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13039

- Synthetic Blips: Generalizing Synthetic Controls for Dynamic Treatment Effects
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2210.11003

- Decomposing LLM-Judge Uncertainty to Target Expert Labels
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.06444

- Guided Adversarial Robust Transfer Learning with Source Mixing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2309.06534

- SIMS: Scale-Invariant Merit-Function-Based Scalarization for Multi-Task Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12599

- Score-based Outlier Generation via Controlling the Radon-Nikodym Derivative
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12113

- Correlation-Guided Fast Machine Unlearning via Hessian Analysis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12620

- EF1-Constrained Nash Social Welfare with Identical Additive Valuations: Complexity, Guarantees, and Experiments
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.03846

- DCRA: Diffusion-Conditioned Representation Alignment for Robust Time-Series Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11997

- GAUGE: When Not to Trust LLM-as-a-Judge in User-Simulated Evaluation of Task-Oriented Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12191

- Temporal Recurrence Favors Fewer Layers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12531

- Self-Verifying Anomaly Detection using Explainable AI for Cybersecurity of DER Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12305

- Hierarchical Prototype Emergence in Modern Hopfield Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12079

- ParaRecover: A Process-Level Benchmark for Error Localization and Recovery in Parallel Tool-Use Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12345

- Hyperion: An AI-powered HPC cluster for sciences and humanities research that utilizes ML for predicting job turnaround time
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11946

- LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.06993

- Multi-Source Wasserstein Distributionally Robust Graph Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19914

- Musec: MomentUm SpEctral Clipping for Stable Muon-type Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11655

- What Drives Recovery in Agentic Text-to-Cypher? LAST-CQ: An LLM Agent Self-Refinement Framework
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12746

- Where Decoder Cosine Similarity Fails for SAE Feature Flow Discovery
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12591

- SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.01343

- Optimizing for the decision not the prediction: an exploration of Smooth Net Benefit as a training objective
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12752

- LLAMA LIMA: A Living Meta-Analysis on the Effects of Generative AI on Learning Mathematics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.18685

- DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.29078

- Toward Reliable Railway-Bogie Response Prediction Using Multifidelity TDNN and Physics-Informed Residual Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12018

- Benign Loss Landscapes Can Coexist with Worst-Case Hardness
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13057

- Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.01473

- Reason Through the Latent! Making Latent Visual Reasoning Necessary
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.06746

- Scalable Krylov Subspace Methods for Generalized Mixed-Effects Models with Crossed Random Effects
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.09552

- A Large-Scale AIS Dataset from Finnish Water
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12938

- AdaVLA: Adaptive Step Flow Matching for Training-free Acceleration of Vision-Language-Action Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.29208

- Fixed State, Long Reach: What a Constant-Size Cache Buys Block Diffusion at Scale
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11998

- Convergence of Stochastic Gradient Methods under Heavy-Tailed Noise and H\"{o}lder Smoothness
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12785

- Simulating Disengaged Students to Evaluate LLM-based Tutors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12331

- Autonomous Research for Open-Ended Problems: A Case Study on Telecom Ticket Retrieval
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13073

- SIFPBPNet: A Dual-Path Network for Wearable and Cuffless Blood Pressure Estimation via Individualized Steady-state Representation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12690

- Granularity-Adaptive Credit Assignment for Long-Horizon LLM Agent Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12424

- Quantile-based Loss Filtering for Outlier-Robust Stochastic Gradient Descent
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13040

- Attention Quantization for Tabular Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13031

- CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.29271

- Physical-State-Guided Diffusion Sampling for Full-Waveform Inversion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12899

- Predicting Collision Cross Sections with GRACE: Geometric Residual Adduct Conditioning via Early-fusion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12223

- FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.16513

- Reinforcement Learning for Syndrome Extraction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12020

- TokenMapper: A Step Toward Interoperable Speech Token Translation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12563

- Linear Exponential Quadratic Gaussian Covariance Steering
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12463

- Can SGD Select Good Fishermen? Local Convergence under Self-Selection Biases
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2504.07133

- Sampling via Decision-Flow: Training-Free Extraction of Improved Latent Reasoning Paths in Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12317

- Block-Norm Geometries for Online Mirror Descent with Sparse Losses
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.13177

- Efficient AI Model Deployment Using Quantization Analysis Tool
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11954

- Exploring Urban Land Use Patterns by Pattern Mining and Unsupervised Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.13050

- Statistical Uncertainty Quantification for Aggregate Performance Metrics in Machine Learning Benchmarks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.04234

- Countdown-Code: A Testbed for Studying The Emergence and Generalization of Reward Hacking in RLVR
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.07084

- Adaptive Chemotherapy Control under Tumor Heterogeneity via Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12264

- Large Distant Gradients Need Not Be Reliable: reliability-weighted credit assignment for long-horizon autoregressive forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12890

- InRTL: Effective Intra-Inter Interaction Learning for Relational Tables
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12712

- Look Before You Leap: Pre-Action Verification for LLM Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11957

- Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13003

- Quantifying the Value of Privileged Information Using a PAC-Bayesian Approach
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12891

- SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.08496

- AIM: A Privacy-Aware Interoperable Memory Framework for Multi-Agent Multi-User LLM Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12320

- DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.15055

- GLaMoR: Consistency Checking of OWL Ontologies using Graph Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2504.19023

- PLSP (Pre-hoc Liminal Space Profiling): OOD Prediction over Detection -- An Anticipatory Approach for Machine Learning Model Reliability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12225

- MInTRL: Off-policy Intervention can boost On-policy RL
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12419

- Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.04531

- Prism-SQA: An Interpretable and Adaptable Neural Framework for Surface Electromyography Quality Assessment
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12724

- Diffusion learning reveals viable parameter manifolds and compensation geometry in biological dynamical systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.03671

- ETHOS: Towards a Modular Ethics Framework for Clinical Multi-Agent Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.15424

- Certified Safety Curation: Distribution-Free Guarantees for Safe Offline Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12014

- Poisson-Corrector Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12594

- Receiver-Surface Hit Patterns via Legendre Approximation for Molecular Signal Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12089

- Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacy
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12067

- Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.06377

- VertiFuseX: Generalizable Financial Forecasting via Multi-Stream Temporal Fusion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12793

- SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.09113

- Dimension-Corrected Hitting Times for Heavy-Tailed Spectral Emergence in Neural Optimizer Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12994

- Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.00165

- Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetries
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13035

- OpenFinGym: A Verifiable Multi-Task Gym Environment for Evaluating Quant Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.26350

- Fed-Equilibrium Framework for Topological Pareto Control in Robust and Fair Clinical Federated Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.11937

- PACEvolve: Enabling Progress-Aware Consistent Evolution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.10657

- RiPPLE: Cross-Space Performance Prediction from Early Training for Neural Architecture Search
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.12418

- Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2609.13053

- Safe Learning Under Irreversible Dynamics via Asking for Help
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2502.14043

- Learning Generalizable Reconstruction of High-Dimensional Neural Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.16569