TILens Daily Edition
2026-08-14
Filters: topic=ai, github=hidden

Stats: 391 articles, 8 sources, 384 research papers
Top topics: AI, AI Research, AI Tools

## News

- How Claude’s text watermark works
  Source: anthropic-blog
  Topic: AI Labs (+AI)
  URL: https://www.anthropic.com/news/claude-text-watermark

- State of Open Models: Summer 2026 Observations
  Source: huggingface-blog
  Topic: Hugging Face (+AI)
  URL: https://huggingface.co/blog/state-of-open-models-summer-2026

- Google's $99 Fitbit gets a wild new update
  Source: the-rundown-ai
  Topic: AI (+AI Tools)
  URL: https://www.therundown.ai/articles/google-fitbit-gets-a-wild-new-update

- OpenAI feels the frontier need for speed
  Source: the-rundown-ai
  Topic: AI (+AI Tools)
  URL: https://www.therundown.ai/articles/openai-feels-the-frontier-need-for-speed

- OpenAI Ultrafast ⚡, X open sources algo 📱, DeepSeek Harness 🐋
  Source: tldr-tech
  Topic: General (+AI)
  URL: https://tldr.tech/tech/2026-08-14

## Research

- ViTOED: A Dataset for Target-Oriented Emotion Detection on Vietnamese Social Media Texts
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12776

- Better Decomposition, Free Aggregation: A Synthesizer-Folding Framework for Multilingual Multi-Hop Question Answering
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13160

- SAEVerbalizer: Generating Explanations for Sparse Autoencoder Features via Representation Verbalization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13538

- HC-RAG: Evidence-Centric Retrieval-Augmented Generation over Heterogeneous Financial Filings
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12335

- CASA: Content-Acoustic Speaking Assessment with Speech Encoder and Large Language Model
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13101

- CityRiSE: Reasoning Urban Socio-Economic Status in Large Vision-Language Models via Reinforcement Learning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.22282

- Natural Language Processing: A Comprehensive Practical Guide from Tokenisation to RLHF
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.03799

- Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12713

- Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12426

- Self-Referential Induction Increases Response Instability Relative to Unresolvable and Verifiable Questions in Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13258

- LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13136

- When Your Agent Opens the Chat App: Agent-Controlled Search over Raw Chat Logs Rivals Structured Memory
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12888

- Evaluation design conditions the expert-vs-auto MeSH gap: a controlled comparison of bag-of-words and BiomedBERT on the Cohen benchmark
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.21685

- The Evaluator Is Part of the Experiment: Measuring Open-Ended LLM Conformity
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.04463

- Masked diffusion LLMs can use EoS tokens for hidden reasoning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.05197

- Novels generated by language models show compressed formal variation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12630

- Cat-DPO: Category-Adaptive Safety Alignment
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.17299

- Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13326

- Gradual Code-Switching as Inference-Time Cross-Lingual Representational Alignment for LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.05678

- SoK: From Generation to Consumption of Privacy Documents in Software Systems
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12511

- Localize, Then Reason: Visual Latent Structural Reasoning for Molecular Properties and Edits
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13244

- FastThaiG2P: Lightning-fast Thai Grapheme-to-phoneme Conversion for Voice Agent Pipelines
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12814

- RAGSieve: Self-Referenced Local Contrast for Knowledge-Poison Detection in Retrieval-Augmented Generation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13010

- From Refuse to Richness: Rubric Rewards for Long-Form Hallucination Reinforcement Learning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12337

- AnchorSIPS: A Synthetic Dataset and Evaluation Resource for Evidence-Supported Psychosis-Risk Symptom Measurement
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12329

- Mimicry without understanding: the origins of decision bias in large language models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12339

- Prompts in the Wild: A Large Analyzed Collection of Transactional Prompts in Code
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12905

- One prompt is not enough: Instruction Sensitivity Undermines Embedding Model Evaluation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.22544

- TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13057

- When Should Multi-Round RAG Stop? Structured Stopping Judgments and Retrieval Reduction in Search-R1
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13237

- Predicting consumer-technology ownership without a diffusion history
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12344

- Toward Federated Large Language Models in Medicine: A Parameter-Efficient Framework for Privacy-Preserving, Multi-Institutional Adaptation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.22124

- CoLA: Cross-Modal Low-rank Adaptation for Multimodal Downstream Tasks
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.03314

- Exemplars in Disguise: Pure Exemplar Models Mimic Abstraction-First Learning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.00821

- Token Reduction Is Not Cost Reduction
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.12161

- From Unstructured Recall to Schema-Grounded Memory: Reliable AI Memory via Iterative, Schema-Aware Extraction
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.27906

- CangjieBench: Benchmarking LLMs on a Low-Resource General-Purpose Programming Language
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.14501

- EviReform: Evidence-Guided Query Reformulation for Multi-Hop Graph Retrieval
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13006

- REHEARSE: Experiential Rehearsal for Verbal Confidence Calibration in Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.14390

- The "Knowledge-Behavior Gap" in Cultural Taboo Safety of Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12341

- When AI Is Your Pastor: A Benchmark for Theological Triage and Pastoral Guidance in Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12324

- Large Language Models Persuade Without Planning Theory of Mind
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.17045

- LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12990

- Mixture of Training: Recombining Small-Scale Scaffolded Pretraining Runs into a Larger Language Model
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13277

- Thought-Aware KV Cache Compaction for Reasoning via Adaptive Attention Matching
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12331

- MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13476

- Dual-Stream Cross-Anchor Correction Grounding Long-Form Captions and the Domain Limits of Object-Level Anchors
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12746

- SDAM: Structure-Difference-Aware Memory Evolution for Complex Text-to-SQL
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12338

- AQuA: Recursively Self-Improving Quantitative Trading Research Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12841

- Similarity All The Way Up: Multilingual Generalization in LLMs Relies on Language-Level Similarity Structures
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.22699

- Do Audio Language Models Use Paralinguistic Evidence? Counterfactual Audits for Response Evaluation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.06718

- New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12361

- Are you Talking Logic to Me? Assessing Language Models Syllogistic Reasoning Capabilities
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12374

- LLMs Know the Constraint But Do Not Use It: Activation Bottlenecks in Pragmatic Constraint Reasoning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12321

- Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13430

- Revolutionizing Finance with LLMs: An Overview of Applications and Insights
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2401.11641

- Decoupled Contrastive Decoding via Expert-Aligned Drafting
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12913

- ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12720

- RippleMem: From Isolated Retrieval to Associative Recollection for Long-Term Agent Memory
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13334

- Class-Structure Preservation Beats Diversity: A Comprehensive Benchmark of Text Augmentation Methods for Imbalanced Text Classification
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12340

- From Observation to Intervention: Memory in Brains and Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12377

- DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13517

- Unmasking Conversational Bias in AI Multiagent Systems
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.14844

- Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12847

- On Measuring Semantic Preservation in Legal Ontology Learning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12326

- Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in Diffusion Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.28166

- Measuring Task-Agnostic Training Data Influence Across Language Model Pretraining
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13515

- Mawqif-XT: An Arabic Benchmark Dataset for Cross-Target Stance Detection
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.09539

- Large Language Models Pass the History Exam But Miss the <<History>>: A Polish High School Exit Exam Matura Benchmark
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12343

- From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12836

- Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.02776

- TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.09538

- SLAyiNG: A Diverse and Community-validated Dataset of Queer Slang
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.17449

- How Significant Are the Real Performance Gains? An Unbiased Evaluation Framework for GraphRAG
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.06331

- QUIETT: Query-Independent Table Transformation for Robust Reasoning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.20017

- AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13560

- OmniScientist: An Omni-Modal Omni-Discipline AI Scientist
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13558

- SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.06854

- Toward a Gricean Retreat: Probing LLMs for Knowledge Boundaries and Referent Specificity
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13484

- Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.11753

- Pandora: Leveraging Code-driven Knowledge Transfer for Unified Structured Knowledge Reasoning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.17905

- The Embedder's Dilemma: LLMs Are Better, but at What Cost?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12875

- Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12323

- Diagnostic Foundation for Evaluating LLMs' Research Integrity as Co-Scientists
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12345

- LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12626

- Actions Speak Louder than Words: Measuring Cross-Lingual Policy Retention in Tool-Using Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11110

- PatientAct: Theory-Grounded Mental Health Client Simulation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12750

- CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12779

- Reconcile Once, Write Anytime: A Trust-Tiered Librarian and a Multi-Agent Writer for Drift-Free, Point-in-Time Research
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12984

- CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13387

- Is this Citation on Point?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12571

- Human-like fleeting memory improves language learning but impairs reading time prediction in transformer language models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.05803

- Vision-Language Models are Fragile Multilingual Associators
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12333

- EgoCITE: Context-Augmented Indexing and Time-Aware Retrieval for Long-Horizon Egocentric Memory
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12627

- When Explanations Betray Backdoors: Black-Box Auditing for Language Model Classifiers
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12623

- HybridRAG-BN: A Retrieval-Augmented Framework with Fine-Tuned Verification for Bangla KBQA
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13004

- Falsehood and Impossibility Are Different Directions in an AI's Representation of Language
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12852

- It's How You Ask: Gender-Associated Linguistic Bias in LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13328

- Steering the Language Axis: From Linear Decodability to Causal Control
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12334

- DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill Evolution
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12486

- Motor, Cognitive, or Corpus? What Survives Cross-Lingual Transfer in Speech-Based Parkinsons Disease Detection
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13425

- Comparing Architectures for Supervised Political Scaling
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.01464

- Query Timing Produces Opposite Positional Biases Between LLMs and Humans
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12387

- Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13304

- Intensional Anaphora
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12598

- What Drives LLM Self-Reflection? A Controlled Ablation of Uncertainty Routing in Armed Conflict Forecasting
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12322

- Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12218

- LoRA-Diffusion: Parameter-Efficient Fine-Tuning via Low-Rank Trajectory Decomposition
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12328

- Reliability-Aware Sexism Detection: Combining DPO with Annotator Agreement and Token-Level Confidence Scoring
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12330

- Which LLM Is Your Ideal Companion? Evaluating Emotional Companion Capabilities of LLMs Based on Adult Attachment Theory
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13168

- StorySpark: Module-wise Evolutionary Search for Story Premise Generation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12336

- RIG-RoPE: Relation-Stratified Multimodal Attention with Instance-Local Rotary Geometry and Representation-Aware Traversal Coordinates
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.05154

- When Large Language Models are More PersuasiveThan Incentivized Humans, and Why
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.09662

- GEM: A Generative Embedding Model Bridging Reasoning and Retrieval
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13200

- Learning Latency-Aware Orchestration for Multi-Agent Systems
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.10560

- BavGround: A Benchmark for Regional Cultural Grounding and Dialect Competence in Bavarian
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12894

- RadarGen: Automotive Radar Point Cloud Generation from Cameras
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.17897

- Decomposition of Evidence, Contradiction, and Fragility in Perturbation Responses
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12935

- Safe Exploration via Policy Priors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.19612

- Short-term load forecasting under EU-AI Act Requirements in Safety-Critical Environments: Results from a 41-day live challenge on the aggregated German transmission-grid load
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.05018

- Latent On-Policy Self-Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13040

- Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12764

- Exponential Convex Calibration Dimension for the Multi-Label Jaccard Measure
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13549

- MergeOver: Post-Training Token Merging for Recursive Vision Transformers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13141

- EGRL: Edge generation-guided relation-aware learning for RNA-protein interaction prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12906

- Which Site, and When: A Free-Satellite-Data Test of Himalayan Glacial Lake Bursts, Landslides, and Ice Floods
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12422

- Robust data-driven discovery of fractional differential equations via weak formulations and Pareto-based subset selection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12879

- Trajectory First: A Curriculum for Discovering Diverse Policies
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.01568

- Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.19058

- Into the ORBIT for Time Series: Training Regimes for Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13262

- Unifying Depth and Width Pruning for LLMs via Binary Knapsack Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12953

- Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12831

- TraVEL: Trajectory-Guided Video Embedding Learning for Driving-Video Retrieval
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13495

- Langevin dynamics for high-dimensional optimization: the case of multi-spiked tensor PCA
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2408.06401

- SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.08519

- Chance-constrained selection of sequential intervention strategies from counterfactual estimates
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13209

- From Approximation Rates to Loss-Landscape Barrier Decay in Shallow ReLU Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.17596

- TRAPSBench: Vision-Language Models Encode but Fail to Express Epistemic Restraint
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13167

- Adaptive $k$ Nearest Neighbors Classifier via Granular Ball Computing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12903

- Distribution Steering via Sliced Optimal Transport Control
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12828

- Identifiability and Estimation for Unlabeled Finite Mixtures under Marginal Independence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.07914

- Accelerated Markov Chain Monte Carlo Algorithms on Discrete States
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.12599

- SDS-LoRA: Overcoming Anisotropic Gradient Scaling in Low-Rank Adaptation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.16454

- Liquidity-Based Audit of Algorithmic Trading Strategies
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.29018

- The Objective Is the Bottleneck: Latent World Models Encode What Their Planners Cannot Use
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12959

- Performance-Carbon Trade-Offs across Architectural Biases in Shear Flow Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.24517

- Variance Reduction Based Experience Replay for Policy Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.05379

- Fast Length-Squared Sampling for Positive-Semidefinite Matrices
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12503

- Equivariant learning of a transferable three-dimensional classical density functional
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13506

- Online Correlation Clustering: Simultaneously Optimizing All $\ell_p$-norms
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.15076

- Foundations of Independent Component Analysis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13229

- Bayesian Distributional Models of Executive Functioning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.00387

- 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

- Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.00367

- Comment on "Modeling rapid language learning by distilling Bayesian priors into artificial neural networks"
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12974

- Federated Compositional Muon Optimizer for Matrix-Wise Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12710

- Predictive Allostatic Organization in Recurrent and Spiking Agents Under Partial Observability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11506

- Intervention-Aware Clinical World Model for Post-Op Outcome Forecasting in Cardiology
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13518

- DiffGRM: Diffusion-based Generative Recommendation Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.21805

- Task- and dataset-specific information in protein language models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12090

- History-informed Lagrangian Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13215

- Interpretable Causal Discovery via Causal-Effect Constraints
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12640

- DYSANOS Generative Dynamic Smooth Arbitrage-free Non-parametric Option Surfaces
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12587

- Bagging Robustly Learns VC Classes with Linear Sample Complexity
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13514

- Momentum as Residual-Driven Multiplier Correction for Deep Learning Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12925

- SAFE-SVD: Sensitivity-Aware Fidelity-Enforcing SVD for Physics Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.17985

- Beckmann Transport Models: From Autonomous Flows to One-Step Maps
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.01692

- Unlearning at Scale: State-Exact Trace-Preserving Deletion in Billion-Parameter Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.12220

- Intern-S2-Preview: Scientific Agentic Foundation Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13505

- Online Inference for Quantile Temporal Difference Learning in Distributional Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12973

- Which Decisions Low-Bit Quantization Breaks, and How to Predict Them
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.06564

- The Optimal Sample Complexity of Multiclass and List Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.24749

- Enhancing In-Hospital Mortality Prediction Using Multi-Representational Learning with LLM-Generated Expert Summaries
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2411.16818

- Optimizing Likelihoods via Mutual Information: Bridging Simulation-Based Inference and Bayesian Optimal Experimental Design
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2502.08004

- Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.05809

- Regularization can make diffusion models more efficient
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2502.09151

- Do LLM Recommenders Know When They're Hallucinating? Auditing Confidence Calibration in Catalog Faithfulness
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10008

- Cueless EEG imagined speech for subject identification: dataset and benchmarks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.09700

- Wasserstein Filtering: A Sample Selection Method for Robust Distribution Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13418

- A Probe Direction Is a Property of Its Prompt
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13329

- CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12629

- PAIR: Pairwise-Aware Inclusion Reweighting for Adaptive Rollout Allocation in RLVR
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11368

- In Silico Study for Optimizing Intensity and Focality Electrode Configurations for Directional DBS Under Uncertainty Using Metaheuristic L1L1 Method
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.13452

- Drive-to-Music: Context-Aware Generative Audio for In-Vehicle Experiences
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12615

- Identifiability and Stability of Generative Drifting in the Companion-Elliptic Kernel Family
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.24196

- Prof-K: Probabilistic One-Pass Filtering for Efficient Top-k Selection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12573

- Knowledge-guided Pattern Discovery via Coupled Tensor Factorizations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13234

- GENADA: efficient generative time series adversarial attack framework
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12535

- A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.18733

- CookVoice: Unified Framework for Style Controllable Multi-Modal Human Voice Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11590

- MatchMiner-AI: Open-source, Privacy-preserving Cancer Clinical Trial Matching using Artificial Intelligence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2412.17228

- The Noise Premium in Adversarial Training for Kernel Regression
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.27995

- ReconSpan: Reconstruction-Guided Adaptive Latent Tokenization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12756

- Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12704

- Personalized Scorer Modeling: A Learning-Based Framework for Deriving Robust Sleep Stage Labels from Multiple Experts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12446

- The Impact of Temporal Context Length and Encoding Strategies on Self-Supervised ECG Representation Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12695

- Tight Nonasymptotic Local Convergence of Sinkhorn-Knopp
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11760

- Reduced Matrix Multiplication: Input-Adaptive Matrix-Product Reduction for LLM Inference
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13426

- Keep, Customize, or Exit: Default Design and Token Pricing in LLM Reasoning Services
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13315

- Simulation-to-real transfer learning for infrared spectroscopic chemical sensing and analysis from molecules to complex samples
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13341

- Finding the Needle in a Haystack: Test-Time Analog Circuit Representation Adaptation for Bayesian Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12687

- "Cause" is Mechanistic Narrative within Scientific Domains: An Ordinary Language Philosophical Critique of "Causal Machine Learning"
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.05844

- A Multispectral Framework for the Detection of Calcium Carbide-Induced Ripening and Shelf-Life Estimation in Climacteric Fruits
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13073

- A Bayes-Markov Neuromorphic Model of Cortical Orientation Selectivity: A Computational Re-implementation and Quantitative Simulation Study
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12388

- Represent, Then Generate: Multimodal-Conditioned Time-Series Generation under Irregular Missingness
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12592

- Explanatory Engagement Under Rare Anomalous Failure: Asymptotic Rarity in Model Behavior (or: The Asymptotic AI)
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13063

- Multi-AUV Ad-hoc network-based Target Tracking: A Value Gradient Guidance Multi-Agent Diffusion Reinforcement Learning Approach
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12436

- Security and Detectability Analysis of Unicode Text Watermarking Methods against Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.13325

- Learning the Mathematical Property for Designing Low Mutual Coherence Binary Sensing Matrices
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12982

- SteerBench-Work: A Benchmark for Agent Steering at Action Boundaries
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12654

- Active-Trace Complexity Bounds for Moreau--Yosida Unadjusted Langevin Sampling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13467

- A Simple State Space Model Excels at Multivariate Time Series Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.27406

- A Lyapunov Drift-Plus-Penalty Method Tailored for Reinforcement Learning with Queue Stability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.04291

- CardioState-JEPA: Delay-Aware Cross-Modal Learning of a Shared Cardiac Representation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12944

- From Visual Widgets to UI Code: Efficient Tool-Grounded Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12611

- Unifying Generative Models with Path Integrals
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12438

- Concept Drift Detection and Adaptive Retraining of Malware Classification Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13465

- Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12108

- Learning Under Treatment-Induced Label Indeterminacy with Expert Annotations of Counterfactual Outcomes: A Case Study in Neurological Prognostication
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12477

- Difference-of-Convex Regularization for Graph Learning by Differentiable Programming
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12757

- Foundation models for movement data: Are they ready for prime-time?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13316

- Beyond Simulated Benchmarks: Evaluating Motion Representations for Fall Detection Under Real-World Data Scarcity
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13197

- I-SDPO: Instance-Level Adaptive Self-Distillation Policy Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12957

- The Time Value of Evolution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13297

- Non-Degenerate Risk Certification for Automated Security Decisions: A Decision-Contract Theory with ATT\&CK-Aligned Triage as a Worked Instance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12444

- TabH2O: A Unified Foundation Model for Tabular Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.18383

- Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practice
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12962

- Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13337

- Can Spectral-Clipping Enable Better Learning While Forgetting Less for Low-Rank Adaptation?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12332

- Round-Trip Consistency: Bidirectional Diffusion Models Can Predict Their Own Rollout Errors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.00675

- Constitutional On-Policy Safe Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.03089

- Exponential quantum advantage for learning signals with a single qubit
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13521

- Multiview Representation Learning via Distributed Joint Latent Space Structuring
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2504.18455

- REOPD: Reliability-Adaptive Reward Extrapolation for On-Policy Distillation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11698

- Virtual Temperature Sensors in Power Transformers Using Neural Ordinary Differential Equations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13260

- Sinkhorn Linearization and the Spectral Proxy: Unifying the Statistical and Algorithmic Theory of Feature-Parameterized Inverse Optimal Transport via a Single Spectral Sandwich
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13201

- Finite-Time Minimax Bounds and an Optimal Lyapunov Policy in Queueing Control
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.18278

- AIFS-TC: A simple correction competitive with the operational frontier for tropical cyclone intensity forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.09959

- HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12821

- Do Transformers Need Three Projections? Systematic Study of QKV Variants
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.04032

- LittleLearner: Language Models Under Pedagogically Controlled Knowledge Exposure
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13545

- Diagnosing JEPA World Models with Action-Conditioned Predictive Consistency
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12939

- Structure-preserving uncertainty quantification for GENERIC dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12624

- Exemplar-based objective classification of gust-induced loads across multiple flight conditions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12448

- LLM-Assisted Dynamic Threat Analysis for Attacker-Reachable Software Weaknesses in Autonomous Vehicles
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13450

- Novel Knowledge-Guided Generative Methods for Synthetic Transcriptomic Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13256

- Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10766

- DiG-bench: Discovery in Games
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12593

- Generative Brownian Bridge Diffusion In Motion Space For Enhanced Myocardial Strain Analysis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.01677

- Reduced Order Modeling for Tsunami Forecasting with Bayesian Hierarchical Pooling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.19804

- Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.08567

- Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.02575

- CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12805

- Sustaining Plasticity via Learnable Wavelet Activations in Continual Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12874

- SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.03612

- Functional-prior-based approaches to Bayesian PDE-constrained inversion using physics-informed neural networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.07060

- Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12391

- Training Under Challenge: Executable Certificates and Challenge-Closed Optimality for Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12655

- Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13228

- Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.19703

- FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13096

- General Bayesian Policy Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.23672

- Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12717

- EEG Decoding Using CNN and LSTM Network
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13285

- SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.27431

- Dimension-Calibrated Unexplained Mass: An Interpretable Drift Statistic for Contamination Monitoring in Data Streams
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.16811

- Position: Reasoning is a Learnable Rule-Based Process
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12325

- Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.18852

- Fine-tuned Normalizing Flows for ALICE Zero Degree Calorimeter Fast Simulation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12795

- From Recoverability to Functional Use: Certifying Temporal Reports in Time-Series Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10433

- Dual Spatial-Temporal Attribution: Architecture-Aligned Post-Hoc Explainability for Recurrent Graph Anomaly Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12441

- Incremental Evaluation and Training in Relational Deep Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13023

- Analysis of Motor Signatures of Social Adaptation in Autism for Efficient Human-Centric Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12548

- Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12663

- Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.06239

- MARCH: Scaling Recurrent Memory with Content-Routed State Anchors
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12435

- How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13267

- Large-scale Testing Global Optimization Methods with Black-box Adversarial Attacks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13296

- Defensive Boosting for Online Probabilistic Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13554

- OC-Distill: Ontology-aware Contrastive Learning with Cross-Modal Distillation for ICU Risk Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.16878

- Noise as a Probe: Membership Inference Attacks on Diffusion Models Leveraging Initial Noise
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.21628

- Synthetic Persona Pretraining: Alignment from Token Zero
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13482

- A Cloud-Edge System for Multimodal Clinical Screening in Resource-Constrained Rural Settings
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12745

- Sampling Luck Masquerades as Allocation Gain: Auditing Test-Time Budget Allocation for Neural Combinatorial Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13087

- Revisiting Overestimation Bias Problem of Q-learning: Settling Large Discrete Action Space via Action Intersection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12912

- MBA: Multimodal Benchmark and Agents for Real-World Business Ideation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11616

- Dead text or binding clause? Measuring and restoring constraint influence in black-box LLM dialogues
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12599

- SpinCastML an Open Decision-Making Application for Inverse Design of Electrospinning Manufacturing: A Machine Learning, Optimal Sampling and Inverse Monte Carlo Approach
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.09120

- H-VAEP and H-xT: Valuing Offensive On-the-Ball Actions in Handball by Estimating Probabilities
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12926

- Self-Localizing MIMO Beam Mapping for Intelligent Open RAN with Continuously Evolving Channel Memory
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.17007

- Training AI Scientists to Replicate Research
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13331

- Stochastic Neural Networks for Quantum Devices
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.22241

- LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.09633

- Recursive Synthesis for Long-Horizon Terminal Tasks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.05466

- Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets for Vision
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.12532

- A Compositional Theory of Curvature in Probabilistic Circuits
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12869

- ProME: Prototype-Margin Environments with Repair-Aware Selection for Group-Robust Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13190

- LOCUS-DT: Localization via Observation-Conditioned Uncertainty Scoring with Digital Twins
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.00406

- Statistical Properties of Robust Learning under Distributional Shifts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13133

- FSGR: Mitigating Token Frequency Bias for Fair SID-Based Generative Recommendation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12845

- Physics-Informed Laplace Neural Operator for Solving Partial Differential Equations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.12706

- When Does Trace-Driven Evaluation Mislead MoE Expert Caching? Replay Semantics, Workload Contamination, and Operating Regimes
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.07911

- Wrong Design Intent Is Worse Than Never Conditioning: A Derangement-Control Diagnosis of Header Conditioning in CAD Program Completion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.23191

- Learning Discrete Decisions for MIPs with Constraint-Aware Diffusion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13079

- DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.09233

- The Boolean Power of ReLU
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12617

- Distributed Online Submodular Maximization under Communication Delays: A Simultaneous Decision-Making Approach
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.27803

- Branch and Bound for Relational Verification of Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13118

- Balanced Adaptive Prototype Selection for Scalable TabPFN Inference on Large-Scale Tabular Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12989

- Automated Design Optimization via Strategic Search with Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.22651

- Doctorina MedBench: A Dialogue-Based Benchmark and Evaluation Framework for Agent-Based Medical AI
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.25821

- Vanilla SGD with Momentum Survives Heavy-Tailed Noise: Convergence Analysis without Gradient Clipping or Normalization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.08104

- On the Importance of Geometric Nonlinearity and Temperature-Dependent Properties in Multi-Material Thermo-Mechanical Topology Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10344

- Manifold constrained steepest descent for smooth and closed-set optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.21487

- When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13365

- Exploring Oversmoothing with Householder Matrices
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12514

- Doubly Robust Estimation of Causal Effect on CVR with Targeted Regularization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13461

- EU-ETS under attack? The impact of carbon price suppression on the decarbonization of the power sector
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12363

- Sparse Orthogonal Regression Technique: A Spectral Framework for Equation Discovery, Approximation, and Integration
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13504

- A Local-Linearly Convergent Algorithm for Nonconvex Equality-Constrained Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12665

- Multi-perspective Imbalance-Conscious 6G Beamforming Optimization and Performance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12929

- SSPO: Structure-Aware Similarity-Weighted Preference Optimization for Neural Combinatorial Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12443

- Thermalizing Stochastic Programs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.01615

- Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12597

- Post-Hoc Uncertainty-Aware Explanations for Deployed Power Quality Disturbance Classifiers via Laplace Approximation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.13658

- Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.03172

- Aftab: A Comprehensive Benchmark of CNN Encoders and Advanced Value Functions in Parallelized Q-Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.07335

- On the global feature importance for interpretable and trustworthy heat demand forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13039

- Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.10473

- TabSOM: A tabular-to-image encoding method based on self-organizing maps
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13513

- Designing AI Pipelines for Decision-Ready ITSM Intelligence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12670

- In-context superposition: human-like working memory interference in large language models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.09670

- Harmonizing Safety and Speed: A Human-Algorithm Approach to Enhance the FDA's Medical Device Clearance Policy
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2407.11823

- SpaRRTa: A Synthetic Benchmark for Evaluating Spatial Intelligence in Visual Foundation Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.11729

- Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12753

- Scaling Time Series Classification via XAI-Driven Data Reduction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.15774

- Comparative Analysis of Multilingual Pre-trained Models for Nepali Automatic Speech Recognition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12327

- When Can You Trust Offline Evaluation of Equal-Cost Top-k Allocation? A Controlled, Reproducible Benchmark and Practitioner's Guide
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12489

- Regulatory Approval Is Not Enough: Gaps in Trustworthy AI Reporting in FDA-Cleared Medical Devices
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12360

- DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13524

- High-dimensional networks and mean squared error for possibly misspecified models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13171

- Infrared Organization and Critical Cognitive Field Formation in Transformer Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.10923

- Efficient Image Restoration with State-Dependent Forward Diffusion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.16733

- SparseDitto: Customizing GPU Kernels for Different Sparsity Patterns with LLM-Based Agentic System
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.05033

- Scaling Automatic Research Agents via World Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12564

- MAG: MAnifold Guided Semi-Supervised Multi-modal In-Context Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12724

- Symmetry-Breaking De Novo Crystal Generation via Markovian Jump Diffusion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13457

- Architecture Before the Formula: Individuating Neural Architecture Beyond the Composite Map
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2601.11618

- INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.20088

- Geometric and Behavioral Stratification in Transformer Residual Streams
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12447

- Towards Socially Compliant Navigation in Deep Reinforcement Learning via Proxemics-Based Reward Modeling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12917

- TANGCO: Learning Topology-Aware Capacity Allocation for Overload-driven Cascading Failures
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13212

- Discovering Persistent Behavioural Patterns for Interpretable Blockchain Forensics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12864

- Gradient-Free Warm-Start Library Recovery: an Amortized-Regret Separation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.21253

- Embedding networks with the random walk first return time distribution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.02694

- The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13520

- Continual Distillation Learning for Rehearsal-Free Class-Incremental Learning via Decoupled Prompting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2407.13911

- From Local Mismatch to Global Impact: Optimizing Cache Reuse Policy for Efficient Diffusion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13043

- Subtract, Transport, or Replay? Auditable Deletion from Language-Model Memory
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.27539

- AI-Driven Multiscenario Interest Rate Forecasting: A Proof of Concept for Banking Asset Management
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12424

- CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teachers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12773

- Black-Box Knowledge Transfer across Distinct Feature Sets
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12403

- On the Structural Limits of Machine Learning Decision Systems: An Information-Theoretic, Interaction-Based, and Stochastic-Dynamical Perspective
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13510

- CAS: A Causal Attribution Score for Local and Global Explainable Artificial Intelligence
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12555

- Yes, Q-learning Helps Offline In-Context RL
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2502.17666

- Vero: Can AI Agents Build Formally Verified Software Repositories?
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13522

- LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12419

- Latent Fact-Checking: Detecting Misinformation through Activation Engineering
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.06417

- VALG: An Agentic System for ML Theory Research
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13060

- Dimensional Balance Improves Large Scale Spatiotemporal Prediction Performance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.18793

- Demand Transfer Estimation at Scale via Restricted Logit Modeling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12680

- Thermodynamics of Learning: A Typed Four-Component Accounting of Memory, Fit, and Value
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12791

- Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12342

- Excess Separability: Nuisance-Controlled Residual-Stream Probing for Benchmark Contamination Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12652

- A Contract-Grade Verifier for LLM-Generated GPU Kernels, and a Native Blackwell Backward for the Gated-Linear-Recurrence Family
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12700

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

- SEAR: Sample Efficient Action Chunking Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.01891

- RoutePack: Expert Placement and Attention-Aware Data Packing for MoE Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12146

- Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12408

- Training and Benchmarking Code Generation for Physics-Inspired Animations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.10840

- What Makes a Peer? Valuation-Anchored Similarity in Private Markets
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.12594

- Annealed Softmax Greedy in Many-Armed Bayesian Bandits
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.31034

- Neural Quadratic Forms: A Unified Minimal Model for Sudden Learning and Scaling Laws
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.13335

- The Illusion of Improvement: Reject Inference Strategies in Credit Scoring
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.18479

## Community

- Don't classify. Hallucinate!
  Source: simon-willison
  Topic: Python (+AI, Django)
  URL: https://simonwillison.net/2026/Aug/14/dont-classify-hallucinate/

- The Codebase Is the Agent's Working Environment
  Source: adam-bien
  Topic: Java (+AI)
  URL: https://adambien.blog/roller/abien/entry/the_codebase_is_the_agent_s_working_environment