TILens Daily Edition
2026-08-21
Filters: topic=ai, github=hidden

Stats: 422 articles, 10 sources, 411 research papers
Top topics: AI, AI Research, Python

## News

- Measuring benchmark optimization in speech recognition
  Source: huggingface-blog
  Topic: Hugging Face (+AI)
  URL: https://huggingface.co/blog/asr-benchmark-optimization

- How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code
  Source: huggingface-blog
  Topic: Hugging Face (+AI)
  URL: https://huggingface.co/blog/pwc-search

- The mRNA cancer vaccine finally delivers
  Source: the-rundown-ai
  Topic: AI (+AI Tools)
  URL: https://www.therundown.ai/articles/the-mrna-cancer-vaccine-finally-delivers

- OpenAI Adds Controls That Should've Been There Already
  Source: darkreading
  Topic: DevSec (+AI)
  URL: https://www.darkreading.com/application-security/openai-adds-controls-already

- Slack turns coding into a group project
  Source: the-rundown-ai
  Topic: AI (+AI Tools)
  URL: https://www.therundown.ai/articles/slack-turns-coding-into-a-group-project

- Anthropic eyes $2T+ IPO 💰, Slack Code 👨‍💻, end of open source 💻
  Source: tldr-tech
  Topic: General (+AI)
  URL: https://tldr.tech/tech/2026-08-21

## Research

- An AI tool for prioritizing candidate biomarkers from wearable sensor data
  Source: google-research-blog
  Topic: AI Labs (+AI, AI Research)
  URL: https://research.google/blog/an-ai-tool-for-prioritizing-candidate-biomarkers-from-wearable-sensor-data/

- How mobility gives language models a deeper understanding of place
  Source: google-research-blog
  Topic: AI Labs (+AI, AI Research)
  URL: https://research.google/blog/how-mobility-gives-language-models-a-deeper-understanding-of-place/

- Designing Human-mediated AI Guidance: Ready Together for Personalized Family Emergency Preparedness
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19950

- Socioduality: A Relational Process Framework for Human-AI Interaction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11322

- Improving Requirements Classification with SMOTE-Tomek Preprocessing
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.06491

- ReguSim: Evaluating LLM Agent Rule Grounding in Financial Compliance
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19974

- MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19901

- Interaction valence reveals contrasting social networks in dairy cattle
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19222

- DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20161

- FMT$^{\mathrm{X}}$: Lazy Wavefront Search for Dynamic Replanning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.08521

- Rule-Compliant Visual Spatial Planning for Multimodal Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20237

- Prompt-Conditioned Channel Attention for Hierarchical Feature Modulation toward Anatomy-Agnostic Segmentation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20229

- Learning to Beat: Phenotype-Guided Latent Flow with Regional Motion Priors for Biventricular Motion Synthesis
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19738

- Gen AI in Proof-based Math Courses: A Pilot Study
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.13570

- Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19556

- CharTool: Tool-Integrated Visual Reasoning for Chart Understanding
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.02794

- DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20114

- Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19973

- Graph Surgery and the Do-Operator: A Precise Correspondence for Acyclic Structural Causal Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.17634

- ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20009

- Computational Phenomenology of Borderline Personality Disorder: A Comparative Evaluation of LLM-Simulated Expert Personas and Human Clinical Experts
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.19008

- Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20316

- Growth Without Us: Machine Consumers, Corporate Circularity, and the Decoupling of GDP from Humanity after AGI
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20231

- MKG-CARE: Case-Aware Reasoning with Multimodal Knowledge Graphs for Explainable Medical Image Diagnosis
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.22547

- Bounded Sovereignty and the Control Tax: Pricing AI Oversight When the Deployer Does Not Own the Model
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19216

- Write Once, Run Everywhere: The Axon DSL for Shape-Safe and Framework-Agnostic LLM Architectures
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19889

- Frequency-Aware Continual Learning for Smart Contract Vulnerability Detection with Large Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19680

- Repo0: Design-Driven Zero-to-All Code Generation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19854

- The Basic B*** Effect: The Use of LLM-based Agents Reduces the Distinctiveness and Diversity of People's Choices
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.02910

- How to Navigate Uncertainty About AI Consciousness
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19215

- The First Drop of Ink: Nonlinear Impact of Distracting Information in Long-Context Reasoning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.10828

- Towards Professional Tennis Styles for Humanoid Robots with Adaptive Motion Planning and Tracking
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20087

- Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20011

- Your Turn: At Home Turning Angle Estimation for Parkinson's Disease Severity Assessment
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2408.08182

- EXIMO: VLM Guided Exploration of VLA Policies
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19891

- Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19487

- From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20195

- Learning-Augmented Power System Operations: A Unified Optimization View
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.05203

- PACT: Phenotype-Aware Contrastive Team Representation for Multi-Phenotype Grouped Ad Hoc Teamwork
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.25340

- Distilling Aggregate Mobility Statistics into a Language Model Policy for Post-Event Crowd Simulation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19778

- ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.02022

- Extended to Reality: Prompt Injection in 3D Environments
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.07104

- SafeBranch: Branch-Pair Safety Alignment for Embodied Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19729

- CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.23487

- Does Marginal Coverage Guarantee Class-Conditional Safety for Zero-Shot VLMs Under Shift?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19376

- Mapping General-Purpose AI Governance in Twenty AI Middle-Power Jurisdictions
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19278

- Catching the Rug: Early Prediction of Fraudulent Memecoins on Solana via Machine Learning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20271

- WNM-3D: A World Navigation Model with 3D Scene Conditioning for Closed-Loop VLN
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.07267

- SUM-AgriVLN: Spatial Understanding Memory for Agricultural Vision-and-Language Navigation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.14357

- Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networks
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19817

- DA-WAM: Decision-Aligned Future Latents for Driving World Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19085

- Rethinking the Evaluation and Optimization of LLM-Based Social Simulation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19689

- TESTNAV: Pareto-Guided Search for Compositional Robustness Testing
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19882

- A Physics-Informed Neural Network Approach for UAV Path Planning in Dynamic Environments
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.21874

- Learning Early-to-Final Solution Consistency for MILP Acceleration
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19953

- Air Traffic Control Using Large Language Models: Prompt Engineering, Architecture, and Evaluation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19299

- VISD: Enhancing Video Reasoning via Structured Self-Distillation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.06094

- A three-dimensional typology of agency for advanced AI systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20041

- Symposium: Trust via Auditable Records for Communities of AI Scientist Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19511

- ReynoldsFlow: Physics-Inspired Spatiotemporal Flow Representation for Video Understanding
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2503.04500

- Multi-Method Causal Evidence Synthesis: Ranking Candidate Drivers by Convergent Cross-Method Evidence from Observational Data
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20187

- Robust Cross-Modal Foundation Model Perception for Underwater Robots under Degraded Visual Conditions
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19710

- Power Couple? AI Growth and Renewable Energy Investment
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.26678

- Escaping the Quicksand: A Call to Arms
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19674

- EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20055

- LLMs as Acquisition Policies for Finite-Pool Materials Optimization: A Controlled Study
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19790

- Anatomy Contextualized Adaptation of CT Foundation Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.27154

- FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.21596

- MidTool: Mid-training Data Synthesis for Agentic Tool Use
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20314

- SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19842

- Contrastive Mixed Prompt Learning for Incomplete Multimodal Sentiment Analysis with Unseen Modality Combination
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20019

- A Tool to Map AI Programs in the U.S.: A Snapshot from April 2026 and an Analysis of Requirements for AI Majors and Minors
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.12428

- A Strong Linear Baseline for Whole-Heart Cardiac Shape Completion on CT, with an Open Eleven-Structure Statistical Shape Model
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19932

- ChronoAgentic: A Code-based Multi-Agent World Simulator for Physically Grounded Simulation Construction
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.14398

- Bringing analytic rigor to agentic AI for science: The Brain Researcher platform for neuroimaging data analysis
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19902

- CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19776

- On the Applicability of Safety Nets: A Safety-By-Design Solution for Certifying Neural Networks
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20053

- PO-PDDL: Learning Symbolic POMDPs from Visual Demonstrations for Robot Planning Under Uncertainty
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.15654

- Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20256

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

- InsufficiencyBench: Evaluating LLM legal advice on underspecified user queries
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20220

- QUASAR: A Quantum-Classical Neural Network for SAR Satellite Physical-Layer Authentication
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20240

- Beyond Memory Majority: Latent-Source Reasoning for Multi-Agent Memory Arbitration
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19701

- Towards general embodied intelligence: integrating large language models, knowledge bases, and reasoning capabilities to build the next generation of AI agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19794

- TestifAI: Tomography-Based Testing for Deep Learning Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18900

- Evaluating Investment Logic in Large Language Models: A Real-World Benchmark Towards Personalzied Financial Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.06108

- The Thousand Brains Theory 2.0: An Extension for the Long-Range Connections of the Neocortical Heterarchy
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2507.05888

- When AI Writes, Who Gets Cited? Evidence of Citation Monoculture Across Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19230

- When Saying No Makes Better Videos: Designing Dual Gatekeeping for Pedagogically Grounded AI Content Creation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19812

- Robust Metaheuristics under Uncertainty for Berth Allocation and Quay Crane Assignment: A Review
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19214

- Fairness-Aware Network Embeddings: Methods, Applications, and Challenges
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19381

- The Third Restructuring of Software Form: From the Three-Tier Architecture to Storage, Models, and Agents
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20201

- Optimal Skill Selection for LLM Agents with Provable Bicriteria Guarantees
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19993

- TT-net: Quantum Inspired Tensor Network Denoising in Conditional GANs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19789

- Can Predicted Dynamics Exist in the Physical World?
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.00089

- SoftVTBench: A Safety-Aware Visuo-Tactile Benchmark for Physically Constrained Robotic Manipulation of Deformable Objects (Early Version)
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.04234

- Andy: A Mathematical Agent for Rigorous Proof and Autonomous Research
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.15052

- VGI-BENCH: Probing Visual Intelligence in Video Generation Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19583

- Scientific Data Skills: Enabling Agent-Ready Scientific Data Services at Scale
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19625

- Evidence-Gated Task and Motion Planning with Vision-Language Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20084

- Electronic Navigational Chart Change Classification
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20218

- Scale-Separated Conditioning for Style-Encoder-Free Diffusion Stylization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19719

- Towards Quantifying Benchmark Optimization in ASR Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19936

- GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.09921

- Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.05616

- LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.15242

- A Distributional Robustness Margin For Pathology Foundation Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.25497

- Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.10555

- Causal Reasoning with Bipartite Graphical Causal Models
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19831

- Loreley: Repository-Scale Program Evolution with Quality-Diversity Search
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19703

- Incident-Data Robustness Analysis of the OWASP Top 10 for LLM Applications (2026): How a Community-Expert Ranking Holds Up Against a Large-Scale LLM Incident Corpus
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19266

- Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19863

- ADAPT: Physics-Aware Diffusion-based World Models for Adaptive Predictive Transferable HVAC Control
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19804

- Regressor-Guided Image Editing Shifts Emotion and Disengagement Timing in Social Media
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.12289

- The Bidding Games: Reinforcement Learning for MEV Extraction on Polygon Blockchain
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.14642

- WaveVerif: Acoustic Side-Channel based Verification of Robotic Workflows
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.25960

- Generative AI Use in Entrepreneurship: An Integrative Review and an Empowerment-Entrapment Framework
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.02567

- GenMatch: An End-to-End Generative Matching Framework for Micro-View Order-Dispatching in Ride-Hailing
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19751

- Every Step of the Way: Video-based Parkinsonian Turning Step Counting
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.27918

- A Model-Internal Protocol for Assessing Multimodal Models as Integrated Systems
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11907

- CVSD-Reg: Cross-Modal Visual Semantic Prior Distillation for Robust LiDAR Registration
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19536

- GOAG: Generative and Object-Agnostic Grasp Planner for Dexterous Robotic Manipulation
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19759

- MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.06245

- Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.12616

- Rethinking Patch Based Multivariate Time Series Forecasting with Semantic Structured Partitioning
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19966

- Enforcing LLM Safety through DMD-based Classification of Prompt-Response Embedding Dynamics
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19579

- PrefixAgent: An LLM-Powered Design Framework for Efficient Prefix Adder Optimization
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2507.06127

- GridCodex: A RAG-Driven AI Framework for Power Grid Code Reasoning and Compliance
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.12682

- Specification-delta-driven data governance: an empirical study of the {\guillemotleft}spec-delta{\guillemotright} as the unit of change in lakehouse data platforms
  Source: arxiv-cs-ai
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19838

- When Machines Speak: A Unified Generative Framework for Integrating Machine-Native Symbols into Pretrained Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19529

- Towards Audio Token Compression in Large Audio Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.20973

- Automatic bioinformatic software named entity recognition from literature
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19201

- Remember, Verify, or Ask? Cross-Family Evaluation of Memory Commitment in LLM Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19564

- One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19741

- HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2502.15411

- TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.03519

- Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19211

- TempJail: Temporal Jailbreak Attack against Large Vision-Language Models via Subtitle Scheduling
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19737

- G-CARL: Grounded Checklist-Aligned Reward Learning for Patient-Oriented Medical Report Interpretation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20331

- PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19598

- SynFlow: A Multidimensional Diachronic Semantic Analysis Toolkit
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19472

- ConceptGuard: Benchmarking Context-Sensitive Unlearning in Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20338

- 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

- HARP: Hierarchical Adaptive Ranking with Preference-Adaptive Fusion for Query-Based CVE Prioritization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19430

- Dynamic Gated Cross-Modal Fusion with Sarcastic-aware Contrastive Regularization for Multimodal Sarcasm Detection
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19942

- SWE-bench Science: Can Coding Agents Resolve Engineering Tasks in Science?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19799

- GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18752

- FormalTCS: Benchmarking End-to-End Frontier Formal Theoretical Computer Science Research of Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20153

- StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19723

- Hallucination as a Feature, not a Defect: Evaluating a multi-agent architecture to transform speculative language-model outputs into testable scientific hypotheses
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19206

- Interrupting the Loop: Periodic Subject Changes Raise Judged Surprise and Connection in Base Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19893

- Grading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19009

- Can Conversational AI loosen Us-Versus-Them Boundaries? The Effects of Common, Dual, and Separate Identity Framings on Pro-Immigrant Intergroup Helping
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19220

- Are LLMs becoming similarly creative? Evidence from three years of models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19437

- A Virtual Member of a Community of Practice for the Society of Petroleum Engineers: From Prototype to Deployment
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19199

- PersonalBench: Measuring the Authorship Gap in LLM Personalization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19746

- Break It Down, Pass It On: Cross-Task Skill Transfer in LLM Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20274

- Outcome Monitors: Recovery Affordances for Silent Tool Failures
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19303

- When Text and Numbers Disagree: Evidence Arbitration in Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20116

- A Finite-Calibration Regime Map for LLM Judge Panels
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.01034

- Calibrated Triage, Not Autonomy: Confidence Estimation for Medical Vision-Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.15910

- NepOOC-M: Bilingual Nepali-English Benchmark and Comparative Analysis of Multimodal Architectures for OOC Detection
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19212

- OenoBench: A Wine-Domain Benchmark for Knowledge-Grounded Evaluation of Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20106

- From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19535

- Self-Harness: Harnesses That Improve Themselves
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.09498

- DiverValue-Bench: A Benchmark and Fine-Tuning Framework for Aligning Large Language Models with Diverse Human Values
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.08022

- LoRA-GA$^2$: Low Rank Adaptation with Multi-step Gradient Adaptive Alignment
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19800

- FlashPrefill V2: Block-Sparse Prefill Attention for Long-Context LLM Serving
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19758

- SABET-QA: Temporal Knowledge Graph Question Answering
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20083

- Hear2Act: Benchmarking When Prosody Should Change What an Assistant Does
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19515

- Transformer Models for Text Summarization: A Comparative Study of BART, BERT, and RoBERTa
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19200

- Reliable Financial Named Entity Recognition under Domain Shift
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19558

- When Irrelevant Text Matters: Affine Margin Shifts in Multimodal Large Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19208

- Measuring What a Specification Determines: A Formal Semantic-Block Model and an Execution-Judged Benchmark
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19475

- Towards Clinically Faithful Medical Image Captioning via Enhanced Vision-Language Alignment
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19825

- Natural Language Code Retrieval for 1C:Enterprise: An Open Benchmark and Efficient Bi-Encoder
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19957

- Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Language Models
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.18738

- A Speech Corpus for Mizo Automatic Speech Recognition: Whisper and SraVaani 1.0 Fine-Tuning with Morphology-Aware Evaluation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19361

- Automated Summarization of Financial News Using Large Language Models and Retrieval-Augmented Generation: An Early Empirical Study (Fall 2023)
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19526

- EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.26170

- Mitigating GenAI-Powered Evidence Pollution for Out-Of-Context Misinformation Detection
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.14728

- Multi-Agent Orchestration with the Common-Sense Reasoning Capabilities of LLMs for Autonomous Driving
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20129

- Stopping and Routing LLM Judge Panels
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19802

- The Asymmetric Harms of LLM Compression
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19670

- Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.13731

- Linguistic Holonomy and Statistical Watermarks: Inner Geometry of Meaning-Preserving Transformations
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19369

- ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19662

- Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.28969

- Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.21875

- Phantom Gains: Auditing Self-Improvement Against a Measured Null
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20290

- Does Listening Matter? Backchanneling and Nodding in AI Clone
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19527

- Mitigating Identity Essentialism in LLM Agents with Longitudinal Life Trajectories
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19621

- SPyCE: Skill-Policy Co-evolution for Multimodal Agents
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.13854

- Generating Diverse Personas for User Simulators to Test Interview Dialogue Systems
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19549

- Robust Incomplete Multimodal Sentiment Analysis via Iterative Proxy Correction
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19971

- Language Has Two Parameters: Narrative-Induced Semantic Plasticity and Phase-Sensitive Interpretation
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18041

- An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20320

- Qworld: Question-Specific Evaluation Criteria for LLMs
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.23522

- Explainable Multimodal Depression Recognition in Clinical Interviews via PHQ-Aligned Symptom Summarization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2501.16106

- Inducing Task Models from Computer-Use Traces
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20319

- Learning how to Forget: Fine-tuning for Long-Context Sparse Attention
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19920

- PTXBench: Benchmark and Adapt LLMs for GPU Kernel Optimization with Architecture-specific PTX
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.17379

- ContractScrub: A benchmark for final review of legal contracts
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20204

- Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20281

- Compliance, Capability, and Conflict: Benchmarking Multimodal LLMs under System Messages
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19207

- When Contextual Inference Fails: Cancelability in Interactive Instruction Following
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.19997

- ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2508.00554

- Can Agent Memory Systems Track Evolving State?
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19652

- HealMed: Multilingual Evaluation of Large Language Models in Medicine
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19981

- A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19875

- RepSelect: Robust LLM Unlearning via Representation Selectivity
  Source: arxiv-cs-cl
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.17168

- Gravitational-wave parameter estimation with machine-learning generated surrogate waveforms
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20222

- A Standardized Framework for Machine Learning in Power System Protection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20181

- Drift-Adaptive ICU Intervention Prediction: Freezing the Physiological Encoder for Auditable Model Updating
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.19020

- TorchDCM: A Unified PyTorch-Native Package for Discrete Choice Modeling
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19231

- Far from the Crowd: Scalable Self-Supervised Learning via Geographic Isolation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19766

- Transfer Learning in Nonparametric Regression with Deep ReLU Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20255

- FinVerse: Financial Time-Series Benchmark
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.03259

- A Unified Physics-Informed Neural Network for Modeling Coupled Electro- and Elastodynamic Wave Propagation Using Three-Stage Loss Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.13811

- FleetSieve: Decision-Critical Profiling for SLO-Aware LLM Fleet Configuration
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19659

- Unsupervised Anomaly Detection Using Flow Matching on Tabular Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19801

- Continuous Adversarial MeanFlow Transfer
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19540

- Demons on a Budget: Adaptive Measurement Placement at the Entanglement Phase Transition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19248

- Why Can't I See My Clusters? A Precision-Recall Approach to Dimensionality Reduction Validation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.04222

- Why AI Detection Fails for Academic Integrity
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11256

- SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20117

- CLaST: Context-aware Contrastive VAE for Probabilistic Time Series Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20025

- Composition-Driven Phase Evolution in Sm-Doped BiFeO3 via Latent-Field Reconstruction of Atomically Resolved STEM Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19544

- What You Can't See Is What You Learn: Restricted Evidence Visibility Favors Compositional Generalization in Shared-Genome Language-Model Societies
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20054

- Uncovering the Limits of Proof Sharing for Neural Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19351

- Bootstrap Theory of Representational Emergence (TBER): Explanatory Insufficiency, Transition Regimes, and the Emergence of New Representational Levels
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.07303

- Discrete Diffusion Inference-Time Control with Nested Sequential Monte Carlo
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20123

- Scale-Aware Pretraining of Time Series Foundation Models via Multi-Patch Token Alignment and Hybrid Masking
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20005

- RequestRouter: Request-Boundary Routing for Efficient Single-GPU LLM Inference
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.23057

- Learning piecewise-smooth dynamical systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19785

- Recovering Nonlinear Functions of Latent Variables: A Plausible-Value Neural Network Framework
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19282

- FAR-DPO: Feasibility-Aware and Robust Direct Preference Optimization for Cyclic Peptide Design
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19808

- G-MARK: Grounded Multi-Agent Reasoning for Cooperative Driving via Knowledge Graphs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19964

- Time-Series Retrieval for Grounding Multimodal Language Models in Remaining Useful Life
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19218

- DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20052

- A Two-Stage Time-Aware Transformer for Short-Horizon AECOPD Risk Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19578

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

- Feature Evolution and Migration during Vision Transformer Training
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20134

- Quantum Kernel Estimation for the Discovery of Early Lung Cancer Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19304

- DeltaML-Bench: Evaluating Machine Learning Agents on Real-World Research Repositories
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19653

- Rationally Enriched Chebyshev Trunk Bases for DeepONet Surrogates of High P\'eclet Entrance Transport
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19658

- GraphPFN: A Prior-Data Fitted Graph Foundation Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.21489

- SAGE-XGBoost: Spatially Augmented Graph Embeddings--Machine Learning Framework for Natural Hazards Susceptibility Mapping under Data Scarcity
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19672

- Which Eviction Policy Should an LLM Cache Use? A Systematic Study Across Workloads, Capacities, and Encoders
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20280

- Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19669

- Structured Affinity for Unsupervised Visual Class-Incremental Memory in Deep Artificial Immune Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20104

- The Value of Finite Observation in Positive-Data Learning of Multiple Context-Free Languages
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.11644

- From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.23955

- DICS: Data-Informed Centroid Splitting for Decision Tree Classifiers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20258

- Graph Machine: Exploring Edge Mechanisms as an Inductive Bias
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.06834

- Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19297

- Uncertainty-Aware Compositional Localization and Placement Assessment of Catheters and Tubes in Chest X-Rays
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11288

- Table2Image: Lightweight Tabular Learning with Generated Proxy Representations and Reliability Diagnostics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2412.06265

- Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.23689

- A comparison between ceiling-mounted FMCW, IR-UWB and Wi-Fi radar for in-bedroom human activity monitoring and sleep interruption detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20322

- Answer-Level Trust Selection for Physical Vision-Language Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19807

- Ask Self, Ask Others: Relation Is All You Need
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20172

- Which Negatives Matter? Ask Your Text Encoder: Adaptive Similarity Margins for Dense-Caption Retrieval
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18521

- Flow Matching Meets 3D Curvilinear Structure Segmentation in Medical Imaging
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19965

- Longitudinal Bayesian Learning of Continuous Disease Position across the Alzheimer's Disease Continuum
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19436

- Maximum Likelihood Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.02710

- From Noise to Signal: Improving Security Log Anomaly Detection Using LLMs with Endpoint-Specific Logs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19938

- Interpretable Feature Learning for RF Fingerprinting via Polar MKANs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19881

- HYDRA: A Heterogeneous Chiplet DSE Framework for Serving Dynamic Hybrid LLM Workloads
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19395

- Quantum Gaussian processes for prediction of channel observations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19306

- CarBench: A Comprehensive Benchmark for Neural Surrogates on High-Fidelity 3D Car Aerodynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.07847

- Grounded verification of chemical and materials reasoning: detection is the bottleneck
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.17417

- Microlensify: a Transformer Based Machine Learning Classifier for Microlensing Events Trained on TESS Light Curves
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19419

- Evaluating Neural Cartographic Relief Shading for Urban Environments: A Downtown Calgary Study Using High-Resolution DEM and DSM Data
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20149

- M3: A State-Event Generative Foundation Model for Market Microstructure Dynamics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19227

- 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

- Auditing Recorded Predictive Lead Service-Line Classifications Against Physical Verification: A Statewide Study of New York
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19922

- Orthogonal JEPA: Factorized Predictive States for Latent World Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20065

- Asymptotic Theory for IV-Based Reinforcement Learning with Potential Endogeneity
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2103.04021

- Towards Formalizing Reinforcement Learning Theory: A Robbins-Siegmund Approach
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2511.03618

- ReAugment: Model Zoo-Guided RL for Few-Shot Time Series Augmentation and Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2409.06282

- AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20318

- VQC-ZTI: Variational Quantum Control for Zero Trust Protection of the Tactile Internet
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18572

- Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19836

- Empirical Characterization of Learning Geometry in Hybrid Quantum Forecasting Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19497

- Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19408

- LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19463

- Deep neural networks as lattice gauge theories
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19331

- Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2406.09770

- Automating Learner Assessment: Benchmarking Machine Learning and Deep Learning Models for EEG-Based Familiarity Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.16541

- LODESTAR: Robust Entropy-Based Answer Selection in Retrieval-Augmented Generation for Question Answering -- Directing Frozen-LLM Entropy with a Reinforcement-Learned Prompt Polarizer under Misleading Passages
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.11922

- Physical-Support Confidence Sets for Highly Coherent Dictionaries
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20295

- MulTTiPop: A Multitrack Transcription Dataset for Pop Music
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.08756

- Virtual Sensing to Enable Real-Time Monitoring of Inaccessible Locations & Unmeasurable Parameters
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2412.00107

- Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19858

- The Price of Hidden Curvature: Improved Lower Bounds for Bandit Convex Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.18652

- Systematic Evaluation of TabPFN-TS for Zero-Shot Probabilistic Heat Load Forecasting in District Heating Networks
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20024

- Daedalus-150M: A Convolution-Attention Hybrid Designed for CPU Inference
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20210

- Triangular Fuzzy Rescaling Distance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19234

- GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.00140

- Learn for Variation: Efficient AAV Trajectory Learning through a Differentiable Wireless World Model
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2603.18853

- In Two Minds about Lifelong Learning: Exploring Hemispheric Redundancy and Specialisation in Neural Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19514

- R\'enyi Sharpness: A Novel Sharpness that Strongly Correlates with Generalization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.07758

- Too Sure to Be Safe: Model Calibration for Reliable Log Anomaly Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.17965

- Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19490

- HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.13710

- Provably Efficient Self-Calibrating Quantum Fault Tolerance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.05686

- PETA:Parameter-Efficient Test-Time Adaptation for Virtual Screening
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19906

- Quantifying Event Impacts on Time Series via Multiscale Contrastive Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19447

- Partition of Unity Neural Networks for Interpretable Classification with Explicit Class Regions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.00511

- Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18578

- DeltaMomentum: A Key-Value based Anisotropic Momentum Update via Delta Rule
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19491

- Reliable Neural Collapse Approximation for Open-World Test-Time Adaptation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19890

- LLM Capability Limits: Static Emergence and Dynamic Boundary Control
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.01548

- Data-Driven Time-Varying Control Barrier Functions for Adaptive Safe-Set Learning with Online Decremental Support Vector Machines
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19366

- The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.24856

- Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.15949

- Agents unlock new capabilities through Switching LoRA Adapters as a Tool (SLAaaT)
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.17034

- Unregularized Convergence of Single-Loop, Entropy-Regularized Natural Actor-Critic
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19587

- The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.29411

- Learning Hierarchical Skill Policies with Offline Quality-Diversity Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19684

- Evidence Before Expansion: Reuse, Spawn, or Defer in Lifelong Expert Pools
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19888

- Deep-MKV-TS: Path-Dependent McKean--Vlasov Control for Financial Time Series Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19394

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

- A Locally Tokenized Generative Model for Robust Time-Series Watermarking
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19727

- Higher Resolution, Better Generalization: Unlocking Visual Scaling in Deep Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.10546

- RecPFN: Prior-Fitted Networks for In-Context-Based Recommendations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19735

- MileGPO: Milestone Inference with Local Evidence for Graph-Based Policy Optimization of Long-Horizon LLM Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19803

- A Layered Simplex Architecture for Large Alphabets
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19908

- Beyond Multimodal Alignment: Certifying Physical Language through Response Substitution and Ordered Execution
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19492

- A Neurosymbolic Approach for Explainable Early Diagnosis of Alzheimer's Disease
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.29530

- Learning Asymptotics with Convergence-Rate Guarantees using Linear Least Squares
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.23287

- An Irreducible Quantum Advantage in Aligning World Models with Reality
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19779

- Distributional Determinantal Point Process for Repulsive Clustering of Distributions
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.21847

- Where Does the Union Bound Go? Best-Arm Identification and Strong FWER Control
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19903

- Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19760

- Learning-Based Speed Estimation from Accelerometer-Only Inertial Sensing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2401.07468

- Detecting Explanatory Insufficiency in Learned Representations: A Framework for Representational Vigilance
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.13172

- Reward-Guided Autoregressive Graph Generation for Efficient Multi-Agent Communication Topology Design
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20099

- Inadvertent Context Leakage in Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19857

- Teacher-free Latent Self-distillation and Class-separable Representations for Lightweight IoT Attack Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2403.15509

- Separating Covariate Shift from Mechanism Change with Two Discriminators: CJSD, a Conditional Discrepancy with an Exact Covariate-Concept Decomposition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19885

- Continual Reasoning Gym: Diagnosing and Harnessing Shared Reasoning in Continual RLVR
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18574

- Information on trajectories: martingales and random times
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20337

- From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.01476

- On the convergence of optimistic policy iteration for stochastic shortest path problem
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/1808.08763

- Graphical Design of Interpretable Architectures
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.18936

- Geometric Evolution Maps: Extracting Stable Concept Probes from Transformer Residual Streams
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.25848

- When Is Shallow Enough? Adaptive Split Federated Learning with Client-Specific Sufficiency Estimation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.15639

- Concentrated Liquidity Provision: a Reinforcement Learning Perspective
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19389

- HiRA-CAM: Preserving Fine-Grained Spatial Relevance in Gradient-Based Visual Explanations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19407

- Asymmetric Attention Heads: Structured Head-Wise Context Allocation for Transformer Attention
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19203

- ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2506.07459

- Heteroscedastic Neural Surrogate Modeling for Robust and Rapid Bayesian Inference in Fusion Plasma Diagnostics
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19377

- From Street View Imagery to Street Quality Indicators: Vision Language Inference for the Suburban 15-minute City
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20026

- From Prediction to Self: Developmental Conditions for Agency in Minimal Neural Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.05605

- Decoding silent reading from non-invasive EEG
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20186

- Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.22950

- Continuous Behavioral Authentication via Multi-Expert BERT Log Analysis for Secure Data Sharing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.21900

- Improved Confidence Estimates for Black-Box Large Language Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19323

- Green BOA: Determining the environmental break-even point for ML-based data compression
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19994

- Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2607.07382

- Explainable Transformer Models for Clinical Prediction Tasks on Structured Electronic Health Records
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20315

- skchange: Fast and Flexible Algorithms for Changepoint Detection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19767

- Question-Guided Evidence Acquisition for Multimodal Visual Question Answering
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19739

- Truncate Bad, Upweight Good: BoN-Style Distillation via Rank-Based Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19748

- Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2509.05441

- Guided Diffusion by Optimized Loss Functions on Relaxed Parameters for Inverse Material Design
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.15648

- Causal Inference under Interference with Learned Exposure Mappings
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19224

- Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19611

- Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20183

- EnvHarness: Awakening Static Worlds for Agent Learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19880

- Auditing Cross-Lingual Fairness in Language Model Watermarking
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20047

- Towards On-Board Implementation of ML-Based Helicopter Weight Estimator
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19210

- Spike-based Belief Propagation in Nonlinear Dynamical Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19907

- Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19338

- DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2505.20894

- SCAPE: Scenario-Conditioned Simulation-Augmented Policy Evaluation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19425

- Neural Prior Estimation: Learning Class Priors from Latent Representations
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.17853

- End-to-end Early Classification of Time Series in Non-Stationary Environments
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20044

- Projector Is All You Train
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19726

- $TCP_\alpha$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20326

- The impact of feature engineering and an optimisation framework for ocean colour machine learning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19899

- RIPE++: Reinforced Keypoint Learning from Positive Pairs Only
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19693

- Multi-Modal Graph Interaction for Multi-Graph Convolution Network in Urban Spatiotemporal Forecasting
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/1905.11395

- Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2604.06501

- Verifiably grounded machine interpretation of lunar geology
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.09276

- DraftFM: A FoundationModel for Day-Zero Drafting in Magic: The Gathering
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19568

- Active Inference as Context Acquisition for AI Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19202

- Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20061

- Dynamic Structural Causal Modeling for Sleep
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20285

- CacheRoute: Planned Prefix-Affinity Routing for Large-Scale LLM Serving
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19677

- PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19861

- Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulness under Optimization
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.24960

- Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20169

- K\"ahler landscapes for complex neural network descents and guarantees including a search and destroy of the Calabi-Yau manifold
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19584

- Time-Uniform Self-Normalized Concentration for Discounted Least Squares: Limits and Corrections
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19643

- Better Call Graphs: A New Dataset of Function Call Graphs for Malware Classification
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2512.20872

- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal Prostate MRI Segmentation
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2510.17529

- A Robust In-Context Model for Conservation Laws: Injecting Context into Flux Neural Operators via Recurrent Vision Transformers
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2605.05488

- Complementary, Not Cumulative: Interaction Effects in Physics-Informed Neural Networks for Navier-Stokes Vortex Shedding
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19632

- Learning Deterministic and Stochastic Forced Hamiltonian Systems
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19688

- MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20202

- Clustering and Token Denoising for Faster and More Robust VLMs
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19285

- Finite-Horizon Input-Output Dynamics of Minibatch Perturbations in AdamW
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19762

- PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2606.08926

- Active Spiking Perception: The Membrane Potential as a Belief State for Anytime 3D Point Cloud Recognition
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19232

- Reducing the Complexity of Matrix Multiplication by Quantum Computing
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2602.05541

- An Inclusive and Lightweight Approach to Federated Continual Learning for Cultural Heritage
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.20038

- A Repeated Measurements Approach to $SoH$ Battery Modelling of Cyclic Aged Data in a Laboratory Environment
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19879

- When to Retrain: An Empirical Study of Retraining Policies for Streaming ML Under Concept Drift, Budget, and Latency Constraints
  Source: arxiv-cs-lg
  Topic: AI Research (+AI)
  URL: https://arxiv.org/abs/2608.19488

## Community

- llm 0.32.1
  Source: simon-willison
  Topic: Python (+AI, Django)
  URL: https://simonwillison.net/2026/Aug/21/llm/

- llm-openrouter 0.7
  Source: simon-willison
  Topic: Python (+AI, Django)
  URL: https://simonwillison.net/2026/Aug/21/llm-openrouter/

- Stop Making TUIs
  Source: simon-willison
  Topic: Python (+AI, Django)
  URL: https://simonwillison.net/2026/Aug/21/stop-making-tuis/

- Quoting Matt Webb
  Source: simon-willison
  Topic: Python (+AI, Django)
  URL: https://simonwillison.net/2026/Aug/21/matt-webb/

## Media

- Hugging Face Journal Club: Training AI Scientists to Replicate Research
  Source: youtube-huggingface
  Topic: Hugging Face (+AI)
  URL: https://www.youtube.com/watch?v=HxahKqN1q2g