DailyArxiv - AI Research Podcast

Today's papers: - Agents of Chaos: https://arxiv.org/abs/2602.20021v1 - Recurrent Structural Policy Gradient for Partially Observable Mean Field Games: https://arxiv.org/abs/2602.20141v1 - Shape-informed cardiac mechanics surrogates in data-scarce regimes via geometric encoding and generative augmentation: https://arxiv.org/abs/2602.20306v1 - Assessing Risks of Large Language Models in Mental Heal...

Today's papers: - Defining Explainable AI for Requirements Analysis: https://arxiv.org/abs/2602.19071v1 - Learning to Detect Language Model Training Data via Active Reconstruction: https://arxiv.org/abs/2602.19020v1 - Asking the Right Questions: Improving Reasoning with Generated Stepping Stones: https://arxiv.org/abs/2602.19069v1 - Online Navigation Planning for Long-term Autonomous Operation of...

Today's papers: - DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference: https://arxiv.org/abs/2602.18846v1 - HONEST-CAV: Hierarchical Optimization of Network Signals and Trajectories for Connected and Automated Vehicles with Multi-Agent Reinforcement Learning: https://arxiv.org/abs/2602.18740v1 - BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Genera...

Today's papers: - MoDora: Tree-Based Semi-Structured Document Analysis System: https://arxiv.org/abs/2602.23061v1 - SC-Arena: A Natural Language Benchmark for Single-Cell Reasoning with Knowledge-Augmented Evaluation: https://arxiv.org/abs/2602.23199v1 - Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving: https://arxiv.org/abs/2602.23259v1 - ColoDiff: Integra...

Today's papers: - GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL: https://arxiv.org/abs/2602.22190v1 - Two-Stage Active Distribution Network Voltage Control via LLM-RL Collaboration: A Hybrid Knowledge-Data-Driven Approach: https://arxiv.org/abs/2602.21715v1 - Following the Diagnostic Trace: Visual Cognition-guided Cooperative Netw...

Today's papers: - OrthoDiffusion: A Generalizable Multi-Task Diffusion Foundation Model for Musculoskeletal MRI Interpretation: https://arxiv.org/abs/2602.20752v1 - SoK: Agentic Skills -- Beyond Tool Use in LLM Agents: https://arxiv.org/abs/2602.20867v1 - Some Simple Economics of AGI: https://arxiv.org/abs/2602.20946v1 - EKF-Based Depth Camera and Deep Learning Fusion for UAV-Person Distance Estim...

Today's papers: - Efficient endometrial carcinoma screening via cross-modal synthesis and gradient distillation: https://arxiv.org/abs/2602.19822v1 - CausalFlip: A Benchmark for LLM Causal Judgment Beyond Semantic Matching: https://arxiv.org/abs/2602.20094v1 - Agentic AI for Scalable and Robust Optical Systems Control: https://arxiv.org/abs/2602.20144v1 - MAS-FIRE: Fault Injection and Reliability...

Today's papers: - Aurora: Neuro-Symbolic AI Driven Advising Agent: https://arxiv.org/abs/2602.17999v1 - DohaScript: A Large-Scale Multi-Writer Dataset for Continuous Handwritten Hindi Text: https://arxiv.org/abs/2602.18089v1 - Conformal Tradeoffs: Guarantees Beyond Coverage: https://arxiv.org/abs/2602.18045v1 - "How Do I ...?": Procedural Questions Predominate Student-LLM Chatbot Conversations: ht...

Today's papers: - A Privacy by Design Framework for Large Language Model-Based Applications for Children: https://arxiv.org/abs/2602.17418v1 - AI Gamestore: Scalable, Open-Ended Evaluation of Machine General Intelligence with Human Games: https://arxiv.org/abs/2602.17594v1 - A feature-stable and explainable machine learning framework for trustworthy decision-making under incomplete clinical data:...

Today's papers: - AI-Driven Structure Refinement of X-ray Diffraction: https://arxiv.org/abs/2602.16372v1 - Retrieval Augmented Generation of Literature-derived Polymer Knowledge: The Example of a Biodegradable Polymer Expert System: https://arxiv.org/abs/2602.16650v1 - Articulated 3D Scene Graphs for Open-World Mobile Manipulation: https://arxiv.org/abs/2602.16356v1 - FlowPrefill: Decoupling Pree...

Today's papers: This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.

Today's papers: - MIND: Benchmarking Memory Consistency and Action Control in World Models: https://arxiv.org/abs/2602.08025v2 - A Kinetic-Energy Perspective of Flow Matching: https://arxiv.org/abs/2602.07928v1 - Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible: https://arxiv.org/abs/2602.10139v2 - DIAL-SUMMER: A Structured Evaluation Framework of Hierarchic...

Today's papers: - Deriving Neural Scaling Laws from the statistics of natural language: https://arxiv.org/abs/2602.07488v2 - TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Control: https://arxiv.org/abs/2602.07439v1 - Brep2Shape: Boundary and Shape Representation Alignment via Self-Supervised Transformers: https://arxiv.org/abs/2602.07429v1 - Can LLMs Truly Embody H...

Today's papers: - Malicious Agent Skills in the Wild: A Large-Scale Security Empirical Study: https://arxiv.org/abs/2602.06547v1 - DAVE: Distribution-aware Attribution via ViT Gradient Decomposition: https://arxiv.org/abs/2602.06613v1 - TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering: https://arxiv.org/abs/2602.06911v1 - AIRS-Bench: a Suite of Tasks for Fronti...

Today's papers: - Rethinking Zero-Shot Time Series Classification: From Task-specific Classifiers to In-Context Inference: https://arxiv.org/abs/2602.00620v1 - MCP-Atlas: A Large-Scale Benchmark for Tool-Use Competency with Real MCP Servers: https://arxiv.org/abs/2602.00933v1 - Forecasting Energy Availability in Local Energy Communities via LSTM Federated Learning: https://arxiv.org/abs/2602.00694...

Today's papers: - RovoDev Code Reviewer: A Large-Scale Online Evaluation of LLM-based Code Review Automation at Atlassian: https://arxiv.org/abs/2601.01129v2 - A Platform for Interactive AI Character Experiences: https://arxiv.org/abs/2601.01027v1 - ScienceDB AI: An LLM-Driven Agentic Recommender System for Large-Scale Scientific Data Sharing Services: https://arxiv.org/abs/2601.01118v1 - Does Mem...

Today's papers: - Automatic Question Generation for Intuitive Learning Utilizing Causal Graph Guided Chain of Thought Reasoning: https://arxiv.org/abs/2601.06098v1 - HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Experts: https://arxiv.org/abs/2601.00583v1 - Improving Scientific Document Retrieval with Academic Concept Index: https://arxiv.org/abs/2601.00567v1 - Avatar Fo...

Today's papers: - Data Science and Technology Towards AGI Part I: Tiered Data Management: https://arxiv.org/abs/2602.09003v1 - CIC-Trap4Phish: A Unified Multi-Format Dataset for Phishing and Quishing Attachment Detection: https://arxiv.org/abs/2602.09015v3 - ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation: https://arxiv.org/abs/2602.09014v1 - MUZ...

Today's papers: - LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation: https://arxiv.org/abs/2602.10367v1 - Towards Autonomous Mathematics Research: https://arxiv.org/abs/2602.10177v2 - Beyond Calibration: Confounding Pathology Limits Foundation Model Specificity in Abdominal Trauma CT: https://arxiv.org/abs/2602.10359v1 - ENIGMA: EEG-to-Image in 15 Minut...

Today's papers: - Enhancing Predictability of Multi-Tenant DNN Inference for Autonomous Vehicles' Perception: https://arxiv.org/abs/2602.11004v1 - Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System: https://arxiv.org/abs/2602.10915v1 - Fine-Tuning GPT-5 for GPU Kernel Generation: https://arxiv.org/abs/2602.11000v1 - Computational Phenomenology of Tem...

An in-depth exploration of 'Large Language Model Reasoning Failures' by Peiyang Song, Pengrui Han, Noah Goodman. Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, achieving impressive results across a wide range of tasks. Despite these advances, significant reasoning failures persist... This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.

Today's papers: - xList-Hate: A Checklist-Based Framework for Interpretable and Generalizable Hate Speech Detection: https://arxiv.org/abs/2602.05874v1 - Bagging-Based Model Merging for Robust General Text Embeddings: https://arxiv.org/abs/2602.05787v1 - Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations: https://arxiv.org/abs/2602.05885v1 - Metric Hedonic Games on the Lin...

Today's papers: - When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?: https://arxiv.org/abs/2602.04755v1 - El Agente Quntur: A research collaborator agent for quantum chemistry: https://arxiv.org/abs/2602.04850v1 - Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents: https://arxiv.org/abs/2602.04813v1 - Let Expert...

Today's papers: - $V_0$: A Generalist Value Model for Any Policy at State Zero: https://arxiv.org/abs/2602.03584v1 - Enhancing Imbalanced Node Classification via Curriculum-Guided Feature Learning and Three-Stage Attention Network: https://arxiv.org/abs/2602.03808v1 - Can LLMs Do Rocket Science? Exploring the Limits of Complex Reasoning with GTOC 12: https://arxiv.org/abs/2602.03630v1 - Controllin...

Today's papers: - RACA: Representation-Aware Coverage Criteria for LLM Safety Testing: https://arxiv.org/abs/2602.02280v1 - ReasonCACHE: Teaching LLMs To Reason Without Weight Updates: https://arxiv.org/abs/2602.02366v1 - Poly-attention: a general scheme for higher-order self-attention: https://arxiv.org/abs/2602.02422v1 - Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via...