DailyArxiv - AI Research Podcast

Today's papers: - Neural posterior estimation of the neutrino direction in IceCube using transformer-encoded normalizing flows on the sphere: https://arxiv.org/abs/2604.19846v1 - Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs: https://arxiv.org/abs/2604.19292v1 - Large Language Models Exhibit Normative Conformity: https://arxiv.org/abs/2604.19301v1 - Design Rule...

Today's papers: - OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural Tokens: https://arxiv.org/abs/2604.18827v1 - Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence: https://arxiv.org/abs/2604.18292v1 - The Collaboration Gap in Human-AI Work: https://arxiv.org/abs/2604.18096v1 - $R^2$-dLLM: Accelerating Diffusion Large La...

Today's papers: - MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment: https://arxiv.org/abs/2604.17007v1 - Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale: https://arxiv.org/abs/2604.18572v1 - mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval: https://arxiv.org/abs/2604.17054v1 - Integrating Gra...

Today's papers: - Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval: https://arxiv.org/abs/2604.15951v1 - ECG-Lens: Benchmarking ML & DL Models on PTB-XL Dataset: https://arxiv.org/abs/2604.15822v1 - DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy: https://arxiv.org/abs/2604.15851v1 - NeuroLip: An Event-driven Spatiotemporal Learning Framework for Cro...

Today's papers: - Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation: https://arxiv.org/abs/2604.13956v1 - Agent-Aided Design for Dynamic CAD Models: https://arxiv.org/abs/2604.15184v1 - Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications: https://arxiv.org/abs/2604.15233v1 - Retrieve, Then Classify: Corpus-Grounded...

Today's papers: - Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective: https://arxiv.org/abs/2604.14025v1 - GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis: https://arxiv.org/abs/2604.13888v1 - A Dynamic-Growing Fuzzy-Neuro Controller, Application to a 3PSP Parallel Robot: https://arxiv.org/abs/2604.13763v1 - MAny: Merge Anything for Multimodal C...

Today's papers: - NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1): https://arxiv.org/abs/2604.12512v1 - RePAIR: Interactive Machine Unlearning through Prompt-Aware Model Repair: https://arxiv.org/abs/2604.12820v1 - Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation: https://arxiv.org/abs/2604.12424v...

Today's papers: - Automating Structural Analysis Across Multiple Software Platforms Using Large Language Models: https://arxiv.org/abs/2604.09866v1 - Structuring versus Problematizing: How LLM-based Agents Scaffold Learning in Diagnostic Reasoning: https://arxiv.org/abs/2604.09158v1 - PhysInOne: Visual Physics Learning and Reasoning in One Suite: https://arxiv.org/abs/2604.09415v1 - HM-Bench: A Co...

Today's papers: - LMGenDrive: Bridging Multimodal Understanding and Generative World Modeling for End-to-End Driving: https://arxiv.org/abs/2604.08719v1 - Vision Transformers for Preoperative CT-Based Prediction of Histopathologic Chemotherapy Response Score in High-Grade Serous Ovarian Carcinoma: https://arxiv.org/abs/2604.09197v1 - An Imperfect Verifier is Good Enough: Learning with Noisy Reward...

Today's papers: - MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning: https://arxiv.org/abs/2604.08203v1 - IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling: https://arxiv.org/abs/2604.08033v1 - How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace: https://arxiv.org/ab...

Today's papers: - Emotion Concepts and their Function in a Large Language Model: https://arxiv.org/abs/2604.07729v1 - Small Vision-Language Models are Smart Compressors for Long Video Understanding: https://arxiv.org/abs/2604.08120v1 - PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models: https://arxiv.org/abs/2604.08340v1 - Uni-ViGU: Towards Unified Video Generation and Un...

Today's papers: - LPM 1.0: Video-based Character Performance Model: https://arxiv.org/abs/2604.07823v1 - HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology: https://arxiv.org/abs/2604.08305v1 - Enabling Intrinsic Reasoning over Dense Geospatial Embeddings with DFR-Gemma: https://arxiv.org/abs/2604.07490v1 - Faithful GRPO: Improving Vi...

Today's papers: - LLMs Should Express Uncertainty Explicitly: https://arxiv.org/abs/2604.05306v1 - Semantic-Topological Graph Reasoning for Language-Guided Pulmonary Screening: https://arxiv.org/abs/2604.05620v1 - Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models: https://arxiv.org/abs/2604.06912v1 - Flowr -- Scaling Up Retail Supply Chain Operations Through Ag...

Today's papers: - StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing: https://arxiv.org/abs/2604.05014v1 - QED-Nano: Teaching a Tiny Model to Prove Hard Theorems: https://arxiv.org/abs/2604.04898v1 - Thinking Diffusion: Penalize and Guide Visual-Grounded Reasoning in Diffusion Multimodal Language Models: https://arxiv.org/abs/2604.05497v1 - MedGemma 1.5 Technical Report: htt...

Today's papers: - A Generative Foundation Model for Multimodal Histopathology: https://arxiv.org/abs/2604.03635v1 - TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables: https://arxiv.org/abs/2604.03660v1 - ROSClaw: A Hierarchical Semantic-Physical Framework for Heterogeneous Multi-Agent Collaboration: https://arxiv.org/abs/2604.04664v1 - FeynmanBe...

Today's papers: - SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation: https://arxiv.org/abs/2603.22228v1 - Mind over Space: Can Multimodal Large Language Models Mentally Navigate?: https://arxiv.org/abs/2603.21577v1 - Tiny Inference-Time Scaling with Latent Verifiers: https://arxiv.org/abs/2603.22492v2 - Cerebra: A Multidisciplinary A...

Today's papers: - The Library Theorem: How External Organization Governs Agentic Reasoning Capacity: https://arxiv.org/abs/2603.21272v1 - AgentHER: Hindsight Experience Replay for LLM Agent Trajectory Relabeling: https://arxiv.org/abs/2603.21357v1 - RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models: https://arxiv.org/abs/2603.21341v1 - QMoP: Que...

Today's papers: - Analysis of Optimality of Large Language Models on Planning Problems: https://arxiv.org/abs/2604.02910v1 - Efficient3D: A Unified Framework for Adaptive and Debiased Token Reduction in 3D MLLMs: https://arxiv.org/abs/2604.02689v1 - How and why does deep ensemble coupled with transfer learning increase performance in bipolar disorder and schizophrenia classification?: https://arxi...

https://www.nature.com/articles/s41562-025-02324-0 **Episode Description** Ever wonder how your brain learns from rewards? For decades, scientists have used simple reinforcement learning models to explain this—basically, your brain keeps a running score and updates it with each new experience. But a fascinating new study suggests that picture is way too simple. Researchers built hybrid models comb...

Today's papers: - Transformer self-attention encoder-decoder with multimodal deep learning for response time series forecasting and digital twin support in wind structural health monitoring: https://arxiv.org/abs/2604.01712v1 - DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning: https://arxiv.org/abs/2604.01765v1 - SHOE: Semantic HOI Open-Vocabulary Eva...

Today's papers: - Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models: https://arxiv.org/abs/2604.01840v1 - ActionParty: Multi-Subject Action Binding in Generative Video Games: https://arxiv.org/abs/2604.02330v1 - ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic Based Cues: https://arxiv.org/abs/2604.01925v1 -...

Today's papers: - Online Reasoning Calibration: Test-Time Training Enables Generalizable Conformal LLM Reasoning: https://arxiv.org/abs/2604.01170v1 - LiveMathematicianBench: A Live Benchmark for Mathematician-Level Reasoning with Proof Sketches: https://arxiv.org/abs/2604.01754v1 - Lifting Unlabeled Internet-level Data for 3D Scene Understanding: https://arxiv.org/abs/2604.01907v1 - Look Twice: T...

Today's papers: - A Reasoning-Enabled Vision-Language Foundation Model for Chest X-ray Interpretation: https://arxiv.org/abs/2604.00493v1 - Brainstacks: Cross-Domain Cognitive Capabilities via Frozen MoE-LoRA Stacks for Continual LLM Learning: https://arxiv.org/abs/2604.01152v1 - Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models: https://arxiv.org/abs/2604.00445v1 - Be...

Today's papers: - Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization: https://arxiv.org/abs/2603.24093v1 - SM-Net: Learning a Continuous Spectral Manifold from Multiple Stellar Libraries: https://arxiv.org/abs/2603.23899v2 - A Deep Dive into Scaling RL for Code Generation with Synthetic Data and Curricula: https://arxiv.org/abs/2603.24202v1 - When Understand...

Today's papers: - SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling: https://arxiv.org/abs/2603.23414v1 - Contrastive Metric Learning for Point Cloud Segmentation in Highly Granular Detectors: https://arxiv.org/abs/2603.23356v1 - VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAs: https://arxiv.org/abs/2603.23481v1 - LLMLOOP: Improving L...