DailyArxiv - AI Research Podcast

Today's papers: - Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks: https://arxiv.org/abs/2607.07907v1 - COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation: https://arxiv.org/abs/2607.08071v1 - Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native...

Today's papers: - Ad Headline Generation using Self-Critical Masked Language Model: https://arxiv.org/abs/2607.06818v1 - SPEAR: A Simulator for Photorealistic Embodied AI Research: https://arxiv.org/abs/2607.06701v1 - TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting: https://arxiv.org/abs/2607.06349v1 - Search, Fail, Recover: A Training Framework f...

Today's papers: - Unified Audio Intelligence Without Regressing on Text Intelligence: https://arxiv.org/abs/2607.05196v2 - LLM-as-a-Verifier: A General-Purpose Verification Framework: https://arxiv.org/abs/2607.05391v2 - DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation: https://arxiv.org/abs/2607.05147v1 - Wasserstein Residuals: Learning Gradient Flows from Pop...

Today's papers: - Where do LLMs Fall Short in CBT-Guided Affective Reasoning?: https://arxiv.org/abs/2607.02885v1 - DynaVieW: Schema-Guided World Modeling for Understanding Hierarchical Visual Dynamics: https://arxiv.org/abs/2607.04112v1 - Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs: https://arxiv.org/abs/2607.04371v1 - Unsupervised Features Mining via Activation Geometry: https://...

Today's papers: - PACE: A Proxy for Agentic Capability Evaluation: https://arxiv.org/abs/2607.02032v1 - Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction: https://arxiv.org/abs/2607.01764v1 - AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanations: https://arxiv.org/abs/2607.01934v1 - UA-ChatDev: Uncertainty-Aware Multi-Agen...

Today's papers: - Loss Smoothing for Stable Adaptation Under Distribution Shift: https://arxiv.org/abs/2607.00634v1 - Coachable agents for interactive gameplay: https://arxiv.org/abs/2607.00642v1 - Diffusion-GR2: Diffusion Generative Reasoning Re-ranker: https://arxiv.org/abs/2607.01170v1 - CausalMix: Data Mixture as Causal Inference for Language Model Training: https://arxiv.org/abs/2607.01104v1...

Today's papers: - Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents: https://arxiv.org/abs/2606.31270v1 - A Technical Typology of AI Systems in Public Administration: https://arxiv.org/abs/2606.31755v1 - DigitalCoach: Communication and Grounding Gaps in Human and Agentic Computer Use Coaching: https://arxiv.org/abs/2606.31980v1 - A Tutorial on Autonomous Fault-Tolerant...

Today's papers: - SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematics - Mandol: An Agglomerative Agent Memory System for Long-Term Conversations - TDGT: A Tabular Data Generation Toolkit supporting adaptive GPU-accelerated Bayesian mixture models, diffusion-based models, and latent-space generative modeling - Cross-lingual Relation Extraction with Large Language Mod...

Today's papers: - Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation: https://arxiv.org/abs/2606.27978v1 - The CRISTAL Method: Neurosymbolic analysis from AI-synthesized world models: https://arxiv.org/abs/2606.29799v1 - Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing: https://arxiv.org/abs/2606.30555v1 - BTI-Net: Bidirectional Decoder-Level Task...

Today's papers: - Autoregressive Boltzmann Generators: https://arxiv.org/abs/2606.27361v1 - Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs: https://arxiv.org/abs/2606.27909v1 - A Latent ODE Approach to Spatiotemporal Modeling of Cine Cardiac MRI: https://arxiv.org/abs/2606.26718v1 - Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks: https://arxiv.or...

Today's papers: - The Capability Frontier: Benchmarks Miss 82% of Model Performance: https://arxiv.org/abs/2606.26836v1 - Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection: https://arxiv.org/abs/2606.26552v1 - auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation: https://arxiv.org/abs/26...

Today's papers: - Project Auto-World: Towards Automated Benchmarking of Neural Relational Reasoners: https://arxiv.org/abs/2606.24965v1 - Benchmarking the Alignment of Data-Quality Metrics, Human Judgment and Land-Cover Segmentation Performance for Earth Observation: https://arxiv.org/abs/2606.25128v1 - Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models a...

Today's papers: - Female-RHINO: A Real-Time Scanner-Integrated Framework for Automated Quantitative Uterine MRI Analysis and Structured Reporting: https://arxiv.org/abs/2606.24390v1 - A Fair Evaluation of Graph Foundation Models for Node Property Prediction: https://arxiv.org/abs/2606.24509v1 - IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation: https://arxiv.org...

Today's papers: - Generating Public Health Responses using Survey-Augmented Large Language Models: https://arxiv.org/abs/2606.21820v1 - Evaluating Large Language Models for Hausa and Fongbe Machine Translation: Benchmarks, Failures, and Metric Reliability: https://arxiv.org/abs/2606.22269v1 - Foundation Models for Epileptogenic Zone Identification in Drug-Resistant Epilepsy: https://arxiv.org/abs/...

Today's papers: - Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings: https://arxiv.org/abs/2606.19744v1 - Co-policy: Responsive Human-Robot Co-Creation for Musical Performances: https://arxiv.org/abs/2606.19914v1 - How Transparent is DiffusionGemma?: https://arxiv.org/abs/2606.20560v1 - See-and-Reach: Precise Vision-Language Navigation for U...

Today's papers: - Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages: https://arxiv.org/abs/2606.20517v1 - Scaling Generative Foundation Models for Chest Radiography with Rectified Flow Transformers: https://arxiv.org/abs/2606.19460v1 - PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models: https://arxiv.org/abs/2606.19534v1 - Review of Machine Learn...

Today's papers: - Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training: https://arxiv.org/abs/2606.19004v1 - MIVE: A Minimalist Integer Vector Engine for Softmax LayerNorm and RMSNorm Acceleration: https://arxiv.org/abs/2606.17781v1 - Better Adherence, Richer Context: A Field Evaluation of LLM-Powered Conversational Voice Diaries for Sleep: https://arxiv.org/abs/2606.1859...

Today's papers: - Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning: https://arxiv.org/abs/2606.16118v1 - Scalable Circuit Learning for Interpreting Large Language Models: https://arxiv.org/abs/2606.16939v1 - Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering: https://arxiv.org/abs/2606.17257v1 - WE...

Today's papers: - Every Eval Ever: A Unifying Schema and Community Repository for AI Evaluation Results: https://arxiv.org/abs/2606.14516v1 - Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning: https://arxiv.org/abs/2606.15007v1 - Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time Torque Feedback: https:/...

Today's papers: - SuperThoughts: Reasoning Tokens in Superposition: https://arxiv.org/abs/2606.13862v1 - Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources: https://arxiv.org/abs/2606.14141v1 - EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery: https://arxiv.org/abs/2606.13662v2 - Reasoning for Mobile User Experience with Multimodal LLMs:...

Today's papers: - Toward Generalist Autonomous Research via Hypothesis-Tree Refinement: https://arxiv.org/abs/2606.11926v1 - Mathematical perspective on genetic algorithms with optimization guided operators: https://arxiv.org/abs/2606.12279v1 - Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics: https://arxiv.org/abs/2606.12365v1 - ALIGNBEAM : Inference-Time Alignment Tr...

Today's papers: - ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models: https://arxiv.org/abs/2606.11164v1 - DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?: https://arxiv.org/abs/2606.12402v1 - UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation: https://arxiv.org/abs/2606.10466v1 - ABC-Bench: An...

Today's papers: - Do VLMs Reason Like Engineers? A Benchmark and a Stage-wise Evaluation: https://arxiv.org/abs/2606.10833v1 - Difference-Aware Retrieval Policies for Imitation Learning: https://arxiv.org/abs/2606.09758v1 - Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents: https://arxiv.org/abs/2606.10209v1 - Advancing the State-of-the-Art in Empiri...

Today's papers: - ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning: https://arxiv.org/abs/2606.06915v2 - Mitosis Detection in the Wild: Multi-Tumor and Context-Aware Generalization in the MIDOG 2025 Challenge: https://arxiv.org/abs/2606.07368v1 - A robust PPG foundation model using multimodal physiological supervision: https://arxiv.org/abs/2606.07365v1 - Larch: Le...

Today's papers: - Consistency Training Along the Transformer Stack: https://arxiv.org/abs/2606.05817v1 - Learning Visual Spatial Planning from Symbolic State via Modality-Gap-Aware Self-Distillation: https://arxiv.org/abs/2606.06076v1 - Representation Learning Enables Scalable Multitask Deep Reinforcement Learning: https://arxiv.org/abs/2606.05555v1 - RREDCoT: Segment-Level Reward Redistribution f...