Daily Paper Cast
Jingwen Liang, Gengyu Wang
We update every weekday to discuss highest-voted papers from Huggingface Daily Paper (https://huggingface.co/papers). Both the podcast scripts and audio are generated by AI. Feedback and suggestions are welcome! Email us: [email protected]:Jingwen Liang, 3D ML, https://www.linkedin.com/in/jingwen-liang/Gengyu Wang, LLM ML, http://wanggengyu.comListen on: Spotify: https://open.spotify.com/show/21nrhmdaA8qoBiH8q03NXLApple Podcast: https://podcasts.apple.com/us/podcast/daily-paper-...
Episodes (1777)
ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative R...
Daily Paper Cast
4DNeX: Feed-Forward 4D Generative Modeling Made Easy
Daily Paper Cast
Next Visual Granularity Generation
Daily Paper Cast
Speed Always Wins: A Survey on Efficient Architectures for Large Language Models
Daily Paper Cast
When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods...
Daily Paper Cast
Has GPT-5 Achieved Spatial Intelligence? An Empirical Study
Daily Paper Cast
HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Vir...
Daily Paper Cast
SSRL: Self-Search Reinforcement Learning
Daily Paper Cast
DINOv3
Daily Paper Cast
Thyme: Think Beyond Images
Daily Paper Cast
BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining
Daily Paper Cast
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerializati...
Daily Paper Cast
We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical R...
Daily Paper Cast
NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Sca...
Daily Paper Cast
PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over...
Daily Paper Cast
ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing
Daily Paper Cast
Story2Board: A Training-Free Approach for Expressive Storyboard Generation
Daily Paper Cast
Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery
Daily Paper Cast
Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation
Daily Paper Cast
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing
Daily Paper Cast
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term...
Daily Paper Cast
AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Probl...
Daily Paper Cast
Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchr...
Daily Paper Cast
Complex Logical Instruction Generation
Daily Paper Cast
Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models
Daily Paper Cast
HierSearch: A Hierarchical Enterprise Deep Search Framework Integrating Local an...
Daily Paper Cast
ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
Daily Paper Cast
WideSearch: Benchmarking Agentic Broad Info-Seeking
Daily Paper Cast
Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation
Daily Paper Cast
A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Found...
Daily Paper Cast
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Resear...
Daily Paper Cast
SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Spe...
Daily Paper Cast
Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping...
Daily Paper Cast
MolmoAct: Action Reasoning Models that can Reason in Space
Daily Paper Cast
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Daily Paper Cast
Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Tr...
Daily Paper Cast
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens
Daily Paper Cast
VeriGUI: Verifiable Long-Chain GUI Dataset
Daily Paper Cast
Efficient Agents: Building Effective Agents While Reducing Cost
Daily Paper Cast
SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experien...
Daily Paper Cast
Training Long-Context, Multi-Turn Software Engineering Agents with Reinforcement...
Daily Paper Cast
Enhancing Vision-Language Model Training with Reinforcement Learning in Syntheti...
Daily Paper Cast
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
Daily Paper Cast
Qwen-Image Technical Report
Daily Paper Cast
SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and...
Daily Paper Cast
CellForge: Agentic Design of Virtual Cell Models
Daily Paper Cast
Beyond the Trade-off: Self-Supervised Reinforcement Learning for Reasoning Model...
Daily Paper Cast
Llama-3.1-FoundationAI-SecurityLLM-8B-Instruct Technical Report
Daily Paper Cast
Beyond Fixed: Variable-Length Denoising for Diffusion Large Language Models
Daily Paper Cast
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation...
Daily Paper Cast