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-...
Brands advertising on this show
See all 1 brand with the ad reads →Detected in the episodes we have transcribed. How we detect ad reads →
Notable Guests
Episodes (2366)
AgentGarten: Code Worlds for Evolving Agents
Daily Paper Cast
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Env...
Daily Paper Cast
TokenRouter: Efficient Serving System for Token-Level LLM Routing
Daily Paper Cast
From Traces to Agentic Worlds: Agentic Language World Models for Interactive Env...
Daily Paper Cast
SuperNav: An Agentic Navigation System for Any Task in Any Scene
Daily Paper Cast
MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement
Daily Paper Cast
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Ta...
Daily Paper Cast
Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction
Daily Paper Cast
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
Daily Paper Cast
Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence...
Daily Paper Cast
STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantizati...
Daily Paper Cast
Long-WAM: Scaling the Context of World-Action Models
Daily Paper Cast
nanoMuse: An Open-Source Personal Agent for Every Device You Own
Daily Paper Cast
Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harnes...
Daily Paper Cast
Questioning the Questions: Sustaining Self-Evolution in Reasoning Models
Daily Paper Cast
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Daily Paper Cast
GRACE: Generation-aware latent compression for efficient video generation
Daily Paper Cast
VepAgent: Bridging Causal-Transition via Tool-Augmented Reinforcement Learning f...
Daily Paper Cast
SGF+: Decoupling Gradient Flows for Autoregressive Video Generation
Daily Paper Cast
UniWAM: Unified World-Action Model
Daily Paper Cast
Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Su...
Daily Paper Cast
DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation
Daily Paper Cast
TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning...
Daily Paper Cast
EVISKILL: Grounding Skill Evolution in Replayable Evidence
Daily Paper Cast
From Evidence to Action: How Tool-Using Agents Fail
Daily Paper Cast
AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents
Daily Paper Cast
Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generati...
Daily Paper Cast
ALoDLM: Adaptively Looped Diffusion Language Models
Daily Paper Cast
Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video...
Daily Paper Cast
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
Daily Paper Cast
Hierarchical Continuous Diffusion Language Models
Daily Paper Cast
Agent Priors-guided Policy Learning
Daily Paper Cast
World Observer: Joint Actor-Observer Generation for Persistent World Modeling
Daily Paper Cast
ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
Daily Paper Cast
Sharpening Tax in Post-Training
Daily Paper Cast
A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robus...
Daily Paper Cast
ROWBench: Do Video Models Render What the Program Specifies?
Daily Paper Cast
AutoGUIWorld: Image Generators as Visual World Models for GUI Agent
Daily Paper Cast
The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Represen...
Daily Paper Cast
UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model S...
Daily Paper Cast
False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search A...
Daily Paper Cast
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Daily Paper Cast
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents
Daily Paper Cast
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Daily Paper Cast
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
Daily Paper Cast
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
Daily Paper Cast
More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision Mo...
Daily Paper Cast
Raven: The Harness of Harnesses for Composable Agentic Intelligence
Daily Paper Cast
MaLiang-Harness: A Programmable Path to Image and Video Generation
Daily Paper Cast
PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation
Daily Paper Cast