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)
Seedance 2.0: Advancing Video Generation for World Complexity
Daily Paper Cast
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Age...
Daily Paper Cast
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Tes...
Daily Paper Cast
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Envir...
Daily Paper Cast
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language En...
Daily Paper Cast
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding...
Daily Paper Cast
From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
Daily Paper Cast
Exploration and Exploitation Errors Are Measurable for Language Model Agents
Daily Paper Cast
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
Daily Paper Cast
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mecha...
Daily Paper Cast
Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization
Daily Paper Cast
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
Daily Paper Cast
Toward Autonomous Long-Horizon Engineering for ML Research
Daily Paper Cast
BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference...
Daily Paper Cast
QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Gener...
Daily Paper Cast
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
Daily Paper Cast
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Gene...
Daily Paper Cast
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mit...
Daily Paper Cast
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation
Daily Paper Cast
Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Bas...
Daily Paper Cast
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Un...
Daily Paper Cast
CocoaBench: Evaluating Unified Digital Agents in the Wild
Daily Paper Cast
CodeTracer: Towards Traceable Agent States
Daily Paper Cast
WildDet3D: Scaling Promptable 3D Detection in the Wild
Daily Paper Cast
FORGE: Fine-grained Multimodal Evaluation for Manufacturing Scenarios
Daily Paper Cast
EXAONE 4.5 Technical Report
Daily Paper Cast
RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details
Daily Paper Cast
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horiz...
Daily Paper Cast
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimizati...
Daily Paper Cast
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Daily Paper Cast
RAGEN-2: Reasoning Collapse in Agentic RL
Daily Paper Cast
MARS: Enabling Autoregressive Models Multi-Token Generation
Daily Paper Cast
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
Daily Paper Cast
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Under...
Daily Paper Cast
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
Daily Paper Cast
Learning to Retrieve from Agent Trajectories
Daily Paper Cast
ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation
Daily Paper Cast
GBQA: A Game Benchmark for Evaluating LLMs as Quality Assurance Engineers
Daily Paper Cast
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning
Daily Paper Cast
ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refi...
Daily Paper Cast
Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervis...
Daily Paper Cast
MegaTrain: Full Precision Training of 100B+ Parameter Large Language Models on a...
Daily Paper Cast
Watch Before You Answer: Learning from Visually Grounded Post-Training
Daily Paper Cast
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
Daily Paper Cast
MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale
Daily Paper Cast
LIBERO-Para: A Diagnostic Benchmark and Metrics for Paraphrase Robustness in VLA...
Daily Paper Cast
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Daily Paper Cast
Adam's Law: Textual Frequency Law on Large Language Models
Daily Paper Cast
AURA: Always-On Understanding and Real-Time Assistance via Video Streams
Daily Paper Cast
ClawArena: Benchmarking AI Agents in Evolving Information Environments
Daily Paper Cast