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)
EnterpriseOps-Gym: Environments and Evaluations for Stateful Agentic Planning an...
Daily Paper Cast
Grounding World Simulation Models in a Real-World Metropolis
Daily Paper Cast
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Int...
Daily Paper Cast
Attention Residuals
Daily Paper Cast
Mixture-of-Depths Attention
Daily Paper Cast
Effective Distillation to Hybrid xLSTM Architectures
Daily Paper Cast
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations...
Daily Paper Cast
ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer
Daily Paper Cast
LMEB: Long-horizon Memory Embedding Benchmark
Daily Paper Cast
Can Vision-Language Models Solve the Shell Game?
Daily Paper Cast
Cheers: Decoupling Patch Details from Semantic Representations Enables Unified M...
Daily Paper Cast
daVinci-Env: Open SWE Environment Synthesis at Scale
Daily Paper Cast
Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Doc...
Daily Paper Cast
OpenClaw-RL: Train Any Agent Simply by Talking
Daily Paper Cast
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
Daily Paper Cast
MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agent...
Daily Paper Cast
LLM2Vec-Gen: Generative Embeddings from Large Language Models
Daily Paper Cast
Urban Socio-Semantic Segmentation with Vision-Language Reasoning
Daily Paper Cast
STEP3-VL-10B Technical Report
Daily Paper Cast
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
Daily Paper Cast
Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning
Daily Paper Cast
Controlled Self-Evolution for Algorithmic Code Optimization
Daily Paper Cast
DeepResearchEval: An Automated Framework for Deep Research Task Construction and...
Daily Paper Cast
MAXS: Meta-Adaptive Exploration with LLM Agents
Daily Paper Cast
Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning
Daily Paper Cast
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Laten...
Daily Paper Cast
SkinFlow: Efficient Information Transmission for Open Dermatological Diagnosis v...
Daily Paper Cast
OpenDecoder: Open Large Language Model Decoding to Incorporate Document Quality...
Daily Paper Cast
OpenVoxel: Training-Free Grouping and Captioning Voxels for Open-Vocabulary 3D S...
Daily Paper Cast
MemGovern: Enhancing Code Agents through Learning from Governed Human Experience...
Daily Paper Cast
Solar Open Technical Report
Daily Paper Cast
KnowMe-Bench: Benchmarking Person Understanding for Lifelong Digital Companions
Daily Paper Cast
User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale
Daily Paper Cast
ShowUI-$π$: Flow-based Generative Models as GUI Dexterous Hands
Daily Paper Cast
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking
Daily Paper Cast
MemoBrain: Executive Memory as an Agentic Brain for Reasoning
Daily Paper Cast
Motion Attribution for Video Generation
Daily Paper Cast
3AM: Segment Anything with Geometric Consistency in Videos
Daily Paper Cast
BabyVision: Visual Reasoning Beyond Language
Daily Paper Cast
PaCoRe: Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning
Daily Paper Cast
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Daily Paper Cast
X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions...
Daily Paper Cast
GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thought...
Daily Paper Cast
Lost in the Noise: How Reasoning Models Fail with Contextual Distractors
Daily Paper Cast
OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agent
Daily Paper Cast
Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization
Daily Paper Cast
MMFormalizer: Multimodal Autoformalization in the Wild
Daily Paper Cast
CaricatureGS: Exaggerating 3D Gaussian Splatting Faces With Gaussian Curvature
Daily Paper Cast
The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Though...
Daily Paper Cast
Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with...
Daily Paper Cast