Every morning, new papers
Today’s AI research, as podcasts you can play.
The day’s most-discussed papers become two-minute podcast episodes. The ones worth it get a deep dive. Then each one is a quest: guess the result, make the authors’ choices, and win the viva.
- papers
- 2,340
- papers
- quests
- 1,139
- quests
- deep dives
- 173
- deep dives
- days of research
- 50
- days of research
Listen
A short Brief for each day’s papers from the Hugging Face Daily Papers feed: what it does, how, and what it found, in about two minutes. Download a whole day for the commute.
Play the paper
Paper Quests teach a paper in seven chapters: the problem, the key idea, the authors’ choices, the method, the results, then a viva graded on your own words.
Keep it
Every term you meet joins your codex. Card games and quizzes bring them back just before you’d forget them.
The latest papers · Wednesday, November 11
All 2,340 papers ›- Few-Step Streaming Video Generation via Condition Shifting Tsinghua University, Shengshu Technology, Westlake University · ▲ 78
- Tree-Ising: Repairing Language Models with Bit-Level Ising Edits QDeep, ITMO University · ▲ 78
- World In-Context Learning for Agentic Robot Manipulation Huazhong University of Science and Technology, ArcheOne AI · ▲ 66
- Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents KAIST, DeepAuto AI · ▲ 56
- dNaViT: Discrete Codes are General-Purpose Visual Representations Meituan's LongCat Team · ▲ 33
- MMDM: Measuring Massive Multitask Decision Making Chinese University of Hong Kong, Hong Kong University of Science and Technology, Lightspeed · ▲ 26
- DexForesight: Grounding Dexterous Policies with Implicit Spatial Foresight Sharpa Robotics, Shanghai Jiao Tong University, Chinese University of Hong Kong · ▲ 24
- Embodied First Exam Northwestern University, Carnegie Mellon University, University of California, Berkeley · ▲ 24
Start with today’s papers
Free, with Google or an email address. On the web, or as an Android app.
Join free