Tsinghua-LeapLab

Tsinghua-LeapLab on Hugging Face Daily Papers: 6 papers, 0 in the top 3 of their day, 0 paper of the day.

1. What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling 136 upvotes, #8 of 2026-09-30
2. Linearizing Vision Transformer with Test-Time Training 20 upvotes, #21 of 2026-06-01
3. InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation 34 upvotes, #10 of 2026-05-18
4. Linear-Time Global Visual Modeling without Explicit Attention 5 upvotes, #15 of 2026-05-05
5. Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models 24 upvotes, #6 of 2026-04-29
6. The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models 68 upvotes, #4 of 2026-01-23

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.