Xinyin Ma

Xinyin Ma on Hugging Face Daily Papers: 8 papers, 0 in the top 3 of their day, 172 upvotes.

1. In-Video Instructions: Visual Signals as Generative Control 28 upvotes, #7 of 2025-11-25
2. Thinkless: LLM Learns When to Think 46 upvotes, #5 of 2025-05-20
3. Introducing Visual Perception Token into Multimodal Large Language Model 14 upvotes, #9 of 2025-02-26
4. CoT-Valve: Length-Compressible Chain-of-Thought Tuning 12 upvotes, #16 of 2025-02-14
5. TinyFusion: Diffusion Transformers Learned Shallow 13 upvotes, #12 of 2024-12-03
6. Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient 11 upvotes, #11 of 2024-11-28
7. AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising 10 upvotes, #10 of 2024-06-12
8. DeepCache: Accelerating Diffusion Models for Free 23 upvotes, #4 of 2023-12-05

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.