Yexin Liu

Yexin Liu on Hugging Face Daily Papers: 10 papers, 3 in the top 3 of their day, 293 upvotes.

1. Learning Latent Proxies for Controllable Single-Image Relighting 8 upvotes, #26 of 2026-03-17
2. OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation 17 upvotes, #13 of 2025-12-09
3. EditThinker: Unlocking Iterative Reasoning for Any Image Editor 36 upvotes, #2 of 2025-12-08
4. Architecture Decoupling Is Not All You Need For Unified Multimodal Model 28 upvotes, #8 of 2025-12-01
5. TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis 17 upvotes, #8 of 2025-09-01
6. OmniGen2: Exploration to Advanced Multimodal Generation 68 upvotes, #2 of 2025-06-24
7. When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding 4 upvotes, #20 of 2025-06-09
8. Temporal Regularization Makes Your Video Generator Stronger 21 upvotes, #6 of 2025-03-20
9. LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization 18 upvotes, #13 of 2025-03-12
10. VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation 55 upvotes, #1 of 2024-12-04

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.