Senqiao Yang

Senqiao Yang on Hugging Face Daily Papers: 8 papers, 4 in the top 3 of their day, 494 upvotes.

1. Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models 93 upvotes, #2 of 2026-08-31
2. Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model 35 upvotes, #5 of 2026-07-29
3. Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing 72 upvotes, #5 of 2026-07-22
4. Mitigating Object Hallucinations via Sentence-Level Early Intervention 6 upvotes, #9 of 2025-07-21
5. VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning 68 upvotes, #2 of 2025-07-18
6. Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition 43 upvotes, #4 of 2024-12-13
7. VisionZip: Longer is Better but Not Necessary in Vision Language Models 96 upvotes, #1 of 2024-12-06
8. Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs 37 upvotes, #2 of 2024-06-28

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.