Shixuan Liu

Shixuan Liu on Hugging Face Daily Papers: 9 papers, 5 in the top 3 of their day, 1,156 upvotes.

1. HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning 106 upvotes, #1 of 2026-03-23
2. Qwen3-VL Technical Report 120 upvotes, #1 of 2025-12-04
3. Soft Adaptive Policy Optimization 33 upvotes, #6 of 2025-11-26
4. Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window 9 upvotes, #29 of 2025-10-10
5. GRACE: Generative Representation Learning via Contrastive Policy Optimization 9 upvotes, #17 of 2025-10-08
6. Group Sequence Policy Optimization 257 upvotes, #1 of 2025-07-25
7. Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning 144 upvotes, #1 of 2025-06-03
8. Qwen3 Technical Report 152 upvotes, #1 of 2025-05-19
9. TeleChat Technical Report 8 upvotes, #11 of 2024-01-09

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.