Xingtai Lv

Xingtai Lv on Hugging Face Daily Papers: 8 papers, 4 in the top 3 of their day, 465 upvotes.

1. Post-Trained MoE Can Skip Half Experts via Self-Distillation 30 upvotes, #10 of 2026-05-19
2. How Far Can Unsupervised RLVR Scale LLM Training? 52 upvotes, #4 of 2026-03-10
3. FlowRL: Matching Reward Distributions for LLM Reasoning 100 upvotes, #2 of 2025-09-19
4. Towards a Unified View of Large Language Model Post-Training 67 upvotes, #3 of 2025-09-05
5. Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models 26 upvotes, #6 of 2025-03-17
6. Process Reinforcement through Implicit Rewards 53 upvotes, #3 of 2025-02-04
7. Fourier Position Embedding: Enhancing Attention's Periodic Extension for Length Generalization 35 upvotes, #1 of 2024-12-25
8. How to Synthesize Text Data without Model Collapse? 46 upvotes, #4 of 2024-12-20

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.