li sheng

bambisheng's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 13 days ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published 14 days ago • 87

upvoted a paper 29 days ago

Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models

Paper • 2511.08577 • Published Nov 11, 2025 • 110

updated a dataset about 1 month ago

dynn-datasets/Evaluation

Preview • Updated Mar 24 • 61

published a dataset about 1 month ago

dynn-datasets/Evaluation

Preview • Updated Mar 24 • 61

upvoted a paper about 2 months ago

How Far Can Unsupervised RLVR Scale LLM Training?

Paper • 2603.08660 • Published Mar 9 • 59

upvoted a paper 6 months ago

Scaling Latent Reasoning via Looped Language Models

Paper • 2510.25741 • Published Oct 29, 2025 • 229

upvoted 2 papers 8 months ago

rStar2-Agent: Agentic Reasoning Technical Report

Paper • 2508.20722 • Published Aug 28, 2025 • 118

SSRL: Self-Search Reinforcement Learning

Paper • 2508.10874 • Published Aug 14, 2025 • 97

upvoted a paper 11 months ago

The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Paper • 2505.22617 • Published May 28, 2025 • 132

authored a paper about 1 year ago

TTRL: Test-Time Reinforcement Learning

Paper • 2504.16084 • Published Apr 22, 2025 • 122

upvoted a paper about 1 year ago

TTRL: Test-Time Reinforcement Learning

Paper • 2504.16084 • Published Apr 22, 2025 • 122

published 3 models about 1 year ago

bambisheng/UltraIF-8B-UltraComposer

Text Generation • 8B • Updated Apr 3, 2025 • 11 • 1

bambisheng/UltraIF-8B-DPO

Text Generation • 8B • Updated Apr 3, 2025 • 6 • 3

bambisheng/UltraIF-8B-SFT

Text Generation • 8B • Updated Apr 3, 2025 • 130 • 2

updated a model about 1 year ago

bambisheng/UltraIF-8B-DPO

Text Generation • 8B • Updated Apr 3, 2025 • 6 • 3

updated a collection about 1 year ago

UltraIF series

Collection

Open-Sourced model and data for ULTRAIF: Advancing Instruction Following from the Wild. • 6 items • Updated Apr 3, 2025 • 3