JackyLu

Great-Luso

AI & ML interests

LLM, AI for science, Generative Ai.

Recent Activity

authored a paper 6 days ago

Grad2Reward: From Sparse Judgment to Dense Rewards for Improving Open-Ended LLM Reasoning

authored a paper 6 days ago

Large Language Models Explore by Latent Distilling

authored a paper 6 days ago

Harvesting SWE Benchmarks from Wild Vibe Coding Sessions

View all activity

Organizations

None yet

authored 3 papers 6 days ago

Grad2Reward: From Sparse Judgment to Dense Rewards for Improving Open-Ended LLM Reasoning

Paper • 2602.01791 • Published Feb 2 • 2

Large Language Models Explore by Latent Distilling

Paper • 2604.24927 • Published Apr 27 • 73

Harvesting SWE Benchmarks from Wild Vibe Coding Sessions

Paper • 2611.02440 • Published 9 days ago

upvoted a paper 7 months ago

Large Language Models Explore by Latent Distilling

Paper • 2604.24927 • Published Apr 27 • 73

New activity in Qwen/Qwen2.5-Math-PRM-7B 12 months ago

Fix the issues with latest transformers, add previously removed function to compute usable past KV length for cache compatibility.

#13 opened 12 months ago by