arxiv:2505.20139
Yiming Jia
jymmmmm
AI & ML interests
None yet
Recent Activity
liked
a model
2 days ago
Nanbeige/Nanbeige4.1-3B
upvoted
a
paper
10 days ago
SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
upvoted
a
paper
10 days ago
SWE-World: Building Software Engineering Agents in Docker-Free Environments
Organizations
models
14
jymmmmm/vlm-fixed-onpolicy-step600
8B
•
Updated
jymmmmm/vlm-fixed-onpolicy-step400
8B
•
Updated
•
1
jymmmmm/vlm-fixed-onpolicy-step200
8B
•
Updated
jymmmmm/qwen2_5vl_tgrpo_f32_s300
8B
•
Updated
jymmmmm/qwen2_5vl_tgrpo_f32_s900
8B
•
Updated
jymmmmm/qwen2_5vl_tgrpo_f32_s1561
8B
•
Updated
jymmmmm/qwen2_5vl_grpo_f64_s300
8B
•
Updated
jymmmmm/qwen2_5vl_grpo_f64_s900
8B
•
Updated
jymmmmm/qwen2_5vl_grpo_f64_s1500
8B
•
Updated
jymmmmm/qwen2_5vl_grpo_1500
Updated