arxiv:2602.13367
Yiming Jia
jymmmmm
AI & ML interests
None yet
Recent Activity
liked a model 12 days ago
deepseek-ai/DeepSeek-V4-Pro new activity 21 days ago
Nanbeige/Nanbeige4.1-3B:LiveCodeBench-Pro Version upvoted a paper 26 days ago
ClawBench: Can AI Agents Complete Everyday Online Tasks?Organizations
models 14
jymmmmm/vlm-fixed-onpolicy-step600
8B • Updated • 1
jymmmmm/vlm-fixed-onpolicy-step400
8B • Updated • 6
jymmmmm/vlm-fixed-onpolicy-step200
8B • Updated • 3
jymmmmm/qwen2_5vl_tgrpo_f32_s300
8B • Updated • 9
jymmmmm/qwen2_5vl_tgrpo_f32_s900
8B • Updated • 3
jymmmmm/qwen2_5vl_tgrpo_f32_s1561
8B • Updated • 6
jymmmmm/qwen2_5vl_grpo_f64_s300
8B • Updated • 3
jymmmmm/qwen2_5vl_grpo_f64_s900
8B • Updated • 5
jymmmmm/qwen2_5vl_grpo_f64_s1500
8B • Updated • 1
jymmmmm/qwen2_5vl_grpo_1500
Updated • 3