jymmmmm/vlm-fixed-onpolicy-step600
8B • Updated • 1
Yiming Jia
jymmmmm
AI & ML interests
None yet
Recent Activity
upvoted a paper about 5 hours ago
ClawBench: Can AI Agents Complete Everyday Online Tasks? new activity about 6 hours ago
Nanbeige/Nanbeige4.1-3B:LiveCodeBench-Pro Version authored a paper about 1 month ago
VideoEval-Pro: Robust and Realistic Long Video Understanding EvaluationOrganizations
jymmmmm/vlm-fixed-onpolicy-step400
8B • Updated • 2
jymmmmm/vlm-fixed-onpolicy-step200
8B • Updated
jymmmmm/qwen2_5vl_tgrpo_f32_s300
8B • Updated • 4
jymmmmm/qwen2_5vl_tgrpo_f32_s900
8B • Updated • 1
jymmmmm/qwen2_5vl_tgrpo_f32_s1561
8B • Updated • 18
jymmmmm/qwen2_5vl_grpo_f64_s300
8B • Updated • 2
jymmmmm/qwen2_5vl_grpo_f64_s900
8B • Updated • 1
jymmmmm/qwen2_5vl_grpo_f64_s1500
8B • Updated • 2
jymmmmm/qwen2_5vl_grpo_1500
Updated • 1
jymmmmm/training1_checkpoint-1100
8B • Updated
jymmmmm/training1_checkpoint-500
8B • Updated • 1
jymmmmm/visualwebinstruct_temp
Updated
jymmmmm/pot-r1-grpo-qwen2.5-7b-Instruct
Updated