arxiv:2604.05117
Yuxuan Zhang PRO
Reacherx
AI & ML interests
None yet
Recent Activity
authored a paper about 23 hours ago
Watch Before You Answer: Learning from Visually Grounded Post-Training upvoted a paper 1 day ago
Watch Before You Answer: Learning from Visually Grounded Post-Training published a dataset about 1 month ago
Reacherx/Video-R1-soft-filterOrganizations
models 17
Reacherx/Qwen2.5-VL-7B-COT-SFT-LoRA-Filtered1
Updated
Reacherx/Qwen2.5-VL-7B-COT-SFT-Filtered1
Updated
Reacherx/Qwen2.5-VL-7B-COT-SFT-ALL-DATA
Updated
Reacherx/Qwen2.5-VL-7B-Instruct-TW-GRPO-vid-filter-400
Updated
Reacherx/Qwen2.5-VL-7B-Instruct-TW-GRPO-vid-filter
Updated
Reacherx/Qwen2.5-VL-7B-Instruct-v5-reverse
Updated
Reacherx/Qwen2.5-VL-7B-Instruct-v5
8B • Updated • 1
Reacherx/Qwen2.5-VL-7B-Instruct-v1-clip-higher
8B • Updated • 6
Reacherx/Qwen2.5-VL-7B-Instruct-v1-reverse
8B • Updated • 3
Reacherx/Qwen2.5-VL-7B-Instruct-T-Only-GRPO
8B • Updated • 1
datasets 14
Reacherx/Video-R1-soft-filter
Updated • 12
Reacherx/EditReward-Data-100
Updated • 7
Reacherx/EditReward-Data-2K
Preview • Updated • 10
Reacherx/MMVU-Star-New
Viewer • Updated • 598 • 5
Reacherx/VideoMME-Star-New
Viewer • Updated • 762 • 7
Reacherx/MMVU-Star
Viewer • Updated • 1k • 6
Reacherx/VideoMathQA-Star
Viewer • Updated • 840 • 11
Reacherx/VideoMME-Star
Viewer • Updated • 5.4k • 19
Reacherx/VideoMMMU-Star
Viewer • Updated • 900 • 12
Reacherx/V1-Matrix-Res
Viewer • Updated • 5.4k • 56