Zhao Haohan

zhhxte

1

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 19 days ago

Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning

updated a dataset 7 months ago

zhhxte/pathvqa_1-24

published a dataset 7 months ago

zhhxte/pathvqa_1-24

View all activity

Organizations

zhhxte 's datasets 13

zhhxte/pathvqa_1-24

Viewer • Updated Nov 25, 2025 • 5k • 9

zhhxte/pathvqa_lt16

Viewer • Updated Nov 25, 2025 • 5k • 14

zhhxte/pathvqa_gt3

Viewer • Updated Nov 25, 2025 • 5k • 18

zhhxte/mllm_cl_clevr

Viewer • Updated Nov 21, 2025 • 8.64k • 28

zhhxte/mllm_cl_clevr_v2

Updated Nov 21, 2025 • 5

zhhxte/mllm_cl_pathvqa

Viewer • Updated Nov 19, 2025 • 32.6k • 92

zhhxte/mllm_cl_mmlu_pro

Viewer • Updated Aug 28, 2025 • 12k • 10

zhhxte/mllm_cl_geometry3k

Viewer • Updated Aug 28, 2025 • 3k • 10

zhhxte/mllm_cl_mmmu

Viewer • Updated Aug 28, 2025 • 900 • 9

zhhxte/mllm_cl_gqa

Viewer • Updated Aug 28, 2025 • 92.6k • 227

zhhxte/mllm_cl_vizwiz

Viewer • Updated Aug 28, 2025 • 24.8k • 5

zhhxte/mllm_cl_textvqa

Viewer • Updated Aug 28, 2025 • 39.6k • 116

zhhxte/mllm_cl_scienceqa

Viewer • Updated Aug 28, 2025 • 8.24k • 30