arxiv:2509.22824
Dongfu Jiang
DongfuJiang
AI & ML interests
Large Language Model, Modality Reasoning and their evaluation
Recent Activity
liked a model about 18 hours ago
nvidia/Nemotron-Cascade-2-30B-A3B upvoted a paper about 18 hours ago
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation upvoted a paper 3 days ago
Attention ResidualsOrganizations
models 48
DongfuJiang/nano_v3_search_incorrect_only_347_steps
32B • Updated
DongfuJiang/nano_v3_search_correct_only_347_steps
32B • Updated
DongfuJiang/nano_v3_search_200_steps
32B • Updated • 1
DongfuJiang/nano_v3_search_347_steps
32B • Updated
DongfuJiang/nano_v3_search_incorrect_only_200_steps
32B • Updated
DongfuJiang/nano_v3_search_correct_only_200_steps
32B • Updated
DongfuJiang/vs2_qwen2_5vl_sft_17k_1e-5
Image-Text-to-Text • 8B • Updated
DongfuJiang/vs2_qwen2_5vl_sft_17k
Image-Text-to-Text • 8B • Updated
DongfuJiang/math_ct_adapt_qwen2.5_1.5B
2B • Updated • 1
DongfuJiang/math_ct_qwen2.5_1.5B
2B • Updated
datasets 18
DongfuJiang/GPT-OSS-Search
Viewer • Updated • 97.6k • 5 • 1
DongfuJiang/aime_2025
Viewer • Updated • 30 • 314
DongfuJiang/math_35
Viewer • Updated • 8.52k • 8
DongfuJiang/livecodebench
Viewer • Updated • 454 • 1.08k
DongfuJiang/hle_text_only
Viewer • Updated • 2.16k • 3.11k
DongfuJiang/LVBench
Viewer • Updated • 1.55k • 200
DongfuJiang/Big-Math-RL-Verified-CT
Viewer • Updated • 17.8k • 20
DongfuJiang/PRM_SFT
Viewer • Updated • 4.01M • 6
DongfuJiang/zeroeval
Viewer • Updated • 13.5k • 148
DongfuJiang/PRM_eval
Viewer • Updated • 9.54k • 7