arxiv:2509.22824
Dongfu Jiang
DongfuJiang
AI & ML interests
Large Language Model, Modality Reasoning and their evaluation
Recent Activity
liked
a model
1 day ago
nvidia/audio-flamingo-3-hf
upvoted
an
article
2 days ago
Why Did MiniMax M2 End Up as a Full Attention Model?
upvoted
an
article
2 days ago
Aligning to What? Rethinking Agent Generalization in MiniMax M2
Organizations
models
42
DongfuJiang/vs2_qwen2_5vl_sft_17k_1e-5
Image-to-Text
•
8B
•
Updated
•
4
DongfuJiang/vs2_qwen2_5vl_sft_17k
Image-to-Text
•
8B
•
Updated
•
7
DongfuJiang/math_ct_adapt_qwen2.5_1.5B
2B
•
Updated
•
1
DongfuJiang/math_ct_qwen2.5_1.5B
2B
•
Updated
DongfuJiang/Qwen2-VL-VAE-7B-Instruct
Image-Text-to-Text
•
8B
•
Updated
•
3
DongfuJiang/Qwen2-VL-VAE-7B-Instruct-mochi-vae
Text Generation
•
8B
•
Updated
•
1
DongfuJiang/qwen2_chunking_mlp_freeze_uniform_with_shared_start_and_end_2_12_pt
Text Generation
•
0.7B
•
Updated
•
3
DongfuJiang/qwen2_chunking_mlp_freeze_uniform_with_shared_start_and_end_2_12_sft
Text Generation
•
0.7B
•
Updated
DongfuJiang/qwen2_chunking_mlp_freeze_uniform_with_shared_start_and_end_2_6_pt
Text Generation
•
0.6B
•
Updated
•
5
DongfuJiang/qwen2_chunking_mlp_freeze_uniform_with_shared_start_and_end_2_6_sft
Text Generation
•
0.6B
•
Updated
datasets
17
DongfuJiang/aime_2025
Viewer
•
Updated
•
30
•
781
DongfuJiang/math_35
Viewer
•
Updated
•
8.52k
•
16
DongfuJiang/livecodebench
Viewer
•
Updated
•
454
•
844
DongfuJiang/hle_text_only
Viewer
•
Updated
•
2.16k
•
2.72k
DongfuJiang/LVBench
Viewer
•
Updated
•
1.55k
•
209
DongfuJiang/Big-Math-RL-Verified-CT
Viewer
•
Updated
•
17.8k
•
15
DongfuJiang/PRM_SFT
Viewer
•
Updated
•
4.01M
•
4
DongfuJiang/zeroeval
Viewer
•
Updated
•
13.5k
•
13
DongfuJiang/PRM_eval
Viewer
•
Updated
•
9.54k
•
5
DongfuJiang/eval
Viewer
•
Updated
•
6k
•
4