Mingzhe Li

Mubuky's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 1 day ago

STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules

Paper • 2601.03537 • Published Jan 7

liked 2 models 1 day ago

OpenMOSS-Team/SciThinker-4B

Text Generation • 4B • Updated 1 day ago • 338 • 5

OpenMOSS-Team/SciThinker-30B

Text Generation • 31B • Updated 1 day ago • 375 • 8

authored a paper 1 day ago

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published 3 days ago • 230

upvoted a paper 2 days ago

AI Can Learn Scientific Taste

Paper • 2603.14473 • Published 3 days ago • 230

liked 2 models 3 days ago

OpenMOSS-Team/SciJudge-30B

Text Generation • 31B • Updated 1 day ago • 21 • 6

OpenMOSS-Team/SciJudge-4B

Text Generation • 4B • Updated 1 day ago • 22 • 4

liked a dataset 3 days ago

OpenMOSS-Team/SciJudgeBench

Preview • Updated 1 day ago • 9 • 4

New activity in OpenMOSS-Team/SciJudge-30B 3 days ago

upload-model-v1

#1 opened 3 days ago by

Mubuky

New activity in OpenMOSS-Team/SciJudge-4B 3 days ago

upload-model-v1

#1 opened 3 days ago by

Mubuky

New activity in OpenMOSS-Team/SciJudgeBench 3 days ago

upload-dataset-v1

#1 opened 3 days ago by

Mubuky

liked 2 models about 1 month ago

OpenMOSS-Team/MOVA-360p

Image-to-Video • Updated Feb 15 • 37.6k • 210

OpenMOSS-Team/MOSS-TTS

Text-to-Speech • 8B • Updated Feb 13 • 122k • 344

authored a paper about 2 months ago

Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation

Paper • 2507.23440 • Published Jul 31, 2025 • 1

upvoted a paper about 2 months ago

Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation

Paper • 2507.23440 • Published Jul 31, 2025 • 1

upvoted 2 papers 2 months ago

ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking

Paper • 2601.06487 • Published Jan 10 • 54

MOSS Transcribe Diarize: Accurate Transcription with Speaker Diarization

Paper • 2601.01554 • Published Jan 4 • 58

upvoted 3 papers 4 months ago

DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning

Paper • 2511.22570 • Published Nov 27, 2025 • 92

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published Dec 2, 2025 • 262

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Paper • 2512.01374 • Published Dec 1, 2025 • 106