PKU Machine Learning Group's picture

PKU Machine Learning Group

PKU-ML

·

AI & ML interests

None yet

Recent Activity

published a dataset about 7 hours ago

published a dataset about 7 hours ago

PKU-ML/RealErdos

published a model about 7 hours ago

PKU-ML/GRASP-4B

View all activity

Organizations

published 2 datasets about 7 hours ago

PKU-ML/GRASP

Viewer • Updated 25 days ago • 12.4k

PKU-ML/RealErdos

Viewer • Updated 25 days ago • 1.13k

published a model about 7 hours ago

PKU-ML/GRASP-4B

4B • Updated about 9 hours ago • 12

updated a model about 11 hours ago

PKU-ML/GRASP-4B

4B • Updated about 9 hours ago • 12

updated a model about 12 hours ago

PKU-ML/GRASP-base-4B

4B • Updated about 11 hours ago • 1

updated a collection 25 days ago

GRASP

Models and datasets for the paper "GRASP: Graph Reasoning via Agentic Solving and Probing of LLMs". • 4 items • Updated 25 days ago • 1

updated a dataset 25 days ago

PKU-ML/GRASP

Viewer • Updated 25 days ago • 12.4k

upvoted a collection 25 days ago

GRASP

Models and datasets for the paper "GRASP: Graph Reasoning via Agentic Solving and Probing of LLMs". • 4 items • Updated 25 days ago • 1

updated a collection 25 days ago

GRASP

Models and datasets for the paper "GRASP: Graph Reasoning via Agentic Solving and Probing of LLMs". • 4 items • Updated 25 days ago • 1

updated a dataset 25 days ago

PKU-ML/RealErdos

Viewer • Updated 25 days ago • 1.13k

published a model 25 days ago

PKU-ML/GRASP-base-4B

4B • Updated about 11 hours ago • 1

liked a dataset 4 months ago

PKU-ML/Erdos

Viewer • Updated Jun 1, 2025 • 104k • 360 • 2

updated a dataset 5 months ago

PKU-ML/ImageNet-Subset

Viewer • Updated Dec 24, 2025 • 110k • 21

updated 4 models 5 months ago

PKU-ML/SSL4RL-MMBench-Jigsaw-3B

Image-Text-to-Text • 4B • Updated Dec 23, 2025 • 2

PKU-ML/SSL4RL-MMBench-Contrastive-3B

Image-Text-to-Text • 4B • Updated Dec 23, 2025 • 5

PKU-ML/SSL4RL-MMBench-Rotation-3B

Image-Text-to-Text • 4B • Updated Dec 23, 2025 • 4

PKU-ML/SSL4RL-MMBench-Position-3B

Image-Text-to-Text • 4B • Updated Dec 23, 2025 • 5 • 1

updated a collection 5 months ago

SSL4RL

Datasets and models in the paper SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning • 5 items • Updated Dec 23, 2025