Bowen LIU

AdAstraAbyssoque's activity

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

upvoted 2 papers 18 days ago

On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

Paper • 2306.13649 • Published Jun 23, 2023 • 25

Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

Paper • 2508.09138 • Published 25 days ago • 36

updated a collection 20 days ago

GraphMind

Collection

More in https://arxiv.org/pdf/2507.17168, Graph Reasoning Model series • 4 items • Updated 16 days ago

upvoted a paper 20 days ago

Improving LLMs' Generalized Reasoning Abilities by Graph Problems

Paper • 2507.17168 • Published Jul 23 • 1

updated a collection 21 days ago

GraphMind

Collection

More in https://arxiv.org/pdf/2507.17168, Graph Reasoning Model series • 4 items • Updated 16 days ago

updated 3 models 21 days ago

HKUST-DSAIL/GraphMind-LLAMA-3.1-8B

Text Generation • 8B • Updated 21 days ago • 12

HKUST-DSAIL/GraphMind-LLAMA-3-8B

Text Generation • 8B • Updated 21 days ago • 15

HKUST-DSAIL/GraphMind-Gemma2-2B

Text Generation • 3B • Updated 21 days ago • 15 • 1

published 3 models 21 days ago

HKUST-DSAIL/GraphMind-LLAMA-3-8B

Text Generation • 8B • Updated 21 days ago • 15

HKUST-DSAIL/GraphMind-LLAMA-3.1-8B

Text Generation • 8B • Updated 21 days ago • 12

HKUST-DSAIL/GraphMind-Gemma2-2B

Text Generation • 3B • Updated 21 days ago • 15 • 1

upvoted a paper 23 days ago

Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models

Paper • 2508.10751 • Published 23 days ago • 27

New activity in HKUST-DSAIL/Graph-R1-RFT-COT-30K 26 days ago

[bot] Conversion to Parquet

#1 opened about 1 month ago by

parquet-converter

liked 2 models about 1 month ago

openai/gpt-oss-120b

Text Generation • 120B • Updated 11 days ago • 2.87M • • 3.76k

HKUST-DSAIL/Graph-R1-7B

8B • Updated Aug 4 • 28 • 2

updated a dataset about 1 month ago

HKUST-DSAIL/Graph-R1-RFT-COT-30K

Viewer • Updated Aug 4 • 30k • 143 • 1

updated a collection about 1 month ago

Graph-R1

Collection

1.5B and 7B models training on 3 NP Graph Problems and achieved SOTA as GPT-4o and QwQ-32B • 3 items • Updated 21 days ago

liked a dataset about 1 month ago

HKUST-DSAIL/Graph-R1-RFT-COT-30K

Viewer • Updated Aug 4 • 30k • 143 • 1