Songyang Zhang

zsytony's activity

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

authored 3 papers 3 days ago

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

Paper • 2508.03686 • Published 19 days ago • 33

Dissecting Tool-Integrated Reasoning: An Empirical Study and Analysis

Paper • 2508.15754 • Published 3 days ago • 2

Intern-S1: A Scientific Multimodal Foundation Model

Paper • 2508.15763 • Published 3 days ago • 205

upvoted a paper 3 days ago

Intern-S1: A Scientific Multimodal Foundation Model

Paper • 2508.15763 • Published 3 days ago • 205

liked a model 5 days ago

deepseek-ai/DeepSeek-R1

Text Generation • 685B • Updated Mar 27 • 704k • • 12.6k

New activity in ScienceOne-AI/S1-Base-671B 11 days ago

Cannot be demployed with SGLang

#2 opened 11 days ago by

zsytony

upvoted a paper 12 days ago

Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

Paper • 2508.04664 • Published 18 days ago • 12

upvoted a paper 19 days ago

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

Paper • 2508.03686 • Published 19 days ago • 33

commented a paper 19 days ago

CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward

Paper • 2508.03686 • Published 19 days ago • 33 •

4

authored 2 papers about 1 month ago

CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards

Paper • 2507.09104 • Published Jul 12 • 17

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

Paper • 2507.10532 • Published Jul 14 • 85

upvoted a paper about 1 month ago

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

Paper • 2507.10532 • Published Jul 14 • 85

commented a paper about 1 month ago

Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination

Paper • 2507.10532 • Published Jul 14 • 85 •

3

upvoted a paper about 1 month ago

CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards

Paper • 2507.09104 • Published Jul 12 • 17

commented a paper about 1 month ago

CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards

Paper • 2507.09104 • Published Jul 12 • 17 •

1

upvoted a collection about 1 month ago

CompassVerifier

Collection

CompassVerifier: A Unified and Robust Verifier for Large Language Models • 5 items • Updated 18 days ago • 5

updated a model about 1 month ago

opencompass/CompassJudger-2-7B-Instruct

Text Ranking • 8B • Updated Jul 22 • 111 • 2

published a model about 1 month ago

opencompass/CompassJudger-2-7B-Instruct

Text Ranking • 8B • Updated Jul 22 • 111 • 2

updated a model about 2 months ago

opencompass/CompassJudger-2-32B-Instruct

Text Ranking • 33B • Updated Jul 22 • 68 • 2

published a model about 2 months ago

opencompass/CompassJudger-2-32B-Instruct

Text Ranking • 33B • Updated Jul 22 • 68 • 2