TaolinZhang

iridescentttt's activity

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

upvoted 2 papers 8 days ago

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

Paper • 2508.05629 • Published 8 days ago • 144

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

Paper • 2508.01191 • Published 14 days ago • 205

upvoted a paper 10 days ago

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

Paper • 2508.03686 • Published 10 days ago • 32

upvoted a paper 25 days ago

The Invisible Leash: Why RLVR May Not Escape Its Origin

Paper • 2507.14843 • Published 27 days ago • 84

New activity in opencompass/CompassJudger-2-7B-Instruct 25 days ago

Update pipeline tag to `text-ranking` and fix quickstart code

#3 opened 28 days ago by

nielsr

New activity in opencompass/CompassJudger-2-32B-Instruct 25 days ago

Update pipeline tag to text-ranking and add descriptive tags

#3 opened 28 days ago by

nielsr

New activity in opencompass/CompassJudger-2-32B-Instruct 29 days ago

Add pipeline_tag, library_name, and paper link to metadata

#2 opened about 1 month ago by

nielsr

New activity in opencompass/CompassJudger-2-7B-Instruct 29 days ago

Improve model card: Add pipeline tag, library name, and relevant tags; update paper link in content

#2 opened about 1 month ago by

nielsr

upvoted a paper about 1 month ago

CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards

Paper • 2507.09104 • Published Jul 12 • 17

New activity in opencompass/CompassJudger-2-7B-Instruct about 1 month ago

Update README.md

#1 opened about 1 month ago by

iridescentttt

New activity in opencompass/CompassJudger-2-32B-Instruct about 1 month ago

Update README.md

#1 opened about 1 month ago by

iridescentttt

upvoted a paper about 1 month ago

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs

Paper • 2507.07996 • Published Jul 10 • 32

authored 2 papers about 1 month ago

Coding Triangle: How Does Large Language Model Understand Code?

Paper • 2507.06138 • Published Jul 8 • 20

Rethinking Verification for LLM Code Generation: From Generation to Testing

Paper • 2507.06920 • Published Jul 9 • 28

upvoted 2 papers about 1 month ago

Rethinking Verification for LLM Code Generation: From Generation to Testing

Paper • 2507.06920 • Published Jul 9 • 28

Coding Triangle: How Does Large Language Model Understand Code?

Paper • 2507.06138 • Published Jul 8 • 20

upvoted a paper 3 months ago

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective

Paper • 2505.19815 • Published May 26 • 37

upvoted a paper 4 months ago

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published Apr 14 • 280

upvoted a collection 5 months ago

Tulu 3 Datasets

Collection

All datasets released with Tulu 3 -- state of the art open post-training recipes. • 33 items • Updated Apr 30 • 88

upvoted a paper 6 months ago

OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference

Paper • 2502.18411 • Published Feb 25 • 75