TaolinZhang

iridescentttt's activity

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

upvoted a collection 3 days ago

Deepseek Papers

Collection

Deepseek papers collection • 25 items • Updated 2 days ago • 277

upvoted 2 papers 2 months ago

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Paper • 2508.18265 • Published Aug 25 • 201

Intern-S1: A Scientific Multimodal Foundation Model

Paper • 2508.15763 • Published Aug 21 • 254

upvoted 4 papers 3 months ago

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

Paper • 2508.05629 • Published Aug 7 • 177

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

Paper • 2508.01191 • Published Aug 2 • 236

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

Paper • 2508.03686 • Published Aug 5 • 36

The Invisible Leash: Why RLVR May Not Escape Its Origin

Paper • 2507.14843 • Published Jul 20 • 84

upvoted 4 papers 4 months ago

CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards

Paper • 2507.09104 • Published Jul 12 • 17

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

Paper • 2507.07996 • Published Jul 10 • 34

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 • 21

upvoted a paper 5 months ago

Deciphering Trajectory-Aided LLM Reasoning: An Optimization Perspective

Paper • 2505.19815 • Published May 26 • 36

upvoted a paper 7 months ago

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

Paper • 2504.10479 • Published Apr 14 • 297

upvoted a collection 8 months ago

Tulu 3 Datasets

Collection

All datasets released with Tulu 3 -- state of the art open post-training recipes. • 33 items • Updated Sep 18 • 94

upvoted a paper 8 months ago

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

Paper • 2502.18411 • Published Feb 25 • 74

upvoted 2 papers 9 months ago

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Paper • 2502.06781 • Published Feb 10 • 59

Condor: Enhance LLM Alignment with Knowledge-Driven Data Synthesis and Refinement

Paper • 2501.12273 • Published Jan 21 • 14