zhanghengyuan

hengyuanya's activity

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

upvoted a collection 1 day ago

Checkpoint for Long CoT Degradation

Collection

Checkpoint for Long CoT Degradation • 53 items • Updated 1 day ago • 2

updated a dataset 23 days ago

hengyuanya/PerSyn_dataset

Viewer • Updated 23 days ago • 157k • 37

published a dataset 23 days ago

hengyuanya/PerSyn_dataset

Viewer • Updated 23 days ago • 157k • 37

upvoted a paper about 1 month ago

Who's Your Judge? On the Detectability of LLM-Generated Judgments

Paper • 2509.25154 • Published Sep 29 • 29

upvoted a paper 2 months ago

Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR

Paper • 2508.14029 • Published Aug 19 • 118

upvoted a paper 3 months ago

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

Paper • 2508.01191 • Published Aug 2 • 236

upvoted a paper 6 months ago

The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation

Paper • 2505.18759 • Published May 24 • 13

liked a dataset 6 months ago

Cloudriver/PhyX

Viewer • Updated Jul 31 • 17k • 1.51k • 22

upvoted a paper 6 months ago

PhyX: Does Your Model Have the "Wits" for Physical Reasoning?

Paper • 2505.15929 • Published May 21 • 49

upvoted a paper 8 months ago

Balancing Speciality and Versatility: a Coarse to Fine Framework for Supervised Fine-tuning Large Language Model

Paper • 2404.10306 • Published Apr 16, 2024 • 1

upvoted a paper 9 months ago

Preference Leakage: A Contamination Problem in LLM-as-a-judge

Paper • 2502.01534 • Published Feb 3 • 40

upvoted a paper 10 months ago

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

Paper • 2501.12895 • Published Jan 22 • 61