Zhicheng YANG

yangzhch6

·

https://yangzhch6.github.io/

yangzhch6

AI & ML interests

reasoning with LLMs

Recent Activity

upvoted a paper 5 days ago

VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation

published a dataset 5 months ago

yangzhch6/mathnet-dsv4pro-proof

upvoted a paper 5 months ago

Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It

View all activity

Organizations

None yet

yangzhch6 's models 45

yangzhch6/Qwen2.5-Math-1.5B-L-openr1-nothink-3k-f3-step100

2B • Updated Sep 7, 2025 • 1

yangzhch6/Qwen2.5-Math-1.5B-L

Text Generation • 2B • Updated Sep 6, 2025 • 17

yangzhch6/Qwen2.5-7B-L-openr1-f3-ckpt500

8B • Updated Sep 4, 2025 • 1

yangzhch6/Qwen2.5-1.5B-L-openr1-f3-ckpt500

2B • Updated Sep 4, 2025 • 1

yangzhch6/DARS-Llama-ET-Breadth

8B • Updated Sep 3, 2025 • 3

yangzhch6/DARS-7B-HW-Breadth

8B • Updated Sep 1, 2025 • 5

yangzhch6/DARS-1.5B-HW-Breadth

2B • Updated Sep 1, 2025 • 1

yangzhch6/DARS-7B-HW

8B • Updated Aug 31, 2025 • 7

yangzhch6/DARS-7B-ET

8B • Updated Aug 31, 2025 • 6

yangzhch6/DARS-1.5B-HW

2B • Updated Aug 31, 2025 • 3

yangzhch6/DARS-1.5B-ET

2B • Updated Aug 31, 2025 • 5

yangzhch6/dars-env

Updated Aug 31, 2025

yangzhch6/cuda-12.4

Updated Aug 30, 2025

yangzhch6/DARS-1.5B-ET-Breadth

2B • Updated Aug 21, 2025 • 2

yangzhch6/DARS-7B-ET-Breadth

8B • Updated Aug 21, 2025 • 3