Tianyu Chen PRO

C-Tianyu

1 1

https://tianyucodings.github.io/

AI & ML interests

LLM Post-training, Diffusion model, Image distillation

Recent Activity

published a dataset 7 days ago

C-Tianyu/S1-Arena

updated a dataset 7 days ago

C-Tianyu/S1-Arena

updated a dataset about 1 month ago

C-Tianyu/NanoJev-Data

View all activity

Organizations

Collections 2

Papers 1

arxiv:2509.13399

models 8

datasets 12

C-Tianyu/S1-Arena

Viewer • Updated 7 days ago • 49.6k • 296

C-Tianyu/NanoJev-Data

Preview • Updated Sep 20 • 2.08k • 11

C-Tianyu/circo

Viewer • Updated Apr 17 • 220 • 324

C-Tianyu/flash_attn

Updated Apr 8 • 6

C-Tianyu/EdiVal

Updated Mar 1 • 3.93k • 4

C-Tianyu/EditVal

Updated Sep 5, 2025 • 2

C-Tianyu/prompts

Preview • Updated Sep 1, 2025 • 1

C-Tianyu/dapo_sft

Updated Jun 15, 2025 • 16

C-Tianyu/sft

Viewer • Updated Jun 10, 2025 • 40.3k • 11

C-Tianyu/RSD_image

Preview • Updated May 13, 2025 • 5

View 12 datasets

Tianyu Chen PRO

AI & ML interests

Recent Activity

Organizations

Collections 2

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning

Papers 1

models 8

C-Tianyu/NanoJev

C-Tianyu/cifar10_sigma04

C-Tianyu/cifar10_sigma02

C-Tianyu/cifar10_sigma01

C-Tianyu/sid

C-Tianyu/judge

C-Tianyu/RAHF

C-Tianyu/dapo_sft

datasets 12

C-Tianyu/S1-Arena

C-Tianyu/NanoJev-Data

C-Tianyu/circo

C-Tianyu/flash_attn

C-Tianyu/EdiVal

C-Tianyu/EditVal

C-Tianyu/prompts

C-Tianyu/dapo_sft

C-Tianyu/sft

C-Tianyu/RSD_image

Tianyu Chen PRO

AI & ML interests

Recent Activity

Organizations

Collections 2

Papers 1

models 8 Sort: Recently updated

datasets 12 Sort: Recently updated

models 8

datasets 12