Fangyu

rslinfy

6 3

AI & ML interests

None yet

Recent Activity

upvoted an article 14 days ago

Deriving the PPO Loss from First Principles

upvoted a paper 17 days ago

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

upvoted a paper about 1 month ago

Exploring the Design Space of Reward Backpropagation for Flow Matching

View all activity

Organizations

None yet

upvoted an article 14 days ago

Article

Deriving the PPO Loss from First Principles

garg-aayush

•

Dec 25, 2025

• 47

upvoted a paper 17 days ago

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published 19 days ago • 84

upvoted a paper about 1 month ago

Exploring the Design Space of Reward Backpropagation for Flow Matching

Paper • 2606.11075 • Published Jun 9 • 12

upvoted a paper 6 months ago

On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models

Paper • 2602.03392 • Published Feb 3 • 59

upvoted a paper 7 months ago

FlowAct-R1: Towards Interactive Humanoid Video Generation

Paper • 2601.10103 • Published Jan 15 • 78

upvoted a paper 11 months ago

WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research

Paper • 2509.13312 • Published Sep 16, 2025 • 107