๐ŸŽ“How I Study AIHISA
๐Ÿ“–Read
๐Ÿ“„Papers๐Ÿ“ฐBlogs๐ŸŽฌCourses
๐Ÿ’กLearn
๐Ÿ›ค๏ธPaths๐Ÿ“šTopics๐Ÿ’กConcepts๐ŸŽดShorts
๐ŸŽฏPractice
๐Ÿ“Daily Log๐ŸŽฏPrompts๐Ÿง Review
SearchSettings
How I Study AI - Learn AI Papers & Lectures the Easy Way

Papers2

AllBeginnerIntermediateAdvanced
All SourcesarXiv
#Text-to-Image Generation

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO

Intermediate
Yunze Tong, Mushui Liu et al.Feb 6arXiv

Text-to-image models using GRPO used to give the same final reward to every step, which is like giving the whole team the same grade no matter who did what.

#TurningPoint-GRPO#GRPO#Flow Matching

StageVAR: Stage-Aware Acceleration for Visual Autoregressive Models

Intermediate
Senmao Li, Kai Wang et al.Dec 18arXiv

StageVAR makes image-generating AI much faster by recognizing that early steps set the meaning and structure, while later steps just polish details.

#Visual Autoregressive Modeling#Next-Scale Prediction#Stage-Aware Acceleration