Daily Papers of 2023-10-03

1. PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis 63 upvotes, #1 of 2023-10-03
2. Enable Language Models to Implicitly Learn Self-Improvement From Data 24 upvotes, #2 of 2023-10-03
3. Conditional Diffusion Distillation 19 upvotes, #3 of 2023-10-03

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.