Daily Papers of 2024-01-19

1. Self-Rewarding Language Models 156 upvotes, #1 of 2024-01-19
2. VMamba: Visual State Space Model 39 upvotes, #2 of 2024-01-19
3. ChatQA: Building GPT-4 Level Conversational QA Models 35 upvotes, #3 of 2024-01-19
4. DiffusionGPT: LLM-Driven Text-to-Image Generation System 30 upvotes, #4 of 2024-01-19
5. Improving fine-grained understanding in image-text pre-training 19 upvotes, #5 of 2024-01-19
6. Rethinking FID: Towards a Better Evaluation Metric for Image Generation 17 upvotes, #6 of 2024-01-19
7. WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens 17 upvotes, #6 of 2024-01-19
8. SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild 14 upvotes, #8 of 2024-01-19
9. FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder 13 upvotes, #9 of 2024-01-19
10. CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects 9 upvotes, #10 of 2024-01-19

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.