Daily Papers of 2023-05-17

1. SoundStorm: Efficient Parallel Audio Generation 15 upvotes, #1 of 2023-05-17
2. Common Diffusion Noise Schedules and Sample Steps are Flawed 14 upvotes, #2 of 2023-05-17
3. Towards Expert-Level Medical Question Answering with Large Language Models 6 upvotes, #3 of 2023-05-17
4. Online Continual Learning Without the Storage Constraint 4 upvotes, #4 of 2023-05-17
5. FitMe: Deep Photorealistic 3D Morphable Model Avatars 4 upvotes, #4 of 2023-05-17
6. AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation 3 upvotes, #6 of 2023-05-17
7. Make-An-Animation: Large-Scale Text-conditional 3D Human Motion Generation 3 upvotes, #6 of 2023-05-17
8. Pre-Training to Learn in Context 2 upvotes, #8 of 2023-05-17
9. Understanding 3D Object Interaction from a Single Image 2 upvotes, #8 of 2023-05-17
10. Dual-Alignment Pre-training for Cross-lingual Sentence Embedding 1 upvotes, #10 of 2023-05-17

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.