Daily Papers of 2024-01-24

1. Lumiere: A Space-Time Diffusion Model for Video Generation 82 upvotes, #1 of 2024-01-24
2. Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment 36 upvotes, #2 of 2024-01-24
3. Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding 33 upvotes, #3 of 2024-01-24
4. Small Language Model Meets with Reinforced Vision Vocabulary 32 upvotes, #4 of 2024-01-24
5. Large-scale Reinforcement Learning for Diffusion Models 29 upvotes, #5 of 2024-01-24
6. Orion-14B: Open-source Multilingual Large Language Models 14 upvotes, #6 of 2024-01-24
7. BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Models 12 upvotes, #7 of 2024-01-24
8. AutoRT: Embodied Foundation Models for Large Scale Orchestration of Robotic Agents 12 upvotes, #7 of 2024-01-24
9. Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study 9 upvotes, #9 of 2024-01-24
10. GALA: Generating Animatable Layered Assets from a Single Scan 9 upvotes, #9 of 2024-01-24

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.