Daily Papers of 2023-09-04

1. YaRN: Efficient Context Window Extension of Large Language Models 88 upvotes, #1 of 2023-09-04
2. RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback 53 upvotes, #2 of 2023-09-04
3. Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior 23 upvotes, #3 of 2023-09-04
4. VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation 23 upvotes, #3 of 2023-09-04
5. CityDreamer: Compositional Generative Model of Unbounded 3D Cities 21 upvotes, #5 of 2023-09-04
6. FACET: Fairness in Computer Vision Evaluation Benchmark 20 upvotes, #6 of 2023-09-04
7. Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following 13 upvotes, #7 of 2023-09-04

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.