Daily Papers of 2023-09-08

1. Large Language Models as Optimizers 79 upvotes, #1 of 2023-09-08
2. FLM-101B: An Open LLM and How to Train It with $100K Budget 45 upvotes, #2 of 2023-09-08
3. DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models 36 upvotes, #3 of 2023-09-08
4. Tracking Anything with Decoupled Video Segmentation 29 upvotes, #4 of 2023-09-08
5. ProPainter: Improving Propagation and Transformer for Video Inpainting 28 upvotes, #5 of 2023-09-08
6. GPT Can Solve Mathematical Problems Without a Calculator 19 upvotes, #6 of 2023-09-08
7. ImageBind-LLM: Multi-modality Instruction Tuning 17 upvotes, #7 of 2023-09-08
8. InstructDiffusion: A Generalist Modeling Interface for Vision Tasks 14 upvotes, #8 of 2023-09-08
9. SyncDreamer: Generating Multiview-consistent Images from a Single-view Image 13 upvotes, #9 of 2023-09-08
10. Text2Control3D: Controllable 3D Avatar Generation in Neural Radiance Fields using Geometry-Guided Text-to-Image Diffusion Model 12 upvotes, #10 of 2023-09-08
11. XGen-7B Technical Report 8 upvotes, #11 of 2023-09-08
12. Robotic Table Tennis: A Case Study into a High Speed Learning System 7 upvotes, #12 of 2023-09-08
13. Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation 6 upvotes, #13 of 2023-09-08

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.