Daily Papers of 2023-06-19

1. MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing 37 upvotes, #1 of 2023-06-19
2. Full Parameter Fine-tuning for Large Language Models with Limited Resources 31 upvotes, #2 of 2023-06-19
3. Demystifying GPT Self-Repair for Code Generation 21 upvotes, #3 of 2023-06-19
4. Scaling Open-Vocabulary Object Detection 16 upvotes, #4 of 2023-06-19
5. AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation 15 upvotes, #5 of 2023-06-19
6. Robot Learning with Sensorimotor Pre-training 14 upvotes, #6 of 2023-06-19
7. Inverse Scaling: When Bigger Isn't Better 10 upvotes, #7 of 2023-06-19
8. Block-State Transformer 10 upvotes, #7 of 2023-06-19
9. Explore, Establish, Exploit: Red Teaming Language Models from Scratch 7 upvotes, #9 of 2023-06-19
10. CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models 7 upvotes, #9 of 2023-06-19
11. OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning 7 upvotes, #9 of 2023-06-19
12. CAJun: Continuous Adaptive Jumping using a Learned Centroidal Controller 3 upvotes, #12 of 2023-06-19

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.