Daily Papers of 2023-06-09

1. Simple and Controllable Music Generation 169 upvotes, #1 of 2023-06-09
2. MIMIC-IT: Multi-Modal In-Context Instruction Tuning 12 upvotes, #2 of 2023-06-09
3. Tracking Everything Everywhere All at Once 11 upvotes, #3 of 2023-06-09
4. PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization 7 upvotes, #4 of 2023-06-09
5. SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions 7 upvotes, #4 of 2023-06-09
6. Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models 7 upvotes, #4 of 2023-06-09
7. Matting Anything 6 upvotes, #7 of 2023-06-09
8. How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources 5 upvotes, #8 of 2023-06-09
9. INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models 5 upvotes, #8 of 2023-06-09
10. Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts 4 upvotes, #10 of 2023-06-09
11. LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs 4 upvotes, #10 of 2023-06-09
12. Improving Open Language Models by Learning from Organic Interactions 3 upvotes, #12 of 2023-06-09
13. Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models 3 upvotes, #12 of 2023-06-09
14. Grounded Text-to-Image Synthesis with Attention Refocusing 3 upvotes, #12 of 2023-06-09
15. Background Prompting for Improved Object Depth 3 upvotes, #12 of 2023-06-09
16. Optimizing ViViT Training: Time and Memory Reduction for Action Recognition 2 upvotes, #16 of 2023-06-09
17. Modular Visual Question Answering via Code Generation 2 upvotes, #16 of 2023-06-09
18. R-MAE: Regions Meet Masked Autoencoders 2 upvotes, #16 of 2023-06-09
19. Scaling Spherical CNNs 2 upvotes, #16 of 2023-06-09

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.