Daily Papers of 2024-05-17

1. Chameleon: Mixed-Modal Early-Fusion Foundation Models 86 upvotes, #1 of 2024-05-17
2. LoRA Learns Less and Forgets Less 68 upvotes, #2 of 2024-05-17
3. CAT3D: Create Anything in 3D with Multi-View Diffusion Models 35 upvotes, #3 of 2024-05-17
4. Many-Shot In-Context Learning in Multimodal Foundation Models 24 upvotes, #4 of 2024-05-17
5. Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection 21 upvotes, #5 of 2024-05-17
6. Toon3D: Seeing Cartoons from a New Perspective 19 upvotes, #6 of 2024-05-17
7. Dual3D: Efficient and Consistent Text-to-3D Generation with Dual-mode Multi-view Latent Diffusion 14 upvotes, #7 of 2024-05-17
8. TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction 9 upvotes, #8 of 2024-05-17

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.