Daily Papers of 2024-03-28

1. ViTAR: Vision Transformer with Any Resolution 44 upvotes, #1 of 2024-03-28
2. Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models 33 upvotes, #2 of 2024-03-28
3. Long-form factuality in large language models 22 upvotes, #3 of 2024-03-28
4. ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion 21 upvotes, #4 of 2024-03-28
5. BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text 20 upvotes, #5 of 2024-03-28
6. Garment3DGen: 3D Garment Stylization and Texture Generation 15 upvotes, #6 of 2024-03-28
7. Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction 14 upvotes, #7 of 2024-03-28
8. EgoLifter: Open-world 3D Segmentation for Egocentric Perception 7 upvotes, #8 of 2024-03-28
9. FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing 5 upvotes, #9 of 2024-03-28
10. Towards a World-English Language Model for On-Device Virtual Assistants 4 upvotes, #10 of 2024-03-28

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.