Daily Papers of 2024-03-05

1. MovieLLM: Enhancing Long Video Understanding with AI-Generated Movies 21 upvotes, #1 of 2024-03-05
2. OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on 19 upvotes, #2 of 2024-03-05
3. AtomoVideo: High Fidelity Image-to-Video Generation 16 upvotes, #3 of 2024-03-05
4. InfiMM-HD: A Leap Forward in High-Resolution Multimodal Understanding 14 upvotes, #4 of 2024-03-05
5. DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models 10 upvotes, #5 of 2024-03-05
6. ResAdapter: Domain Consistent Resolution Adapter for Diffusion Models 10 upvotes, #5 of 2024-03-05
7. TripoSR: Fast 3D Object Reconstruction from a Single Image 7 upvotes, #7 of 2024-03-05
8. ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models 6 upvotes, #8 of 2024-03-05
9. RT-H: Action Hierarchies Using Language 5 upvotes, #9 of 2024-03-05
10. Twisting Lids Off with Two Hands 5 upvotes, #9 of 2024-03-05
11. 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos 4 upvotes, #11 of 2024-03-05

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.