Daily Papers of 2024-01-18

1. Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model 62 upvotes, #1 of 2024-01-18
2. ReFT: Reasoning with Reinforced Fine-Tuning 32 upvotes, #2 of 2024-01-18
3. SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding 20 upvotes, #3 of 2024-01-18
4. GARField: Group Anything with Radiance Fields 20 upvotes, #3 of 2024-01-18
5. UniVG: Towards UNIfied-modal Video Generation 17 upvotes, #5 of 2024-01-18
6. DeepSpeed-FastGen: High-throughput Text Generation for LLMs via MII and DeepSpeed-Inference 15 upvotes, #6 of 2024-01-18
7. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models 14 upvotes, #7 of 2024-01-18
8. SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers 13 upvotes, #8 of 2024-01-18
9. Asynchronous Local-SGD Training for Language Modeling 12 upvotes, #9 of 2024-01-18
10. TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion 11 upvotes, #10 of 2024-01-18
11. Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis 10 upvotes, #11 of 2024-01-18
12. ICON: Incremental CONfidence for Joint Pose and Radiance Field Optimization 7 upvotes, #12 of 2024-01-18

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.