Daily Papers of 2024-02-14

1. BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data 61 upvotes, #1 of 2024-02-14
2. World Model on Million-Length Video And Language With RingAttention 42 upvotes, #2 of 2024-02-14
3. Mixtures of Experts Unlock Parameter Scaling for Deep RL 36 upvotes, #3 of 2024-02-14
4. Lumos : Empowering Multimodal LLMs with Scene Text Recognition 27 upvotes, #4 of 2024-02-14
5. UFO: A UI-Focused Agent for Windows OS Interaction 17 upvotes, #5 of 2024-02-14
6. Graph Mamba: Towards Learning on Graphs with State Space Models 16 upvotes, #6 of 2024-02-14
7. ChatCell: Facilitating Single-Cell Analysis with Natural Language 13 upvotes, #7 of 2024-02-14
8. IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation 13 upvotes, #7 of 2024-02-14
9. Learning Continuous 3D Words for Text-to-Image Generation 11 upvotes, #9 of 2024-02-14
10. Vision-Based Hand Gesture Customization from a Single Demonstration 9 upvotes, #10 of 2024-02-14
11. Tandem Transformers for Inference Efficient LLMs 9 upvotes, #10 of 2024-02-14
12. NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs 5 upvotes, #12 of 2024-02-14

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.