Daily Papers of 2024-04-11

1. Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention 80 upvotes, #1 of 2024-04-11
2. RULER: What's the Real Context Size of Your Long-Context Language Models? 28 upvotes, #2 of 2024-04-11
3. RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion 19 upvotes, #3 of 2024-04-11
4. DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting 13 upvotes, #4 of 2024-04-11
5. BRAVE: Broadening the visual encoding of vision-language models 13 upvotes, #4 of 2024-04-11
6. Adapting LLaMA Decoder to Vision Transformer 12 upvotes, #6 of 2024-04-11
7. Urban Architect: Steerable 3D Urban Scene Generation with Layout Prior 9 upvotes, #7 of 2024-04-11

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.