Daily Papers of 2023-07-13

1. Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution 36 upvotes, #1 of 2023-07-13
2. PolyLM: An Open Source Polyglot Large Language Model 27 upvotes, #2 of 2023-07-13
3. Stack More Layers Differently: High-Rank Training Through Low-Rank Updates 25 upvotes, #3 of 2023-07-13
4. SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Task Planning 15 upvotes, #4 of 2023-07-13
5. DNAGPT: A Generalized Pretrained Tool for Multiple DNA Sequence Analysis Tasks 10 upvotes, #5 of 2023-07-13
6. Instruction Mining: High-Quality Instruction Data Selection for Large Language Models 10 upvotes, #5 of 2023-07-13
7. SITTA: A Semantic Image-Text Alignment for Image Captioning 6 upvotes, #7 of 2023-07-13
8. Towards Robust and Efficient Continual Language Learning 5 upvotes, #8 of 2023-07-13
9. VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models 4 upvotes, #9 of 2023-07-13
10. Giving Robots a Hand: Learning Generalizable Manipulation with Eye-in-Hand Human Video Demonstrations 3 upvotes, #10 of 2023-07-13

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.