Daily Papers of 2023-12-14

1. SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention 40 upvotes, #1 of 2023-12-14
2. Distributed Inference and Fine-tuning of Large Language Models Over The Internet 27 upvotes, #2 of 2023-12-14
3. CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor 17 upvotes, #3 of 2023-12-14
4. PromptBench: A Unified Library for Evaluation of Large Language Models 16 upvotes, #4 of 2023-12-14
5. Foundation Models in Robotics: Applications, Challenges, and the Future 15 upvotes, #5 of 2023-12-14
6. Clockwork Diffusion: Efficient Generation With Model-Step Distillation 12 upvotes, #6 of 2023-12-14
7. FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects 12 upvotes, #6 of 2023-12-14
8. Invariant Graph Transformer 7 upvotes, #8 of 2023-12-14
9. ProNeRF: Learning Efficient Projection-Aware Ray Sampling for Fine-Grained Implicit Neural Radiance Fields 4 upvotes, #9 of 2023-12-14

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.