Daily Papers of 2023-12-11

1. SparQ Attention: Bandwidth-Efficient LLM Inference 40 upvotes, #1 of 2023-12-11
2. DreaMoving: A Human Dance Video Generation Framework based on Diffusion Models 39 upvotes, #2 of 2023-12-11
3. Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors 17 upvotes, #3 of 2023-12-11
4. Customizing Motion in Text-to-Video Diffusion Models 11 upvotes, #4 of 2023-12-11
5. MVDD: Multi-View Depth Diffusion Models 10 upvotes, #5 of 2023-12-11
6. PathFinder: Guided Search over Multi-Step Reasoning Paths 10 upvotes, #5 of 2023-12-11
7. EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism 7 upvotes, #7 of 2023-12-11
8. Localized Symbolic Knowledge Distillation for Visual Commonsense Models 3 upvotes, #8 of 2023-12-11

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.