Daily Papers of 2024-03-12

1. Stealing Part of a Production Language Model 79 upvotes, #1 of 2024-03-12
2. Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU 51 upvotes, #2 of 2024-03-12
3. V3D: Video Diffusion Models are Effective 3D Generators 25 upvotes, #3 of 2024-03-12
4. An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models 23 upvotes, #4 of 2024-03-12
5. VideoMamba: State Space Model for Efficient Video Understanding 20 upvotes, #5 of 2024-03-12
6. Algorithmic progress in language models 15 upvotes, #6 of 2024-03-12
7. Multistep Consistency Models 12 upvotes, #7 of 2024-03-12
8. VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models 10 upvotes, #8 of 2024-03-12
9. FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation 3 upvotes, #9 of 2024-03-12

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.