AI Research Papers Daily

Stealing Part of a Production Language Model

Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU

VideoMamba: State Space Model for Efficient Video Understanding

V3D: Video Diffusion Models are Effective 3D Generators

An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

Algorithmic progress in language models

VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models

Multistep Consistency Models

FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation