Submitted by akhaliq 53 Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-tuning on a Single GPU · 7 authors 4
Submitted by akhaliq 27 VideoMamba: State Space Model for Efficient Video Understanding · 7 authors 2
Submitted by akhaliq 26 An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models · 7 authors 2
Submitted by akhaliq 16 VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models · 2 authors 4
Submitted by akhaliq 3 FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation · 6 authors 1