Submitted by akhaliq 7 Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models · 4 authors 1
Submitted by akhaliq 4 Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts · 13 authors
Submitted by akhaliq 3 Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models · 5 authors
Submitted by akhaliq 3 Improving Open Language Models by Learning from Organic Interactions · 13 authors 1
Submitted by akhaliq 2 LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs · 6 authors
Submitted by akhaliq 2 Optimizing ViViT Training: Time and Memory Reduction for Action Recognition · 3 authors