Submitted by akhaliq 38 DreaMoving: A Human Dance Video Generation Framework based on Diffusion Models · 14 authors 10
Submitted by akhaliq 17 Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors · 8 authors
Submitted by akhaliq 7 EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism · 5 authors 7
Submitted by akhaliq 3 Localized Symbolic Knowledge Distillation for Visual Commonsense Models · 11 authors