Submitted by akhaliq 31 Analyzing and Improving the Training Dynamics of Diffusion Models · 6 authors 2
Submitted by akhaliq 30 ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation · 2 authors 2
Submitted by akhaliq 25 X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model · 8 authors 1
Submitted by akhaliq 16 LivePhoto: Real Image Animation with Text-guided Motion Control · 7 authors 3
Submitted by akhaliq 12 Orthogonal Adaptation for Modular Customization of Diffusion Models · 4 authors
Submitted by akhaliq 12 Rank-without-GPT: Building GPT-Independent Listwise Rerankers on Open-Source Large Language Models · 5 authors
Submitted by akhaliq 11 LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models · 11 authors
Submitted by akhaliq 10 Fine-grained Controllable Video Generation via Object Appearance and Context · 7 authors
Submitted by akhaliq 9 MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures · 12 authors
Submitted by akhaliq 8 StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D · 10 authors 3
Submitted by akhaliq 7 Alchemist: Parametric Control of Material Properties with Diffusion Models · 8 authors
Submitted by akhaliq 7 GPT4Point: A Unified Framework for Point-Language Understanding and Generation · 8 authors
Submitted by akhaliq 6 Generating Fine-Grained Human Motions Using ChatGPT-Refined Descriptions · 5 authors