Picture for Yu-Xiong Wang

Yu-Xiong Wang

Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers

Add code
Oct 31, 2024
Viaarxiv icon

ReferEverything: Towards Segmenting Everything We Can Speak of in Videos

Add code
Oct 30, 2024
Viaarxiv icon

Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning

Add code
Oct 18, 2024
Viaarxiv icon

SceneCraft: Layout-Guided 3D Scene Generation

Add code
Oct 11, 2024
Figure 1 for SceneCraft: Layout-Guided 3D Scene Generation
Figure 2 for SceneCraft: Layout-Guided 3D Scene Generation
Figure 3 for SceneCraft: Layout-Guided 3D Scene Generation
Figure 4 for SceneCraft: Layout-Guided 3D Scene Generation
Viaarxiv icon

Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervision

Add code
Oct 10, 2024
Viaarxiv icon

InstructG2I: Synthesizing Images from Multimodal Attributed Graphs

Add code
Oct 09, 2024
Figure 1 for InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
Figure 2 for InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
Figure 3 for InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
Figure 4 for InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
Viaarxiv icon

Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding

Add code
Sep 05, 2024
Viaarxiv icon

Floating No More: Object-Ground Reconstruction from a Single Image

Add code
Jul 26, 2024
Viaarxiv icon

ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing

Add code
Jun 13, 2024
Viaarxiv icon

Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion

Add code
Jun 13, 2024
Viaarxiv icon