726 citations · 906 across the 32 of their papers we have counts for
9 papers · 1 filter
Language Model as Visual Explainer
Xingyi Yang, Xinchao Wang
In this paper, we present Language Model as Visual Explainer LVX, a systematic approach for interpreting the internal workings of vision models using a tree-structured linguistic e…
OminiControl: Minimal and Universal Control for Diffusion Transformer
Zhenxiong Tan, Songhua Liu, Xingyi Yang +2
We present OminiControl, a novel approach that rethinks how image conditions are integrated into Diffusion Transformer (DiT) architectures. Current image conditioning methods eithe…
Kolmogorov-Arnold Transformer
Xingyi Yang, Xinchao Wang
Transformers stand as the cornerstone of mordern deep learning. Traditionally, these models rely on multi-layer perceptron (MLP) layers to mix the information between channels. In…
FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally
Qiuhong Shen, Xingyi Yang, Xinchao Wang
This study addresses the challenge of accurately segmenting 3D Gaussian Splatting from 2D masks. Conventional methods often rely on iterative gradient descent to assign each Gaussi…
Compositional Video Generation as Flow Equalization
Xingyi Yang, Xinchao Wang
Large-scale Text-to-Video (T2V) diffusion models have recently demonstrated unprecedented capability to transform natural language descriptions into stunning and photorealistic vid…
GFlow: Recovering 4D World from Monocular Video
Shizun Wang, Xingyi Yang, Qiuhong Shen +2
Recovering 4D world from monocular video is a crucial yet challenging task. Conventional methods usually rely on the assumptions of multi-view videos, known camera parameters, or s…
Hash3D: Training-free Acceleration for 3D Generation
Xingyi Yang, Xinchao Wang
The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models. Despite this progress, the cumbersome optimization process per se present…
Unsegment Anything by Simulating Deformation
Jiahao Lu, Xingyi Yang, Xinchao Wang
Foundation segmentation models, while powerful, pose a significant risk: they enable users to effortlessly extract any objects from any digital content with a single click, potenti…
Relation Rectification in Diffusion Model
Yinwei Wu, Xingyi Yang, Xinchao Wang
Despite their exceptional generative abilities, large text-to-image diffusion models, much like skilled but careless artists, often struggle with accurately depicting visual relati…