1 code implementation • 16 Jun 2025 • Yuheng Yuan, Qiuhong Shen, Shizun Wang, Xingyi Yang, Xinchao Wang
Extensive experiments demonstrate that our technique significantly outperforms previous state-of-the-art methods on the 3D reconstruction and multi-view depth estimation tasks.
1 code implementation • 27 May 2025 • Zeqing Wang, Bowen Zheng, Xingyi Yang, Zhenxiong Tan, Yuecong Xu, Xinchao Wang
Diffusion Transformer (DiT)-based video diffusion models generate high-quality videos at scale but incur prohibitive processing latency and memory costs for long videos.
no code implementations • 20 Mar 2025 • Yuheng Yuan, Qiuhong Shen, Xingyi Yang, Xinchao Wang
(Q1) \textbf{Short-Lifespan Gaussians}: 4DGS uses a large portion of Gaussians with short temporal span to represent scene dynamics, leading to an excessive number of Gaussians.
1 code implementation • 11 Mar 2025 • Zhenxiong Tan, Qiaochu Xue, Xingyi Yang, Songhua Liu, Xinchao Wang
Fine-grained control of text-to-image diffusion transformer models (DiT) remains a critical challenge for practical deployment.
no code implementations • 27 Feb 2025 • Hanyang Kong, Xingyi Yang, Xinchao Wang
In response, we introduce Efficient Dynamic Gaussian Splatting (EDGS), which represents dynamic scenes via sparse time-variant attribute modeling.
1 code implementation • 26 Feb 2025 • Li Ju, Xingyi Yang, Qi Li, Xinchao Wang
Empirical validation, conducted over 16 datasets representative of these scenarios, confirms the framework's capacity for task- and domain-agnostic transfer learning within graph-like data, marking a significant advancement in the field of GNNs.
no code implementations • CVPR 2025 • Suizhi Huang, Xingyi Yang, Hongtao Lu, Xinchao Wang
To tackle this, we propose EquiGen, a framework that can generate new INRs from limited data.
no code implementations • CVPR 2025 • Hanyang Kong, Xingyi Yang, Xinchao Wang
Novel view synthesis from limited observations remains a significant challenge due to the lack of information in under-sampled regions, often resulting in noticeable artifacts.
no code implementations • CVPR 2025 • Bonan Li, ZiCheng Zhang, Xingyi Yang, Xinchao Wang
To further enhance cross-view consistency and alleviate content drift, CoSER rapidly scan all views in spiral bidirectional manner to aware holistic information and then scores each point based on semantic material.
no code implementations • 28 Dec 2024 • Mengnan Zhao, Lihe Zhang, Xingyi Yang, Tianhang Zheng, BaoCai Yin
In this paper, we systematically analyze the impact of diverse text anchors on unlearning performance.
2 code implementations • 22 Nov 2024 • Zhenxiong Tan, Songhua Liu, Xingyi Yang, Qiaochu Xue, Xinchao Wang
In this paper, we introduce OminiControl, a highly versatile and parameter-efficient framework that integrates image conditions into pre-trained Diffusion Transformer (DiT) models.
1 code implementation • 18 Sep 2024 • Qiuhong Shen, Xingyi Yang, Michael Bi Mi, Xinchao Wang
We embark on the age-old quest: unveiling the hidden dimensions of objects from mere glimpses of their visible parts.
1 code implementation • 16 Sep 2024 • Xingyi Yang, Xinchao Wang
In this paper, we introduce the Kolmogorov-Arnold Transformer (KAT), a novel architecture that replaces MLP layers with Kolmogorov-Arnold Network (KAN) layers to enhance the expressiveness and performance of the model.
1 code implementation • 12 Sep 2024 • Qiuhong Shen, Xingyi Yang, Xinchao Wang
Extensive experiments demonstrate the efficiency and robustness of our method in segmenting various scenes, and its superior performance in downstream tasks such as object removal and inpainting.
no code implementations • 23 Aug 2024 • Bonan Li, ZiCheng Zhang, Xingyi Yang, Xinchao Wang
To further enhance cross-view consistency and alleviate content drift, CoSER rapidly scan all views in spiral bidirectional manner to aware holistic information and then scores each point based on semantic material.
no code implementations • 24 Jun 2024 • Zhenxiong Tan, Xingyi Yang, Songhua Liu, Xinchao Wang
Specifically, we propose two coherent mechanisms: Clip parallelism and Dual-scope attention.
1 code implementation • 10 Jun 2024 • Xingyi Yang, Xinchao Wang
Despite the promising results, a significant challenge remains: these models struggle to fully grasp complex compositional interactions between multiple concepts and actions.
no code implementations • 28 May 2024 • Shizun Wang, Xingyi Yang, Qiuhong Shen, Zhenxiang Jiang, Xinchao Wang
To solve this, we introduce GFlow, a new framework that utilizes only 2D priors (depth and optical flow) to lift a video to a 4D scene, as a flow of 3D Gaussians through space and time.
no code implementations • 9 May 2024 • Sitian Shen, Jing Xu, Yuheng Yuan, Xingyi Yang, Qiuhong Shen, Xinchao Wang
User-friendly 3D object editing is a challenging task that has attracted significant attention recently.
1 code implementation • CVPR 2025 • Xingyi Yang, Xinchao Wang
The evolution of 3D generative modeling has been notably propelled by the adoption of 2D diffusion models.
1 code implementation • CVPR 2024 • 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, potentially leading to copyright infringement or malicious misuse.
no code implementations • CVPR 2024 • 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 relationships between objects.
1 code implementation • ICCV 2023 • Sucheng Ren, Xingyi Yang, Songhua Liu, Xinchao Wang
At the heart of our approach is to utilize a significance map, which is estimated through hybrid-scale self-attention and evolves itself during training, to reallocate tokens based on the significance of each region.
1 code implementation • ICCV 2023 • Xingyi Yang, Xinchao Wang
In this paper, we conduct an in-depth investigation of the representation power of DPMs, and propose a novel knowledge transfer method that leverages the knowledge acquired by generative DPMs for recognition tasks.
1 code implementation • CVPR 2023 • Runpeng Yu, Songhua Liu, Xingyi Yang, Xinchao Wang
Machine learning society has witnessed the emergence of a myriad of Out-of-Distribution (OoD) algorithms, which address the distribution shift between the training and the testing distribution by searching for a unified predictor or invariant feature representation.
1 code implementation • CVPRW 2023 • Marcos V. Conde, Manuel Kolmet, Tim Seizinger, Tom E. Bishop, Radu Timofte, Xiangyu Kong, Dafeng Zhang, Jinlong Wu, Fan Wang, Juewen Peng, Zhiyu Pan, Chengxin Liu, Xianrui Luo, Huiqiang Sun, Liao Shen, Zhiguo Cao, Ke Xian, Chaowei Liu, Zigeng Chen, Xingyi Yang, Songhua Liu, Yongcheng Jing, Michael Bi Mi, Xinchao Wang, Zhihao Yang, Wenyi Lian, Siyuan Lai, Haichuan Zhang, Trung Hoang, Amirsaeed Yazdani, Vishal Monga, Ziwei Luo, Fredrik K. Gustafsson, Zheng Zhao, Jens Sjölund, Thomas B. Schön, Yuxuan Zhao, Baoliang Chen, Yiqing Xu, JiXiang Niu
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge.
1 code implementation • 19 Apr 2023 • Qiuhong Shen, Xingyi Yang, Xinchao Wang
3D reconstruction from a single-RGB image in unconstrained real-world scenarios presents numerous challenges due to the inherent diversity and complexity of objects and environments.
no code implementations • CVPR 2023 • Xingyi Yang, Daquan Zhou, Jiashi Feng, Xinchao Wang
Despite the recent visually-pleasing results achieved, the massive computational cost has been a long-standing flaw for diffusion probabilistic models (DPMs), which, in turn, greatly limits their applications on resource-limited platforms.
1 code implementation • NIPS 2022 • Songhua Liu, Kai Wang, Xingyi Yang, Jingwen Ye, Xinchao Wang
In this paper, we study dataset distillation (DD), from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play strategy portable to any existing DD baseline.
3 code implementations • 30 Oct 2022 • Songhua Liu, Kai Wang, Xingyi Yang, Jingwen Ye, Xinchao Wang
In this paper, we study \xw{dataset distillation (DD)}, from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play strategy portable to any existing DD baseline.
1 code implementation • 24 Oct 2022 • Xingyi Yang, Daquan Zhou, Songhua Liu, Jingwen Ye, Xinchao Wang
Given a collection of heterogeneous models pre-trained from distinct sources and with diverse architectures, the goal of DeRy, as its name implies, is to first dissect each model into distinctive building blocks, and then selectively reassemble the derived blocks to produce customized networks under both the hardware resource and performance constraints.
1 code implementation • CVPR 2023 • Xinjiang Wang, Xingyi Yang, Shilong Zhang, Yijiang Li, Litong Feng, Shijie Fang, Chengqi Lyu, Kai Chen, Wayne Zhang
In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised object detection (SSOD).
1 code implementation • 17 Jul 2022 • Jingwen Ye, Yifang Fu, Jie Song, Xingyi Yang, Songhua Liu, Xin Jin, Mingli Song, Xinchao Wang
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge.
1 code implementation • 4 Jul 2022 • Xingyi Yang, Jingwen Ye, Xinchao Wang
The core idea of KF lies in the modularization and assemblability of knowledge: given a pretrained network model as input, KF aims to decompose it into several factor networks, each of which handles only a dedicated task and maintains task-specific knowledge factorized from the source network.
1 code implementation • 12 Dec 2021 • ZiHao Zhou, Xingyi Yang, Ryan Rossi, Handong Zhao, Rose Yu
The key construction of our approach is the nonparametric space-time intensity function, governed by a latent process.
no code implementations • ACL 2021 • Meng Zhou, Zechen Li, Bowen Tan, Guangtao Zeng, Wenmian Yang, Xuehai He, Zeqian Ju, Subrato Chakravorty, Shu Chen, Xingyi Yang, Yichen Zhang, Qingyang Wu, Zhou Yu, Kun Xu, Eric Xing, Pengtao Xie
Training complex dialog generation models on small datasets bears high risk of overfitting.
no code implementations • ACL 2021 • Xingyi Yang, Muchao Ye, Quanzeng You, Fenglong Ma
Medical report generation is one of the most challenging tasks in medical image analysis.
no code implementations • 1 Jan 2021 • ZiHao Zhou, Xingyi Yang, Xinyi He, Ryan Rossi, Handong Zhao, Rose Yu
To the best of our knowledge, this is the first neural point process model that can jointly predict both the space and time of events.
1 code implementation • 22 Dec 2020 • Xingyi Yang
Deep neural networks (DNN) are typically optimized using stochastic gradient descent (SGD).
no code implementations • CVPR 2021 • Ramtin Hosseini, Xingyi Yang, Pengtao Xie
To address this problem, we propose methods to perform differentiable search of robust neural architectures.
1 code implementation • ECCV 2020 • Rui Zhu, Xingyi Yang, Yannick Hold-Geoffroy, Federico Perazzi, Jonathan Eisenmann, Kalyan Sunkavalli, Manmohan Chandraker
Most 3D reconstruction methods may only recover scene properties up to a global scale ambiguity.
no code implementations • 19 Jun 2020 • Xingyi Yang, Xuehai He, Yuxiao Liang, Yue Yang, Shanghang Zhang, Pengtao Xie
There has not been a clear understanding on what properties of data and tasks render one approach outperforms the other.
no code implementations • 17 Jun 2020 • Xingyi Yang, Nandiraju Gireesh, Eric Xing, Pengtao Xie
To address this problem, we develop methods to generate view-consistent, high-fidelity, and high-resolution X-ray images from radiology reports to facilitate radiology training of medical students.
no code implementations • 11 May 2020 • Wenmian Yang, Guangtao Zeng, Bowen Tan, Zeqian Ju, Subrato Chakravorty, Xuehai He, Shu Chen, Xingyi Yang, Qingyang Wu, Zhou Yu, Eric Xing, Pengtao Xie
On these two datasets, we train several dialogue generation models based on Transformer, GPT, and BERT-GPT.
no code implementations • medRxiv 2020 • Xuehai He, Xingyi Yang, Shanghang Zhang, Jinyu Zhao, Yichen Zhang, Eric Xing, Pengtao Xie
Besides, these works require a large number of CTs to train accurate diagnosis models, which are difficult to obtain.
17 code implementations • 30 Mar 2020 • Xingyi Yang, Xuehai He, Jinyu Zhao, Yichen Zhang, Shanghang Zhang, Pengtao Xie
Using this dataset, we develop diagnosis methods based on multi-task learning and self-supervised learning, that achieve an F1 of 0. 90, an AUC of 0. 98, and an accuracy of 0. 89.