Author name cluster

Yufei Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

EAAI Journal 2025 Journal Article

Prescribed-time convergence noise-tolerant zeroing neural network for multi-robot position management and coordination

Tinglei Wang
Yufei Wang
Cheng Hua
Xinwei Cao
Bolin Liao
Shuai Li

A zeroing neural network (ZNN) model with prescribed-time convergence and noise tolerance is constructed for the first time to address multi-robot position planning (MPP) tasks. Unlike traditional ZNN models, which converge within finite, fixed, or predefined times, this model ensures that system errors converge precisely within the predefined time T p. Furthermore, it significantly enhances noise tolerance while maintaining excellent convergence performance. Through rigorous mathematical analysis and detailed numerical simulations, the proposed model demonstrates exceptional convergence and robustness, even under noise disturbances. In a noise-free environment, the convergence time accuracy (CTA) of this model when solving the MPP task reach over 90%, which is approximately 30% higher than traditional predefined-time convergence neural networks.

Details DOI

NeurIPS Conference 2025 Conference Paper

Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling

Zhihao Li
Yufei Wang
Heliang Zheng
Yihao Luo
Bihan Wen

High-fidelity 3D object synthesis remains significantly more challenging than 2D image generation due to the unstructured nature of mesh data and the cubic complexity of dense volumetric grids. Existing two-stage pipelines—compressing meshes with a VAE (using either 2D or 3D supervision), followed by latent diffusion sampling—often suffer from severe detail loss caused by inefficient representations and modality mismatches introduced in VAE. We introduce Sparc3D, a unified framework that combines a sparse deformable marching cubes representation Sparcubes with a novel encoder Sparconv-VAE. Sparcubes converts raw meshes into high-resolution ($1024^3$) surfaces with arbitrary topology by scattering signed distance and deformation fields onto a sparse cube, allowing differentiable optimization. Sparconv-VAE is the first modality-consistent variational autoencoder built entirely upon sparse convolutional networks, enabling efficient and near-lossless 3D reconstruction suitable for high-resolution generative modeling through latent diffusion. Sparc3D achieves state-of-the-art reconstruction fidelity on challenging inputs, including open surfaces, disconnected components, and intricate geometry. It preserves fine-grained shape details, reduces training and inference cost, and integrates naturally with latent diffusion models for scalable, high-resolution 3D generation.

PDF Details

NeurIPS Conference 2024 Conference Paper

A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis

Yue Yang
Mona Gandhi
Yufei Wang
Yifan Wu
Michael S. Yao
Chris Callison-Burch
James C. Gee
Mark Yatskar

While deep networks have achieved broad success in analyzing natural images, when applied to medical scans, they often fail in unexcepted situations. We investigate this challenge and focus on model sensitivity to domain shifts, such as data sampled from different hospitals or data confounded by demographic variables such as sex, race, etc, in the context of chest X-rays and skin lesion images. A key finding we show empirically is that existing visual backbones lack an appropriate prior from the architecture for reliable generalization in these settings. Taking inspiration from medical training, we propose giving deep networks a prior grounded in explicit medical knowledge communicated in natural language. To this end, we introduce Knowledge-enhanced Bottlenecks (KnoBo), a class of concept bottleneck models that incorporates knowledge priors that constrain it to reason with clinically relevant factors found in medical textbooks or PubMed. KnoBo uses retrieval-augmented language models to design an appropriate concept space paired with an automatic training procedure for recognizing the concept. We evaluate different resources of knowledge and recognition architectures on a broad range of domain shifts across 20 datasets. In our comprehensive evaluation with two imaging modalities, KnoBo outperforms fine-tuned models on confounded datasets by 32. 4% on average. Finally, evaluations reveal that PubMed is a promising resource for making medical models less sensitive to domain shift, outperforming other resources on both diversity of information and final prediction performance.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting

Yian Wang
Xiaowen Qiu
Jiageng Liu
Zhehuan Chen
Jiting Cai
Yufei Wang
Tsun-Hsuan Wang
Zhou Xian

Creating large-scale interactive 3D environments is essential for the development of Robotics and Embodied AI research. However, generating diverse embodied environments with realistic detail and considerable complexity remains a significant challenge. Current methods, including manual design, procedural generation, diffusion-based scene generation, and large language model (LLM) guided scene design, are hindered by limitations such as excessive human effort, reliance on predefined rules or training datasets, and limited 3D spatial reasoning ability. Since pre-trained 2D image generative models better capture scene and object configuration than LLMs, we address these challenges by introducing $\textit{Architect}$, a generative framework that creates complex and realistic 3D embodied environments leveraging diffusion-based 2D image inpainting. In detail, we utilize foundation visual perception models to obtain each generated object from the image and leverage pre-trained depth estimation models to lift the generated 2D image to 3D space. While there are still challenges that the camera parameters and scale of depth are still absent in the generated image, we address those problems by ''controlling'' the diffusion model by $\textit{hierarchical inpainting}$. Specifically, having access to ground-truth depth and camera parameters in simulation, we first render a photo-realistic image of only the background. Then, we inpaint the foreground in this image, passing the geometric cues to the inpainting model in the background, which informs the camera parameters. This process effectively controls the camera parameters and depth scale for the generated image, facilitating the back-projection from 2D image to 3D point clouds. Our pipeline is further extended to a hierarchical and iterative inpainting process to continuously generate the placement of large furniture and small objects to enrich the scene. This iterative structure brings the flexibility for our method to generate or refine scenes from various starting points, such as text, floor plans, or pre-arranged environments. Experimental results demonstrate that $\textit{Architect}$ outperforms existing methods in producing realistic and complex environments, making it highly suitable for Embodied AI and robotics applications.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

ContextGS : Compact 3D Gaussian Splatting with Anchor Level Context Model

Yufei Wang
Zhihao Li
Lanqing Guo
Wenhan Yang
Alex C. Kot
Bihan Wen

Recently, 3D Gaussian Splatting (3DGS) has become a promising framework for novel view synthesis, offering fast rendering speeds and high fidelity. However, the large number of Gaussians and their associated attributes require effective compression techniques. Existing methods primarily compress neural Gaussians individually and independently, i. e. , coding all the neural Gaussians at the same time, with little design for their interactions and spatial dependence. Inspired by the effectiveness of the context model in image compression, we propose the first autoregressive model at the anchor level for 3DGS compression in this work. We divide anchors into different levels and the anchors that are not coded yet can be predicted based on the already coded ones in all the coarser levels, leading to more accurate modeling and higher coding efficiency. To further improve the efficiency of entropy coding, e. g. , to code the coarsest level with no already coded anchors, we propose to introduce a low-dimensional quantized feature as the hyperprior for each anchor, which can be effectively compressed. Our work pioneers the context model in the anchor level for 3DGS representation, yielding an impressive size reduction of over 100 times compared to vanilla 3DGS and 15 times compared to the most recent state-of-the-art work Scaffold-GS, while achieving comparable or even higher rendering quality.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning

Weikang Wan
Ziyu Wang
Yufei Wang
Zackory Erickson
David Held

This paper introduces DiffTORI, which utilizes $\textbf{Diff}$erentiable $\textbf{T}$rajectory $\textbf{O}$ptimization as the policy representation to generate actions for deep $\textbf{R}$einforcement and $\textbf{I}$mitation learning. Trajectory optimization is a powerful and widely used algorithm in control, parameterized by a cost and a dynamics function. The key to our approach is to leverage the recent progress in differentiable trajectory optimization, which enables computing the gradients of the loss with respect to the parameters of trajectory optimization. As a result, the cost and dynamics functions of trajectory optimization can be learned end-to-end. DiffTORI addresses the “objective mismatch” issue of prior model-based RL algorithms, as the dynamics model in DiffTORI is learned to directly maximize task performance by differentiating the policy gradient loss through the trajectory optimization process. We further benchmark DiffTORI for imitation learning on standard robotic manipulation task suites with high-dimensional sensory observations and compare our method to feedforward policy classes as well as Energy-Based Models (EBM) and Diffusion. Across 15 model based RL tasks and 35 imitation learning tasks with high-dimensional image and point cloud inputs, DiffTORI outperforms prior state-of-the-art methods in both domains.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

From Chaos to Clarity: 3DGS in the Dark

Zhihao Li
Yufei Wang
Alex Kot
Bihan Wen

Novel view synthesis from raw images provides superior high dynamic range (HDR) information compared to reconstructions from low dynamic range RGB images. However, the inherent noise in unprocessed raw images compromises the accuracy of 3D scene representation. Our study reveals that 3D Gaussian Splatting (3DGS) is particularly susceptible to this noise, leading to numerous elongated Gaussian shapes that overfit the noise, thereby significantly degrading reconstruction quality and reducing inference speed, especially in scenarios with limited views. To address these issues, we introduce a novel self-supervised learning framework designed to reconstruct HDR 3DGS from a limited number of noisy raw images. This framework enhances 3DGS by integrating a noise extractor and employing a noise-robust reconstruction loss that leverages a noise distribution prior. Experimental results show that our method outperforms LDR/HDR 3DGS and previous state-of-the-art (SOTA) self-supervised and supervised pre-trained models in both reconstruction quality and inference speed on the RawNeRF dataset across a broad range of training views. We will release the code upon paper acceptance.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Low-Light Image Enhancement with Normalizing Flow

Yufei Wang
Renjie Wan
Wenhan Yang
Haoliang Li
Lap-Pui Chau
Alex Kot

To enhance low-light images to normally-exposed ones is highly ill-posed, namely that the mapping relationship between them is one-to-many. Previous works based on the pixel-wise reconstruction losses and deterministic processes fail to capture the complex conditional distribution of normally exposed images, which results in improper brightness, residual noise, and artifacts. In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model. An invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution. In this way, the conditional distribution of the normally exposed images can be well modeled, and the enhancement process, i. e. . the other inference direction of the invertible network, is equivalent to being constrained by a loss function that better describes the manifold structure of natural images during the training. The experimental results on the existing benchmark datasets show our method achieves better quantitative and qualitative results, obtaining better-exposed illumination, less noise and artifact, and richer colors.

PDF Details

TMLR Journal 2022 Journal Article

Variational Disentanglement for Domain Generalization

Yufei Wang
Haoliang Li
Hao Cheng
Bihan Wen
Lap-Pui Chau
Alex Kot

Domain generalization aims to learn a domain-invariant model that can generalize well to the unseen target domain. In this paper, based on the assumption that there exists an invariant feature mapping, we propose an evidence upper bound of the divergence between the category-specific feature and its invariant ground-truth using variational inference. To optimize this upper bound, we further propose an efficient Variational Disentanglement Network (VDN) that is capable of disentangling the domain-specific features and category-specific features (which generalize well to the unseen samples). Besides, the generated novel images from VDN are used to further improve the generalization ability. We conduct extensive experiments to verify our method on three benchmarks, and both quantitative and qualitative results illustrate the effectiveness of our method.

PDF Details

NeurIPS Conference 2021 Conference Paper

Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation

Yufei Wang
Can Xu
Huang Hu
Chongyang Tao
Stephen Wan
Mark Dras
Mark Johnson
Daxin Jiang

Sequence-to-Sequence (Seq2Seq) neural text generation models, especially the pre-trained ones (e. g. , BART and T5), have exhibited compelling performance on various natural language generation tasks. However, the black-box nature of these models limits their application in tasks where specific rules (e. g. , controllable constraints, prior knowledge) need to be executed. Previous works either design specific model structures (e. g. , Copy Mechanism corresponding to the rule "the generated output should include certain words in the source input'') or implement specialized inference algorithms (e. g. , Constrained Beam Search) to execute particular rules through the text generation. These methods require the careful design case-by-case and are difficult to support multiple rules concurrently. In this paper, we propose a novel module named Neural Rule-Execution Tracking Machine (NRETM) that can be equipped into various transformer-based generators to leverage multiple rules simultaneously to guide the neural generation model for superior generation performance in an unified and scalable way. Extensive experiments on several benchmarks verify the effectiveness of our proposed model in both controllable and general text generation tasks.

PDF Details

NeurIPS Conference 2020 Conference Paper

Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization

Haoliang Li
Yufei Wang
Renjie Wan
Shiqi Wang
Tie-Qiang Li
Alex Kot

Recently, we have witnessed great progress in the field of medical imaging classification by adopting deep neural networks. However, the recent advanced models still require accessing sufficiently large and representative datasets for training, which is often unfeasible in clinically realistic environments. When trained on limited datasets, the deep neural network is lack of generalization capability, as the trained deep neural network on data within a certain distribution (e. g. the data captured by a certain device vendor or patient population) may not be able to generalize to the data with another distribution. In this paper, we introduce a simple but effective approach to improve the generalization capability of deep neural networks in the field of medical imaging classification. Motivated by the observation that the domain variability of the medical images is to some extent compact, we propose to learn a representative feature space through variational encoding with a novel linear-dependency regularization term to capture the shareable information among medical data collected from different domains. As a result, the trained neural network is expected to equip with better generalization capability to the ``unseen" medical data. Experimental results on two challenging medical imaging classification tasks indicate that our method can achieve better cross-domain generalization capability compared with state-of-the-art baselines.

PDF Details

AAAI Conference 2019 Conference Paper

Deep Reinforcement Learning for Green Security Games with Real-Time Information

Yufei Wang
Zheyuan Ryan Shi
Lantao Yu
Yi Wu
Rohit Singh
Lucas Joppa
Fei Fang

Green Security Games (GSGs) have been proposed and applied to optimize patrols conducted by law enforcement agencies in green security domains such as combating poaching, illegal logging and overfishing. However, real-time information such as footprints and agents’ subsequent actions upon receiving the information, e. g. , rangers following the footprints to chase the poacher, have been neglected in previous work. To fill the gap, we first propose a new game model GSG-I which augments GSGs with sequential movement and the vital element of real-time information. Second, we design a novel deep reinforcement learning-based algorithm, DeDOL, to compute a patrolling strategy that adapts to the real-time information against a best-responding attacker. DeDOL is built upon the double oracle framework and the policy-space response oracle, solving a restricted game and iteratively adding best response strategies to it through training deep Q-networks. Exploring the game structure, DeDOL uses domain-specific heuristic strategies as initial strategies and constructs several local modes for efficient and parallelized training. To our knowledge, this is the first attempt to use Deep Q-Learning for security games.

PDF Details

IROS Conference 2017 Conference Paper

Model-less feedback control for soft manipulators

Yusong Jin
Yufei Wang
Xiaotong Chen
Zhanchi Wang
Xinghua Liu
Hao Jiang 0015
Xiaoping Chen

Soft manipulators have been a rising focus of soft robotics research. Taking advantage of soft materials and flexible, continuous movements, they have promising applicable prospect. However, their highly internal nonlinearity and unpredictable deformation caused by environmental effects make it difficult to build an exact model for control. In this work, we propose a generalized controller for soft manipulators using an estimated Jacobian-based model derived from structural analysis. The model can be simplified from reasonable assumptions of manipulator structure, and updated to balance conformity to reality and stability. In prototype experiments on an 3D multi-segment soft manipulator, the control method exhibits accuracy as well as adaptability to self gravity and external loads.

Details

TIST Journal 2015 Journal Article

A Real-Time Hand Posture Recognition System Using Deep Neural Networks

Ao Tang
Ke Lu
Yufei Wang
Jie Huang
Houqiang Li

Hand posture recognition (HPR) is quite a challenging task, due to both the difficulty in detecting and tracking hands with normal cameras and the limitations of traditional manually selected features. In this article, we propose a two-stage HPR system for Sign Language Recognition using a Kinect sensor. In the first stage, we propose an effective algorithm to implement hand detection and tracking. The algorithm incorporates both color and depth information, without specific requirements on uniform-colored or stable background. It can handle the situations in which hands are very close to other parts of the body or hands are not the nearest objects to the camera and allows for occlusion of hands caused by faces or other hands. In the second stage, we apply deep neural networks (DNNs) to automatically learn features from hand posture images that are insensitive to movement, scaling, and rotation. Experiments verify that the proposed system works quickly and accurately and achieves a recognition accuracy as high as 98.12%.

Details DOI