Author name cluster

Zihan Zhou

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.

17 papers

2 author rows

JBHI Journal 2026 Journal Article

USRMamba: Adaptive Routing-Guided State Space Model for Ultrasound Super-Resolution

Tao Wang
Zihan Zhou
Chufeng Jin
Tianyi Liu
Baike Shi
Guangquan Zhou
Rongjun Ge
Jean-Louis Coatrieux

In ultrasound (US) imaging, resolution degradation caused by the acoustic diffraction limit and transducer array density can significantly reduce image quality, which have negative impacts on clinical diagnosis. Super-resolution (SR) reconstruction is a more flexible and cost-effective measure compared to system upgrades. However, the complexity and diversity of tissue acoustic properties make it difficult to establish a unified model for US image SR reconstruction. In this context, this paper pioneers a revolutionary Mamba-based single US image SR method, referred to as USRMamba. Firstly, a simple and efficient Enhanced Transform Combine Module (ETCM) is designed for shallow feature extraction, which achieves multi-scale decoupling through Laplacian sharpening and wavelet transform to solve the interference of high-frequency information loss and speckle noise in US images; More importantly, an Adaptive Top-k Prompt Module (ATPM) is proposed, whose core is to generate semantic prompts through an adaptive routing-guided strategy to suppress the interference of fuzzy region labels caused by attenuation on detail reconstruction. In addition, a Frequency Channel Attention Module (FCAM) is developed, forming a modeling strategy of “frequency-spatial domain reconstruction” in parallel with ATPM, further optimizing the fidelity for US images SR reconstruction. Qualitative and quantitative experiments demonstrate that USRMamba exhibits superior performance on several US datasets. Especially with scale factor ×2, the proposed method has an average PSNR 1. 31dB higher than state-of-the-art (SOTA) methods.

Details DOI

NeurIPS Conference 2025 Conference Paper

Characterization and Learning of Causal Graphs from Hard Interventions

Zihan Zhou
Muhammad Qasim Elahi
Murat Kocaoglu

A fundamental challenge in the empirical sciences involves uncovering causal structure through observation and experimentation. Causal discovery entails linking the conditional independence (CI) invariances in observational data to their corresponding graphical constraints via d-separation. In this paper, we consider a general setting where we have access to data from multiple experimental distributions resulting from hard interventions, as well as potentially from an observational distribution. By comparing different interventional distributions, we propose a set of graphical constraints that are fundamentally linked to Pearl's do-calculus within the framework of hard interventions. These graphical constraints associate each graphical structure with a set of interventional distributions that are consistent with the rules of do-calculus. We characterize the interventional equivalence class of causal graphs with latent variables and introduce a graphical representation that can be used to determine whether two causal graphs are interventionally equivalent, i. e. , whether they are associated with the same family of hard interventional distributions, where the elements of the family are indistinguishable using the invariances from do-calculus. We also propose a learning algorithm to integrate multiple datasets from hard interventions, introducing new orientation rules. The learning objective is a tuple of augmented graphs which entails a set of causal graphs. We also prove the soundness of the proposed algorithm.

PDF Details

ICML Conference 2025 Conference Paper

Flexible, Efficient, and Stable Adversarial Attacks on Machine Unlearning

Zihan Zhou
Yang Zhou 0001
Zijie Zhang 0001
Lingjuan Lyu
Da Yan 0001
Ruoming Jin
Dejing Dou

Machine unlearning (MU) aims to remove the influence of specific data points from trained models, enhancing compliance with privacy regulations. However, the vulnerability of basic MU models to malicious unlearning requests in adversarial learning environments has been largely overlooked. Existing adversarial MU attacks suffer from three key limitations: inflexibility due to pre-defined attack targets, inefficiency in handling multiple attack requests, and instability caused by non-convex loss functions. To address these challenges, we propose a Flexible, Efficient, and Stable Attack (DDPA). First, leveraging Carathéodory’s theorem, we introduce a convex polyhedral approximation to identify points in the loss landscape where convexity approximately holds, ensuring stable attack performance. Second, inspired by simplex theory and John’s theorem, we develop a regular simplex detection technique that maximizes coverage over the parameter space, improving attack flexibility and efficiency. We theoretically derive the proportion of the effective parameter space occupied by the constructed simplex. We evaluate the attack success rate of our DDPA method on real datasets against state-of-the-art machine unlearning attack methods. Our source code is available at https: //github. com/zzz0134/DDPA.

Details

NeurIPS Conference 2025 Conference Paper

FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration

Luxi Chen
Zihan Zhou
Min Zhao
Yikai Wang
Ge Zhang
Wenhao Huang
Hao Sun
Ji-Rong Wen

Generating flexible-view 3D scenes, including 360° rotation and zooming, from single images is challenging due to a lack of 3D data. To this end, we introduce FlexWorld, a novel framework that progressively constructs a persistent 3D Gaussian splatting representation by synthesizing and integrating new 3D content. To handle novel view synthesis under large camera variations, we leverage an advanced pre-trained video model fine-tuned on accurate depth-estimated training pairs. By combining geometry-aware scene integration and optimization, FlexWorld refines the scene representation, producing visually consistent 3D scenes with flexible viewpoints. Extensive experiments demonstrate the effectiveness of FlexWorld in generating high-quality novel view videos and flexible-view 3D scenes from single images, achieving superior visual quality under multiple popular metrics and datasets compared to existing state-of-the-art methods. Additionally, FlexWorld supports extrapolating from existing 3D scenes, further extending its applicability. Qualitatively, we highlight that FlexWorld can generate high-fidelity scenes that enable 360° rotations and zooming exploration. Our code is available at https: //github. com/ML-GSAI/FlexWorld.

PDF Details

AAAI Conference 2025 Conference Paper

From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach

Xilin Wang
Jia Zheng
Yuanchao Hu
Hao Zhu
Qian Yu
Zihan Zhou

In this paper, we present CAD2Program, a new method for reconstructing 3D parametric models from 2D CAD drawings. Our proposed method is inspired by recent successes in vision-language models (VLMs), and departs from traditional methods which rely on task-specific data representations and/or algorithms. Specifically, on the input side, we simply treat the 2D CAD drawing as a raster image, regardless of its original format, and encode the image with a standard ViT model. We show that such an encoding scheme achieves competitive performance against existing methods that operate on vector-graphics inputs, while imposing substantially fewer restrictions on the 2D drawings. On the output side, our method auto-regressively predicts a general-purpose language describing 3D parametric models in text form. Compared to other sequence modeling methods for CAD which use domain-specific sequence representations with fixed-size slots, our text-based representation is more flexible, and can be easily extended to arbitrary geometric entities and semantic or functional properties. Experimental results on a large-scale dataset of cabinet models demonstrate the effectiveness of our method.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

Shilin Lu
Zihan Zhou
Jiayou Lu
Yuanzhi Zhu
Adams Wai-Kin Kong

Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks during editing, posing significant challenges to copyright protection. In this work, we introduce W-Bench, the first comprehensive benchmark designed to evaluate the robustness of watermarking methods against a wide range of image editing techniques, including image regeneration, global editing, local editing, and image-to-video generation. Through extensive evaluations of eleven representative watermarking methods against prevalent editing techniques, we demonstrate that most methods fail to detect watermarks after such edits. To address this limitation, we propose VINE, a watermarking method that significantly enhances robustness against various image editing techniques while maintaining high image quality. Our approach involves two key innovations: (1) we analyze the frequency characteristics of image editing and identify that blurring distortions exhibit similar frequency properties, which allows us to use them as surrogate attacks during training to bolster watermark robustness; (2) we leverage a large-scale pretrained diffusion model SDXL-Turbo, adapting it for the watermarking task to achieve more imperceptible and robust watermark embedding. Experimental results show that our method achieves outstanding watermarking performance under various image editing techniques, outperforming existing methods in both image quality and robustness. Code is available at https://github.com/Shilin-LU/VINE

Details

AAAI Conference 2025 Conference Paper

Self-Correcting Robot Manipulation via Gaussian-Splatted Foresight

Shaohui Pan
Yong Xu
Ruotao Xu
Zihan Zhou
Si Wu
Zhuliang Yu

Language-conditioned robotic manipulation in unstructured environments presents significant challenges for intelligent robotic systems. However, due to partial observation or imprecise action prediction, failure may be unavoidable for learned policies. Moreover, operational failures can lead to the robotic arm entering an untrained state, potentially causing destructive results. Consequently, the ability to detect and self-correct failures is crucial for the development of practical robotic systems. To address this challenge, we propose a foresight-driven failure detection and self-correction module for robot manipulation. By leveraging 3D Gaussian Splatting, we represent the current scene with multiple Gaussians. Subsequently, we train a prediction network to forecast the Gaussian representation of future scenes conditioned on planned actions. Failure is detected when the predicted future significantly deviates from the real observation after action execution. In such cases, the end-effector rolls back to the previous action to avoid an untrained state. Integrating this approach with the PerACT framework, we develop a self-correcting robot manipulation policy. Evaluations on ten RLBench tasks with 166 variations demonstrate the superior performance of the proposed method, which outperforms state-of-the-art methods by 12.0% success rate on average.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

SpatialLM: Training Large Language Models for Structured Indoor Modeling

Yongsen Mao
Junhao Zhong
Chuan Fang
Jia Zheng
Rui Tang
Hao Zhu
Ping Tan
Zihan Zhou

SpatialLM is a large language model designed to process 3D point cloud data and generate structured 3D scene understanding outputs. These outputs include architectural elements like walls, doors, windows, and oriented object boxes with their semantic categories. Unlike previous methods which exploit task-specific network designs, our model adheres to the standard multimodal LLM architecture and is fine-tuned directly from open-source LLMs. To train SpatialLM, we collect a large-scale, high-quality synthetic dataset consisting of the point clouds of 12, 328 indoor scenes (54, 778 rooms) with ground-truth 3D annotations, and conduct a careful study on various modeling and training decisions. On public benchmarks, our model gives state-of-the-art performance in layout estimation and competitive results in 3D object detection. With that, we show a feasible path for enhancing the spatial understanding capabilities of modern LLMs for applications in augmented reality, embodied robotics, and more.

PDF Details

NeurIPS Conference 2025 Conference Paper

TEMPO: Temporal Multi-scale Autoregressive Generation of Protein Conformational Ensembles

Yaoyao Xu
Di Wang
Zihan Zhou
Tianshu Yu
Mingchen Chen

Understanding the dynamic behavior of proteins is critical to elucidating their functional mechanisms, yet generating realistic, temporally coherent trajectories of protein ensembles remains a significant challenge. In this work, we introduce a novel hierarchical autoregressive framework for modeling protein dynamics that leverages the intrinsic multi-scale organization of molecular motions. Unlike existing methods that focus on generating static conformational ensembles or treat dynamic sampling as an independent process, our approach characterizes protein dynamics as a Markovian process. The framework employs a two-scale architecture: a low-resolution model captures slow, collective motions driving major conformational transitions, while a high-resolution model generates detailed local fluctuations conditioned on these large-scale movements. This hierarchical design ensures that the causal dependencies inherent in protein dynamics are preserved, enabling the generation of temporally coherent and physically realistic trajectories. By bridging high-level biophysical principles with state-of-the-art generative modeling, our approach provides an efficient framework for simulating protein dynamics that balances computational efficiency with physical accuracy.

PDF Details

NeurIPS Conference 2024 Conference Paper

Sample Efficient Bayesian Learning of Causal Graphs from Interventions

Zihan Zhou
Muhammad Qasim Elahi
Murat Kocaoglu

Causal discovery is a fundamental problem with applications spanning various areas in science and engineering. It is well understood that solely using observational data, one can only orient the causal graph up to its Markov equivalence class, necessitating interventional data to learn the complete causal graph. Most works in the literature design causal discovery policies with perfect interventions, i. e. , they have access to infinite interventional samples. This study considers a Bayesian approach for learning causal graphs with limited interventional samples, mirroring real-world scenarios where such samples are usually costly to obtain. By leveraging the recent result of Wienöbst et al. [2023] on uniform DAG sampling in polynomial time, we can efficiently enumerate all the cut configurations and their corresponding interventional distributions of a target set, and further track their posteriors. Given any number of interventional samples, our proposed algorithm randomly intervenes on a set of target vertices that cut all the edges in the graph and returns a causal graph according to the posterior of each target set. When the number of interventional samples is large enough, we show theoretically that our proposed algorithm will return the true causal graph with high probability. We compare our algorithm against various baseline methods on simulated datasets, demonstrating its superior accuracy measured by the structural Hamming distance between the learned DAG and the ground truth. Additionally, we present a case study showing how this algorithm could be modified to answer more general causal questions without learning the whole graph. As an example, we illustrate that our method can be used to estimate the causal effect of a variable that cannot be intervened.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward

Zihan Zhou
Animesh Garg

We propose Structured Exploration with Achievements (SEA), a multi-stage reinforcement learning algorithm designed for achievement-based environments, a particular type of environment with an internal achievement set. SEA first uses offline data to learn a representation of the known achievements with a determinant loss function, then recovers the dependency graph of the learned achievements with a heuristic algorithm, and finally interacts with the environment online to learn policies that master known achievements and explore new ones with a controller built with the recovered dependency graph. We empirically demonstrate that SEA can recover the achievement structure accurately and improve exploration in hard domains such as Crafter that are procedurally generated with high-dimensional observations like images.

Details

NeurIPS Conference 2022 Conference Paper

Multivariate Time-Series Forecasting with Temporal Polynomial Graph Neural Networks

Yijing Liu
Qinxian Liu
Jian-Wei Zhang
Haozhe Feng
Zhongwei Wang
Zihan Zhou
Wei Chen

Modeling multivariate time series (MTS) is critical in modern intelligent systems. The accurate forecast of MTS data is still challenging due to the complicated latent variable correlation. Recent works apply the Graph Neural Networks (GNNs) to the task, with the basic idea of representing the correlation as a static graph. However, predicting with a static graph causes significant bias because the correlation is time-varying in the real-world MTS data. Besides, there is no gap analysis between the actual correlation and the learned one in their works to validate the effectiveness. This paper proposes a temporal polynomial graph neural network (TPGNN) for accurate MTS forecasting, which represents the dynamic variable correlation as a temporal matrix polynomial in two steps. First, we capture the overall correlation with a static matrix basis. Then, we use a set of time-varying coefficients and the matrix basis to construct a matrix polynomial for each time step. The constructed result empirically captures the precise dynamic correlation of six synthetic MTS datasets generated by a non-repeating random walk model. Moreover, the theoretical analysis shows that TPGNN can achieve perfect approximation under a commutative condition. We conduct extensive experiments on two traffic datasets with prior structure and four benchmark datasets. The results indicate that TPGNN achieves the state-of-the-art on both short-term and long-term MTS forecastings.

PDF Details

YNIMG Journal 2022 Journal Article

Single-shot multi-parametric mapping based on multiple overlapping-echo detachment (MOLED) imaging

Lingceng Ma
Jian Wu
Qinqin Yang
Zihan Zhou
Hongjian He
Jianfeng Bao
Lijun Bao
Xiaoyin Wang

Multi-parametric quantitative magnetic resonance imaging (mqMRI) allows the characterization of multiple tissue properties non-invasively and has shown great potential to enhance the sensitivity of MRI measurements. However, real-time mqMRI during dynamic physiological processes or general motions remains challenging. To overcome this bottleneck, we propose a novel mqMRI technique based on multiple overlapping-echo detachment (MOLED) imaging, termed MQMOLED, to enable mqMRI in a single shot. In the data acquisition of MQMOLED, multiple MR echo signals with different multi-parametric weightings and phase modulations are generated and acquired in the same k-space. The k-space data is Fourier transformed and fed into a well-trained neural network for the reconstruction of multi-parametric maps. We demonstrated the accuracy and repeatability of MQMOLED in simultaneous mapping apparent proton density (APD) and any two parameters among T2, T2*, and apparent diffusion coefficient (ADC) in 130–170 ms. The abundant information delivered by the multiple overlapping-echo signals in MQMOLED makes the technique potentially robust to system imperfections, such as inhomogeneity of static magnetic field or radiofrequency field. Benefitting from the single-shot feature, MQMOLED exhibits a strong motion tolerance to the continuous movements of subjects. For the first time, it captured the synchronous changes of ADC, T2, and T1-weighted APD in contrast-enhanced perfusion imaging on patients with brain tumors, providing additional information about vascular density to the hemodynamic parametric maps. We expect that MQMOLED would promote the development of mqMRI technology and greatly benefit the applications of mqMRI, including therapeutics and analysis of metabolic/functional processes.

Details DOI

YNICL Journal 2021 Journal Article

Aberrant rich club organization in patients with obsessive-compulsive disorder and their unaffected first-degree relatives

Ziwen Peng
Xinyi Yang
Chuanyong Xu
Xiangshu Wu
Qiong Yang
Zhen Wei
Zihan Zhou
Tom Verguts

Recent studies suggested that the rich club organization promoting global brain communication and integration of information, may be abnormally increased in obsessive-compulsive disorder (OCD). However, the structural and functional basis of this organization is still not very clear. Given the heritability of OCD, as suggested by previous family-based studies, we hypothesize that aberrant rich club organization may be a trait marker for OCD. In the present study, 32 patients with OCD, 30 unaffected first-degree relatives (FDR) and 32 healthy controls (HC) underwent diffusion tensor imaging (DTI) and functional magnetic resonance imaging (fMRI). We examined the structural rich club organization and its interrelationship with functional coupling. Our results showed that rich club and peripheral connection strength in patients with OCD was lower than in HC, while it was intermediate in FDR. Finally, the coupling between structural and functional connections of the rich club, was decreased in FDR but not in OCD relative to HC, which suggests a buffering mechanism of brain functions in FDR. Overall, our findings suggest that alteration of the rich club organization may reflect a vulnerability biomarker for OCD, possibly buffered by structural and functional coupling of the rich club.

Details DOI

IJCAI Conference 2021 Conference Paper

Temporal Induced Self-Play for Stochastic Bayesian Games

Weizhe Chen
Zihan Zhou
Yi Wu
Fei Fang

One practical requirement in solving dynamic games is to ensure that the players play well from any decision point onward. To satisfy this requirement, existing efforts focus on equilibrium refinement, but the scalability and applicability of existing techniques are limited. In this paper, we propose Temporal-Induced Self-Play (TISP), a novel reinforcement learning-based framework to find strategies with decent performances from any decision point onward. TISP uses belief-space representation, backward induction, policy learning, and non-parametric approximation. Building upon TISP, we design a policy-gradient-based algorithm TISP-PG. We prove that TISP-based algorithms can find approximate Perfect Bayesian Equilibrium in zero-sum one-sided stochastic Bayesian games with finite horizon. We test TISP-based algorithms in various games, including finitely repeated security games and a grid-world game. The results show that TISP-PG is more scalable than existing mathematical programming-based methods and significantly outperforms other learning-based methods.

PDF Details DOI

YNIMG Journal 2020 Journal Article

Evaluation of the diffusion MRI white matter tract integrity model using myelin histology and Monte-Carlo simulations

Zihan Zhou
Qiqi Tong
Lei Zhang
Qiuping Ding
Hui Lu
Laura E. Jonkman
Junye Yao
Hongjian He

Quantitative evaluation of brain myelination has drawn considerable attention. Conventional diffusion-based magnetic resonance imaging models, including diffusion tensor imaging and diffusion kurtosis imaging (DKI), 1 1 AD: Axial diffusivity; AK: Axial kurtosis; AVF: Axonal volume fraction; AWF: Axonal Water Fraction; DTI: Diffusion Tensor Imaging; DKI: Diffusion Kurtosis Imaging; dMRI: Diffusion magnetic resonance imaging; TE: Echo time; FOV: Field-of-view; FA: Fractional anisotropy; LFB: Luxor fast blue; MD: Mean diffusivity; MK: Mean kurtosis; MRI: Magnetic resonance imaging; MVF: Myelin volume fraction; PLP: Proteolipid protein; RESOLVE: Readout segmentation of long variable echo train; RD: Radial diffusivity; RK: Radial kurtosis; TR: Repetition time; ROI: Region-of-interest; WM: White matter; WMTI: White Matter Tract Integrity. have been used to infer the microstructure and its changes in neurological diseases. White matter tract integrity (WMTI) was proposed as a biophysical model to relate the DKI-derived metrics to the underlying microstructure. Although the model has been validated on ex vivo animal brains, it was not well evaluated with ex vivo human brains. In this study, histological samples (namely corpus callosum) from postmortem human brains have been investigated based on WMTI analyses on a clinical 3T scanner and comparisons with gold standard myelin staining in proteolipid protein and Luxol fast blue. In addition, Monte Carlo simulations were conducted to link changes from ex vivo to in vivo conditions based on the microscale parameters of water diffusivity and permeability. The results show that WMTI metrics, including axonal water fraction AWF, radial extra-axonal diffusivity D e ⊥, and intra-axonal diffusivity Da were needed to characterize myelin content alterations. Thus, WMTI model metrics are shown to be promising candidates as sensitive biomarkers of demyelination.

Details DOI

IJCAI Conference 2017 Conference Paper

Learning to Read Irregular Text with Attention Mechanisms

Xiao Yang
Dafang He
Zihan Zhou
Daniel Kifer
C. Lee Giles

We present a robust end-to-end neural-based model to attentively recognize text in natural images. Particularly, we focus on accurately identifying irregular (perspectively distorted or curved) text, which has not been well addressed in the previous literature. Previous research on text reading often works with regular (horizontal and frontal) text and does not adequately generalize to processing text with perspective distortion or curving effects. Our work proposes to overcome this difficulty by introducing two learning components: (1) an auxiliary dense character detection task that helps to learn text specific visual patterns, (2) an alignment loss that provides guidance to the training of an attention model. We show with experiments that these two components are crucial for achieving fast convergence and high classification accuracy for irregular text recognition. Our model outperforms previous work on two irregular-text datasets: SVT-Perspective and CUTE80, and is also highly-competitive on several regular-text datasets containing primarily horizontal and frontal text.

PDF Details