Author name cluster

Xinyu 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.

14 papers

2 author rows

AAAI Conference 2026 Conference Paper

Seeing Is Believing: Rich-Context Hallucination Detection for MLLMs via Backward Visual Grounding

Pinxue Guo
Chongruo Wu
Xinyu Zhou
Lingyi Hong
Zhaoyu Chen
Jinglun Li
Kaixun Jiang
Sen-Ching Samson Cheung

Multimodal Large Language Models (MLLMs) have unlocked powerful cross-modal capabilities, but still significantly suffer from hallucinations. As such, accurate detection of hallucinations in MLLMs is imperative for ensuring their reliability in practical applications. To this end, guided by the principle of “Seeing is Believing”, we introduce VBackChecker, a novel reference-free hallucination detection framework that verifies the consistency of MLLM-generated responses with visual inputs, by leveraging a pixel-level Grounding LLM equipped with reasoning and referring segmentation capabilities. This referencefree framework not only effectively handles rich-context scenarios, but also offers interpretability. To facilitate this, an innovative pipeline is accordingly designed for generating instruction-tuning data (R-Instruct), featuring richcontext descriptions, grounding masks, and hard negative samples. We further establish R 2 -HalBench, a new hallucination benchmark for MLLMs, which, unlike previous benchmarks, encompasses real-world, rich-context descriptions from 18 MLLMs with high-quality annotations, spanning diverse object-, attribute-, and relationship-level details. VBackChecker outperforms prior complex frameworks and achieves state-of-the-art performance on R^2 -HalBench, even rivaling GPT-4o’s capabilities in hallucination detection. It also surpasses prior methods in the pixel-level grounding task, achieving over a 10% improvement.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Text-based Aerial-Ground Person Retrieval

Xinyu Zhou
Yu Wu
Jiayao Ma
Wenhao Wang
Min Cao
Mang Ye

This work introduces Text-based Aerial-Ground Person Retrieval (TAG-PR), which aims to retrieve person images from heterogeneous aerial and ground views with textual descriptions. Unlike traditional Text-based Person Retrieval (T-PR), which focuses solely on ground-view images, TAG-PR introduces greater practical significance and presents unique challenges due to the large viewpoint discrepancy across images. To support this task, we contribute: (1) TAG-PEDES dataset, constructed from public benchmarks with automatically generated textual descriptions, enhanced by a diversified text generation paradigm to ensure robustness under view heterogeneity; and (2) TAG-CLIP, a novel retrieval framework that addresses view heterogeneity through a hierarchically-routed mixture of experts module to learn view-specific and view-agnostic features and a viewpoint decoupling strategy to decouple view-specific features for better cross-modal alignment. We evaluate the effectiveness of TAG-CLIP on both the proposed TAG-PEDES and existing T-PR benchmarks.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Boosting Adversarial Transferability with Spatial Adversarial Alignment

Zhaoyu Chen
HaiJing Guo
Kaixun Jiang
Jiyuan Fu
Xinyu Zhou
Dingkang Yang
Hao Tang
Bo Li

Deep neural networks are vulnerable to adversarial examples that exhibit transferability across various models. Numerous approaches are proposed to enhance the transferability of adversarial examples, including advanced optimization, data augmentation, and model modifications. However, these methods still show limited transferability, partiovovocularly in cross-architecture scenarios, such as from CNN to ViT. To achieve high transferability, we propose a technique termed Spatial Adversarial Alignment (SAA), which employs an alignment loss and leverages a witness model to fine-tune the surrogate model. Specifically, SAA consists of two key parts: spatial-aware alignment and adversarial-aware alignment. First, we minimize the divergences of features between the two models in both global and local regions, facilitating spatial alignment. Second, we introduce a self-adversarial strategy that leverages adversarial examples to impose further constraints, aligning features from an adversarial perspective. Through this alignment, the surrogate model is trained to concentrate on the common features extracted by the witness model. This facilitates adversarial attacks on these shared features, thereby yielding perturbations that exhibit enhanced transferability. Extensive experiments on various architectures on ImageNet show that aligned surrogate models based on SAA can provide higher transferable adversarial examples, especially in cross-architecture attacks.

PDF Details

NeurIPS Conference 2025 Conference Paper

Dense Metric Depth Estimation via Event-based Differential Focus Volume Prompting

Boyu Li
Peiqi Duan
Zhaojun Huang
Xinyu Zhou
Yifei Xia
Boxin Shi

Dense metric depth estimation has witnessed great developments in recent years. While single-image-based methods have demonstrated commendable performance in certain circumstances, they may encounter challenges regarding scale ambiguities and visual illusions in real world. Traditional depth-from-focus methods are constrained by low sampling rates during data acquisition. In this paper, we introduce a novel approach to enhance dense metric depth estimation by fusing events with image foundation models via a prompting approach. Specifically, we build Event-based Differential Focus Volumes (EDFV) using events triggered through focus sweeping, which are subsequently transformed into sparse metric depth maps. These maps are then utilized for prompting dense depth estimation via our proposed Event-based Depth Prompting Network. We further construct synthetic and real-captured datasets to facilitate the training and evaluation of both frame-based and event-based methods. Quantitative and qualitative results, including both in-domain and zero-shot experiments, demonstrate the superior performance of our method compared to existing approaches. Code and data will be available at https: //github. com/liboyu02/EDFV/.

PDF Details

NeurIPS Conference 2025 Conference Paper

Dynamic Semantic-Aware Correlation Modeling for UAV Tracking

Xinyu Zhou
Tongxin Pan
Lingyi Hong
Pinxue Guo
HaiJing Guo
Zhaoyu Chen
Kaixun Jiang
Wenqiang Zhang

UAV tracking can be widely applied in scenarios such as disaster rescue, environmental monitoring, and logistics transportation. However, existing UAV tracking methods predominantly emphasize speed and lack exploration in semantic awareness, which hinders the search region from extracting accurate localization information from the template. The limitation results in suboptimal performance under typical UAV tracking challenges such as camera motion, fast motion, and low resolution, etc. To address this issue, we propose a dynamic semantic aware correlation modeling tracking framework. The core of our framework is a Dynamic Semantic Relevance Generator, which, in combination with the correlation map from the Transformer, explore semantic relevance. The approach enhances the search region's ability to extract important information from the template, improving accuracy and robustness under the aforementioned challenges. Additionally, to enhance the tracking speed, we design a pruning method for the proposed framework. Therefore, we present multiple model variants that achieve trade-offs between speed and accuracy, enabling flexible deployment according to the available computational resources. Experimental results validate the effectiveness of our method, achieving competitive performance on multiple UAV tracking datasets.

PDF Details

NeurIPS Conference 2025 Conference Paper

MoBA: Mixture of Block Attention for Long-Context LLMs

Enzhe Lu
Zhejun Jiang
Jingyuan Liu
Yulun Du
Tao Jiang
Chao Hong
Shaowei Liu
Weiran He

Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI). However, the quadratic increase in computational complexity inherent in traditional attention mechanisms presents a prohibitive overhead. Existing approaches either impose strongly biased structures, such as sink or window attention which are task-specific, or radically modify the attention mechanism into linear approximations, whose performance in complex reasoning tasks remains inadequately explored. In this work, we propose a solution that adheres to the ``less structure'' principle, allowing the model to determine where to attend autonomously, rather than introducing predefined biases. We introduce Mixture of Block Attention (MoBA), an innovative approach that applies the principles of Mixture of Experts (MoE) to the attention mechanism. This novel architecture demonstrates superior performance on long-context tasks while offering a key advantage: the ability to seamlessly transition between full and sparse attention, enhancing efficiency without the risk of compromising performance. MoBA has already been deployed to handle actual production workloads with long-context requirements, demonstrating significant advancements in efficient attention computation for LLMs. Our code is available at https: //github. com/MoonshotAI/MoBA.

PDF Details

NeurIPS Conference 2025 Conference Paper

MoonCast: High-Quality Zero-Shot Podcast Generation

Zeqian Ju
Dongchao Yang
Shen Kai
Yichong Leng
Zhengtao Wang
Songxiang Liu
Xinyu Zhou
Tao Qin

Recent advances in text-to-speech synthesis have achieved notable success in generating high-quality short utterances for individual speakers. However, these systems still face challenges when extending their capabilities to long, multi-speaker, and spontaneous dialogues, typical of real-world scenarios such as podcasts. These limitations arise from two primary challenges: 1) long speech: podcasts typically span several minutes, exceeding the upper limit of most existing work; 2) spontaneity: podcasts are marked by their spontaneous, oral nature, which sharply contrasts with formal, written contexts; existing works often fall short in capturing this spontaneity. In this paper, we propose MoonCast, a solution for high-quality zero-shot podcast generation, aiming to synthesize spontaneous podcast-style speech from text-only sources (e. g. , stories, technical reports, news in TXT, PDF, or Web URL formats) using the voices of unseen speakers. To enable long audio generation, we employ a language model with parameter, data, and context scaling to process sequences in an innovative format designed for modeling entire multi-speaker, multi-turn speech interactions. To enhance spontaneity, we observe that ASR transcripts capture spontaneous speech details (e. g. , filler words indicating hesitations, and specific punctuation and spaces reflecting breathing pauses), suggesting that these transcripts can serve as a partial indicator of speech spontaneity. Building upon this assumption, we utilize a script generation module to generate scripts incorporating these spontaneous elements. Experiments show MoonCast outperforms baselines, with notable improvements in contextual coherence and spontaneity.

PDF Details

ICML Conference 2025 Conference Paper

Private Model Personalization Revisited

Conor Snedeker
Xinyu Zhou
Raef Bassily

We study model personalization under user-level differential privacy (DP) in the shared representation framework. In this problem, there are $n$ users whose data is statistically heterogeneous, and their optimal parameters share an unknown embedding $U^* \in\mathbb{R}^{d\times k}$ that maps the user parameters in $\mathbb{R}^d$ to low-dimensional representations in $\mathbb{R}^k$, where $k\ll d$. Our goal is to privately recover the shared embedding and the local low-dimensional representations with small excess risk in the federated setting. We propose a private, efficient federated learning algorithm to learn the shared embedding based on the FedRep algorithm in (Collins et al. , 2021). Unlike (Collins et al. , 2021), our algorithm satisfies differential privacy, and our results hold for the case of noisy labels. In contrast to prior work on private model personalization (Jain et al. , 2021), our utility guarantees hold under a larger class of users’ distributions (sub-Gaussian instead of Gaussian distributions). Additionally, in natural parameter regimes, we improve the privacy error term in (Jain et al. , 2021) by a factor of $\widetilde{O}(dk)$. Next, we consider the binary classification setting. We present an information-theoretic construction to privately learn the shared embedding and derive a margin-based accuracy guarantee that is independent of $d$. Our method utilizes the Johnson-Lindenstrauss transform to reduce the effective dimensions of the shared embedding and the users’ data. This result shows that dimension-independent risk bounds are possible in this setting under a margin loss.

Details

NeurIPS Conference 2024 Conference Paper

DeTrack: In-model Latent Denoising Learning for Visual Object Tracking

Xinyu Zhou
Jinglun Li
Lingyi Hong
Kaixun Jiang
Pinxue Guo
Weifeng Ge
Wenqiang Zhang

Previous visual object tracking methods employ image-feature regression models or coordinate autoregression models for bounding box prediction. Image-feature regression methods heavily depend on matching results and do not utilize positional prior, while the autoregressive approach can only be trained using bounding boxes available in the training set, potentially resulting in suboptimal performance during testing with unseen data. Inspired by the diffusion model, denoising learning enhances the model’s robustness to unseen data. Therefore, We introduce noise to bounding boxes, generating noisy boxes for training, thus enhancing model robustness on testing data. We propose a new paradigm to formulate the visual object tracking problem as a denoising learning process. However, tracking algorithms are usually asked to run in real-time, directly applying the diffusion model to object tracking would severely impair tracking speed. Therefore, we decompose the denoising learning process into every denoising block within a model, not by running the model multiple times, and thus we summarize the proposed paradigm as an in-model latent denoising learning process. Specifically, we propose a denoising Vision Transformer (ViT), which is composed of multiple denoising blocks. In the denoising block, template and search embeddings are projected into every denoising block as conditions. A denoising block is responsible for removing the noise in a predicted bounding box, and multiple stacked denoising blocks cooperate to accomplish the whole denoising process. Subsequently, weutilize image features and trajectory information to refine the denoised bounding box. Besides, we also utilize trajectory memory and visual memory to improve tracking stability. Experimental results validate the effectiveness of our approach, achieving competitive performance on several challenging datasets. The proposed in-model latent denoising tracker achieve real-time speed, rendering denoising learning applicable in the visual object tracking community.

PDF Details DOI

ICML Conference 2024 Conference Paper

Differentially Private Worst-group Risk Minimization

Xinyu Zhou
Raef Bassily

We initiate a systematic study of worst-group risk minimization under $(\epsilon, \delta)$-differential privacy (DP). The goal is to privately find a model that approximately minimizes the maximal risk across $p$ sub-populations (groups) with different distributions, where each group distribution is accessed via a sample oracle. We first present a new algorithm that achieves excess worst-group population risk of $\tilde{O}(\frac{p\sqrt{d}}{K\epsilon} + \sqrt{\frac{p}{K}})$, where $K$ is the total number of samples drawn from all groups and $d$ is the problem dimension. Our rate is nearly optimal when each distribution is observed via a fixed-size dataset of size $K/p$. Our result is based on a new stability-based analysis for the generalization error. In particular, we show that $\Delta$-uniform argument stability implies $\tilde{O}(\Delta + \frac{1}{\sqrt{n}})$ generalization error w. r. t. the worst-group risk, where $n$ is the number of samples drawn from each sample oracle. Next, we propose an algorithmic framework for worst-group population risk minimization using any DP online convex optimization algorithm as a subroutine. Hence, we give another excess risk bound of $\tilde{O}\left( \sqrt{\frac{d^{1/2}}{\epsilon K}} +\sqrt{\frac{p}{K\epsilon^2}} + \sqrt{\frac{p}{K}} \right)$. Assuming the typical setting of $\epsilon=\Theta(1)$, this bound is more favorable than our first bound in a certain range of $p$ as a function of $K$ and $d$. Finally, we study differentially private worst-group empirical risk minimization in the offline setting, where each group distribution is observed by a fixed-size dataset. We present a new algorithm with nearly optimal excess risk of $\tilde{O}(\frac{p\sqrt{d}}{K\epsilon})$.

Details

EAAI Journal 2023 Journal Article

Assessing project portfolio risk via an enhanced GA-BPNN combined with PCA

Libiao Bai
Chaopeng Song
Xinyu Zhou
Yuanyuan Tian
Lan Wei

Assessing project portfolio risk (PPR) is essential for organizations to grasp the overall risk levels of project portfolios (PPs) and realize PPR mitigation. However, current research is inadequate to effectively assess PPR, which brings challenges to managing PPR. In this context, the purpose of this study is to develop a PPR assessment model via an enhanced backpropagation neural network (BPNN). First, PPR assessment criteria considering project interdependencies are determined. Second, fuzzy logic is used to obtain original data for assessment criteria. Principal component analysis (PCA) is then employed to reduce the dimensionality of assessment criteria and derive the input and output of BPNN. Third, an improved genetic algorithm (IGA) is designed to optimize the initial weights and thresholds of BPNN. On this basis, the PCA-IGA-BPNN assessment model is constructed, followed by training and testing, possessing a test accuracy of 98. 6%. Finally, comparison experiments are conducted from both internal and external perspectives. For internal comparison, the proposed model yields less mean absolute percentage error (MAPE), mean square error (MSE), and root mean square error (RMSE) than PCA-GA-BPNN, IGA-BPNN, PCA-BPNN and BPNN and offers the largest convergence speed ( γ ). As for external comparison, the presented model produces lower MAPE, MSE, and RMSE than Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbor (KNN) and has the largest coefficient of determination ( R 2 ). Results indicate that the established model performs more satisfactorily in assessing PPR. This research enriches PPR assessment methods and provides managers with a useful tool to evaluate PPR.

Details DOI

NeurIPS Conference 2023 Conference Paper

Reading Relevant Feature from Global Representation Memory for Visual Object Tracking

Xinyu Zhou
Pinxue Guo
Lingyi Hong
Jinglun Li
Wei Zhang
Weifeng Ge
Wenqiang Zhang

Reference features from a template or historical frames are crucial for visual object tracking. Prior works utilize all features from a fixed template or memory for visual object tracking. However, due to the dynamic nature of videos, the required reference historical information for different search regions at different time steps is also inconsistent. Therefore, using all features in the template and memory can lead to redundancy and impair tracking performance. To alleviate this issue, we propose a novel tracking paradigm, consisting of a relevance attention mechanism and a global representation memory, which can adaptively assist the search region in selecting the most relevant historical information from reference features. Specifically, the proposed relevance attention mechanism in this work differs from previous approaches in that it can dynamically choose and build the optimal global representation memory for the current frame by accessing cross-frame information globally. Moreover, it can flexibly read the relevant historical information from the constructed memory to reduce redundancy and counteract the negative effects of harmful information. Extensive experiments validate the effectiveness of the proposed method, achieving competitive performance on five challenging datasets with 71 FPS.

PDF Details

NeurIPS Conference 2022 Conference Paper

Task-level Differentially Private Meta Learning

Xinyu Zhou
Raef Bassily

We study the problem of meta-learning with task-level differential privacy. Meta-learning has received increasing attention recently because of its ability to enable fast generalization to new task with small number of data points. However, the training process of meta learning likely involves exchange of task specific information, which may pose privacy risk especially in some privacy-sensitive applications. Therefore, it is important to provide strong privacy guarantees such that the learning process will not reveal any task sensitive information. To this end, existing works have proposed meta learning algorithms with record-level differential privacy, which is not sufficient in many scenarios since it does not protect the aggregated statistics based on the task dataset as a whole. Moreover, the utility guarantees in the prior work are based on assuming that the loss function satisfies both smoothness and quadratic growth conditions, which do not necessarily hold in practice. To address these issues, we propose meta learning algorithms with task-level differential privacy; that is, our algorithms protect the privacy of the entire dataset for each task. In the case when a single meta model is trained, we give both privacy and utility guarantees assuming only that the loss is convex and Lipschitz. Moreover, we propose a new private clustering-based meta-learning algorithm that enables private meta learning of multiple meta models. This can provide significant accuracy gains over the single meta model paradigm, especially when the tasks distribution cannot be well represented by a single meta model. Finally, we conduct several experiments demonstrating the effectiveness of our proposed algorithms.

PDF Details

AAMAS Conference 2021 Conference Paper

RPPLNS: Pay-per-last-N-shares with a Randomised Twist

Philip Lazos
Francisco J. Marmolejo Cossío
Xinyu Zhou
Jonathan Katz

“Pay-per-last-𝑁-shares” (PPLNS) is one of the most common payout strategies used by mining pools in Proof-of-Work (PoW) cryptocurrencies such as Bitcoin. As with any payment scheme, it is imperative to study issues of incentive compatibility of miners within the pool. For PPLNS this question has only been partially answered; we know that reasonably-sized miners within a PPLNS pool prefer following the pool protocol over employing specific deviations. In this paper, we present a novel modification to PPLNS where we randomise the protocol in a natural way. We call our protocol “Randomised pay-per-last-𝑁-shares” (RPPLNS), and note that the randomised structure of the protocol greatly simplifies the study of its incentive compatibility. We show that RPPLNS maintains the strengths of PPLNS (i. e. , fairness, variance reduction, and resistance to pool hopping), while also being robust against a richer class of strategic mining than what has been shown for PPLNS.

PDF