arXiv subjects

Xiaodong Wang

Publications and source records attributed to Xiaodong Wang.

At least 55 records · Page 3Linked to original sources

arXiv2026

Spectral Compressive Imaging via Chromaticity-Intensity Decomposition

In coded aperture snapshot spectral imaging (CASSI), the captured measurement entangles spatial and spectral information, posing a severely ill-posed inverse problem for hyperspectral images (HSIs) reconstruction. Moreover, the captured radiance inherently depends on scene illumination, making it difficult to recover the intrinsic spectral reflectance that remains invariant to lighting conditions. To address these challenges, we propose a chromaticity-intensity decomposition framework, which disentangles an HSI into a spatially smooth intensity map and a spectrally variant chromaticity cube. The chromaticity encodes lighting-invariant reflectance, enriched with high-frequency spatial details and local spectral sparsity. Building on this decomposition, we develop CIDNet, a Chromaticity-Intensity Decomposition unfolding network within a dual-camera CASSI system. CIDNet integrates a hybrid spatial-spectral Transformer tailored to reconstruct fine-grained and sparse spectral chromaticity and a degradation-aware, spatially-adaptive noise estimation module that captures anisotropic noise across iterative stages. Extensive experiments on both synthetic and real-world CASSI datasets demonstrate that our method achieves superior performance in both spectral and chromaticity fidelity. Code and models will be publicly available.

cs.CV↗

arXiv2026

Iconix: Controlling Semantics and Style in Progressive Icon Grids Generation

Visual communication often needs stylistically consistent icons that span concrete and abstract meanings, for use in diverse contexts. We present Iconix, a human-AI co-creative system that organizes icon generation along two axes: semantic richness (what is depicted) and visual complexity (how much detail). Given a user-specified concept, Iconix constructs a semantic scaffold of related analytical perspectives and employs chained, image-conditioned generation to produce a coherent style of exemplars. Each exemplar is then automatically distilled into a progressive sequence, from detailed and elaborate to abstract and simple. The resulting two-dimensional grid exposes a navigable space, helping designers reason jointly about figurative content and visual abstraction. A within-subjects study (N = 32) found that compared to a baseline workflow, participants produced icon grids more creatively, reported lower workload, and explored a coherent range of design variations. We discuss implications for human-machine co-creative approaches that couple semantic scaffolding with progressive simplification to support visual abstraction.

cs.HC↗

arXiv2026

ZK-HybridFL: Zero-Knowledge Proof-Enhanced Hybrid Ledger for Federated Learning

Federated learning (FL) enables collaborative model training while preserving data privacy, yet both centralized and decentralized approaches face challenges in scalability, security, and update validation. We propose ZK-HybridFL, a secure decentralized FL framework that integrates a directed acyclic graph (DAG) ledger with dedicated sidechains and zero-knowledge proofs (ZKPs) for privacy-preserving model validation. The framework uses event-driven smart contracts and an oracle-assisted sidechain to verify local model updates without exposing sensitive data. A built-in challenge mechanism efficiently detects adversarial behavior. In experiments on image classification and language modeling tasks, ZK-HybridFL achieves faster convergence, higher accuracy, lower perplexity, and reduced latency compared to Blade-FL and ChainFL. It remains robust against substantial fractions of adversarial and idle nodes, supports sub-second on-chain verification with efficient gas usage, and prevents invalid updates and orphanage-style attacks. This makes ZK-HybridFL a scalable and secure solution for decentralized FL across diverse environments.

cs.LG↗

arXiv2026

LiViBench: An Omnimodal Benchmark for Interactive Livestream Video Understanding

The development of multimodal large language models (MLLMs) has advanced general video understanding. However, existing video evaluation benchmarks primarily focus on non-interactive videos, such as movies and recordings. To fill this gap, this paper proposes the first omnimodal benchmark for interactive livestream videos, LiViBench. It features a diverse set of 24 tasks, highlighting the perceptual, reasoning, and livestream-specific challenges. To efficiently construct the dataset, we design a standardized semi-automatic annotation workflow that incorporates the human-in-the-loop at multiple stages. The workflow leverages multiple MLLMs to form a multi-agent system for comprehensive video description and uses a seed-question-driven method to construct high-quality annotations. All interactive videos in the benchmark include audio, speech, and real-time comments modalities. To enhance models' understanding of interactive videos, we design tailored two-stage instruction-tuning and propose a Video-to-Comment Retrieval (VCR) module to improve the model's ability to utilize real-time comments. Based on these advancements, we develop LiVi-LLM-7B, an MLLM with enhanced knowledge of interactive livestreams. Experiments show that our model outperforms larger open-source models with up to 72B parameters, narrows the gap with leading proprietary models on LiViBench, and achieves enhanced performance on general video benchmarks, including VideoMME, LongVideoBench, MLVU, and VideoEval-Pro.

cs.CV↗

arXiv2026

A modified Bakry-Émery $Γ_2$ criterion inequality and the monotonicity of the Tsallis entropy

The Bakry-Émery $Γ_2$ criterion inequality provides a method for establishing the logarithmic Sobolev inequality. We prove a one-parameter family of weighted Bakry-Émery $Γ_2$ criterion inequalities which in the limit case yields the improved constant due to Ji \cite{Ji24}. Furthermore, we establish a modified weighted $Γ_2$ criterion inequality which could be interpreted as a monotonicity of the Tsallis entropy under the heat flow and yields a family of sharp Sobolev inequalities.

math.DG↗

arXiv2025

3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-quality Medical Image Generation

The generation of medical images presents significant challenges due to their high-resolution and three-dimensional nature. Existing methods often yield suboptimal performance in generating high-quality 3D medical images, and there is currently no universal generative framework for medical imaging. In this paper, we introduce a 3D Medical Latent Diffusion (3D MedDiffusion) model for controllable, high-quality 3D medical image generation. 3D MedDiffusion incorporates a novel, highly efficient Patch-Volume Autoencoder that compresses medical images into latent space through patch-wise encoding and recovers back into image space through volume-wise decoding. Additionally, we design a new noise estimator to capture both local details and global structural information during diffusion denoising process. 3D MedDiffusion can generate fine-detailed, high-resolution images (up to 512x512x512) and effectively adapt to various downstream tasks as it is trained on large-scale datasets covering CT and MRI modalities and different anatomical regions (from head to leg). Experimental results demonstrate that 3D MedDiffusion surpasses state-of-the-art methods in generative quality and exhibits strong generalizability across tasks such as sparse-view CT reconstruction, fast MRI reconstruction, and data augmentation for segmentation and classification. Source code and checkpoints are available at https://github.com/ShanghaiTech-IMPACT/3D-MedDiffusion.

eess.IV↗

arXiv2025

Conceptual Design of the Muonium-to-Antimuonium Conversion Experiment (MACE)

The spontaneous conversion of muonium to antimuonium is one of the interesting charged lepton flavor violation phenomena offering a sensitive probe of potential new physics and serving as a tool to constrain the parameter space beyond the Standard Model. The Muonium-to-Antimuonium Conversion Experiment (MACE) is designed to utilize a high-intensity muon beam, a Michel electron magnetic spectrometer, a positron transport system, and a positron detection system, to either discover or constrain this rare process with a conversion probability of $\mathcal{O}(10^{-13})$. This article presents an overview of the theoretical framework as well as a detailed description of the experimental design for the search for muonium-to-antimuonium conversion.

hep-ex↗

arXiv2025

SiamMM: A Mixture Model Perspective on Deep Unsupervised Learning

Recent studies have demonstrated the effectiveness of clustering-based approaches for self-supervised and unsupervised learning. However, the application of clustering is often heuristic, and the optimal methodology remains unclear. In this work, we establish connections between these unsupervised clustering methods and classical mixture models from statistics. Through this framework, we demonstrate significant enhancements to these clustering methods, leading to the development of a novel model named SiamMM. Our method attains state-of-the-art performance across various self-supervised learning benchmarks. Inspection of the learned clusters reveals a strong resemblance to unseen ground truth labels, uncovering potential instances of mislabeling.

cs.LG↗

arXiv2025

An Encoder-Decoder Network for Beamforming over Sparse Large-Scale MIMO Channels

We develop an end-to-end deep learning framework for downlink beamforming in large-scale sparse MIMO channels. The core is a deep EDN architecture with three modules: (i) an encoder NN, deployed at each user end, that compresses estimated downlink channels into low-dimensional latent vectors. The latent vector from each user is compressed and then fed back to the BS. (ii) a beamformer decoder NN at the BS that maps recovered latent vectors to beamformers, and (iii) a channel decoder NN at the BS that reconstructs downlink channels from recovered latent vectors to further refine the beamformers. The training of EDN leverages two key strategies: (a) semi-amortized learning, where the beamformer decoder NN contains an analytical gradient ascent during both training and inference stages, and (b) knowledge distillation, where the loss function consists of a supervised term and an unsupervised term, and starting from supervised training with MMSE beamformers, over the epochs, the model training gradually shifts toward unsupervised using the sum-rate objective. The proposed EDN beamforming framework is extended to both far-field and near-field hybrid beamforming scenarios. Extensive simulations validate its effectiveness under diverse network and channel conditions.

eess.SY↗

arXiv2025

Covert Communication and Key Generation Over Quantum State-Dependent Channels

We study covert communication and covert secret key generation with positive rates over quantum state-dependent channels. Specifically, we consider fully quantum state-dependent channels when the transmitter shares an entangled state with the channel. We study this problem setting under two security metrics. For the first security metric, the transmitter aims to communicate covertly with the receiver while simultaneously generating a covert secret key, and for the second security metric, the transmitter aims to transmit a secure message covertly and generate a covert secret key with the receiver simultaneously. Our main results include one-shot and asymptotic achievable positive covert-secret key rate pairs for both security metrics. Our results recover as a special case the best-known results for covert communication over state-dependent classical channels. To the best of our knowledge, our results are the first instance of achieving a positive rate for covert secret key generation and the first instance of achieving a positive covert rate over a quantum channel. Additionally, we show that our results are optimal when the channel is classical and the state is available non-causally at both the transmitter and the receiver.

cs.IT↗

arXiv2025

Progressive Flow-inspired Unfolding for Spectral Compressive Imaging

Coded aperture snapshot spectral imaging (CASSI) retrieves a 3D hyperspectral image (HSI) from a single 2D compressed measurement, which is a highly challenging reconstruction task. Recent deep unfolding networks (DUNs), empowered by explicit data-fidelity updates and implicit deep denoisers, have achieved the state of the art in CASSI reconstruction. However, existing unfolding approaches suffer from uncontrollable reconstruction trajectories, leading to abrupt quality jumps and non-gradual refinement across stages. Inspired by diffusion trajectories and flow matching, we propose a novel trajectory-controllable unfolding framework that enforces smooth, continuous optimization paths from noisy initial estimates to high-quality reconstructions. To achieve computational efficiency, we design an efficient spatial-spectral Transformer tailored for hyperspectral reconstruction, along with a frequency-domain fusion module to gurantee feature consistency. Experiments on simulation and real data demonstrate that our method achieves better reconstruction quality and efficiency than prior state-of-the-art approaches.

cs.CV↗

arXiv2025

Texture-aware Intrinsic Image Decomposition with Model- and Learning-based Priors

This paper aims to recover the intrinsic reflectance layer and shading layer given a single image. Though this intrinsic image decomposition problem has been studied for decades, it remains a significant challenge in cases of complex scenes, i.e. spatially-varying lighting effect and rich textures. In this paper, we propose a novel method for handling severe lighting and rich textures in intrinsic image decomposition, which enables to produce high-quality intrinsic images for real-world images. Specifically, we observe that previous learning-based methods tend to produce texture-less and over-smoothing intrinsic images, which can be used to infer the lighting and texture information given a RGB image. In this way, we design a texture-guided regularization term and formulate the decomposition problem into an optimization framework, to separate the material textures and lighting effect. We demonstrate that combining the novel texture-aware prior can produce superior results to existing approaches.

cs.CV↗

arXiv2025

Plug-and-play Diffusion Models for Image Compressive Sensing with Data Consistency Projection

We explore the connection between Plug-and-Play (PnP) methods and Denoising Diffusion Implicit Models (DDIM) for solving ill-posed inverse problems, with a focus on single-pixel imaging. We begin by identifying key distinctions between PnP and diffusion models-particularly in their denoising mechanisms and sampling procedures. By decoupling the diffusion process into three interpretable stages: denoising, data consistency enforcement, and sampling, we provide a unified framework that integrates learned priors with physical forward models in a principled manner. Building upon this insight, we propose a hybrid data-consistency module that linearly combines multiple PnP-style fidelity terms. This hybrid correction is applied directly to the denoised estimate, improving measurement consistency without disrupting the diffusion sampling trajectory. Experimental results on single-pixel imaging tasks demonstrate that our method achieves better reconstruction quality.

cs.CV↗

arXiv2025

User Manual for Model-based Imaging Inverse Problem

This user manual is intended to provide a detailed description on model-based optimization for imaging inverse problem. Theseproblems can be particularly complex and challenging, especially for individuals without prior exposure to convex optimization orinverse problem theory, like myself. In light of this, I am writing this manual to clarify and systematically organize the mathematicalrationale underlying imaging inverse problems. This manual might not be accurate in mathmatical notion but more focus on the logicalthinking on how to solve and proceed to solve the problems. If you want to think deep about something, try to raise questions! Thismanual is seaprated into four sections, aiming to answer the following four questions: (1) What is inverse imaging problem? (2) Why optimization is used to solve the inverse imaging problem? (3) How to solve the optimization problem? (4) How to implement the optimization algorithm in real imaging system?

math.NA↗

arXiv2025

EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients

Federated learning research has recently shifted from Convolutional Neural Networks (CNNs) to Vision Transformers (ViTs) due to their superior capacity. ViTs training demands higher computational resources due to the lack of 2D inductive biases inherent in CNNs. However, efficient federated training of ViTs on resource-constrained edge devices remains unexplored in the community. In this paper, we propose EFTViT, a hierarchical federated framework that leverages masked images to enable efficient, full-parameter training on resource-constrained edge devices, offering substantial benefits for learning on heterogeneous data. In general, we patchify images and randomly mask a portion of the patches, observing that excluding them from training has minimal impact on performance while substantially reducing computation costs and enhancing data content privacy protection. Specifically, EFTViT comprises a series of lightweight local modules and a larger global module, updated independently on clients and the central server, respectively. The local modules are trained on masked image patches, while the global module is trained on intermediate patch features uploaded from the local client, balanced through a proposed median sampling strategy to erase client data distribution privacy. We analyze the computational complexity and privacy protection of EFTViT. Extensive experiments on popular benchmarks show that EFTViT achieves up to 28.17% accuracy improvement, reduces local training computational cost by up to 2.8$\times$, and cuts local training time by up to 4.4$\times$ compared to existing methods.

cs.CV↗

arXiv2025

Unfolding Framework with Complex-Valued Deformable Attention for High-Quality Computer-Generated Hologram Generation

Computer-generated holography (CGH) has gained wide attention with deep learning-based algorithms. However, due to its nonlinear and ill-posed nature, challenges remain in achieving accurate and stable reconstruction. Specifically, ($i$) the widely used end-to-end networks treat the reconstruction model as a black box, ignoring underlying physical relationships, which reduces interpretability and flexibility. ($ii$) CNN-based CGH algorithms have limited receptive fields, hindering their ability to capture long-range dependencies and global context. ($iii$) Angular spectrum method (ASM)-based models are constrained to finite near-fields.In this paper, we propose a Deep Unfolding Network (DUN) that decomposes gradient descent into two modules: an adaptive bandwidth-preserving model (ABPM) and a phase-domain complex-valued denoiser (PCD), providing more flexibility. ABPM allows for wider working distances compared to ASM-based methods. At the same time, PCD leverages its complex-valued deformable self-attention module to capture global features and enhance performance, achieving a PSNR over 35 dB. Experiments on simulated and real data show state-of-the-art results.

cs.CV↗

arXiv2025

See What You Need: Query-Aware Visual Intelligence through Reasoning-Perception Loops

Human video comprehension demonstrates dynamic coordination between reasoning and visual attention, adaptively focusing on query-relevant details. However, current long-form video question answering systems employ rigid pipelines that decouple reasoning from perception, leading to either information loss through premature visual abstraction or computational inefficiency through exhaustive processing. The core limitation lies in the inability to adapt visual extraction to specific reasoning requirements, different queries demand fundamentally different visual evidence from the same video content. In this work, we present CAVIA, a training-free framework that revolutionizes video understanding through reasoning, perception coordination. Unlike conventional approaches where visual processing operates independently of reasoning, CAVIA creates a closed-loop system where reasoning continuously guides visual extraction based on identified information gaps. CAVIA introduces three innovations: (1) hierarchical reasoning, guided localization to precise frames; (2) cross-modal semantic bridging for targeted extraction; (3) confidence-driven iterative synthesis. CAVIA achieves state-of-the-art performance on challenging benchmarks: EgoSchema (65.7%, +5.3%), NExT-QA (76.1%, +2.6%), and IntentQA (73.8%, +6.9%), demonstrating that dynamic reasoning-perception coordination provides a scalable paradigm for video understanding.

cs.CV↗

arXiv2025

LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering

Video Question Answering (VideoQA) requires identifying sparse critical moments in long videos and reasoning about their causal relationships to answer semantically complex questions. While recent advances in multimodal learning have improved alignment and fusion, current approaches remain limited by two prevalent but fundamentally flawed strategies: (1) task-agnostic sampling indiscriminately processes all frames, overwhelming key events with irrelevant content; and (2) heuristic retrieval captures superficial patterns but misses causal-temporal structures needed for complex reasoning. To address these challenges, we introduce LeAdQA, an innovative approach that bridges these gaps through synergizing causal-aware query refinement with fine-grained visual grounding. Our method first leverages LLMs to reformulate question-option pairs, resolving causal ambiguities and sharpening temporal focus. These refined queries subsequently direct a temporal grounding model to precisely retrieve the most salient segments, complemented by an adaptive fusion mechanism dynamically integrating the evidence to maximize relevance. The integrated visual-textual cues are then processed by an MLLM to generate accurate, contextually-grounded answers. Experiments on NExT-QA, IntentQA, and NExT-GQA demonstrate that our method's precise visual grounding substantially enhances the understanding of video-question relationships, achieving state-of-the-art (SOTA) performance on complex reasoning tasks while maintaining computational efficiency.

cs.CV↗