arXiv subjects

Hui Zhang

Publications and source records attributed to Hui Zhang.

At least 19 recordsLinked to original sources

arXiv2026

UniH$^3$: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration

All-in-One medical image restoration (MedIR) aims to address diverse tasks across modalities and degradation types using a single universal model. Existing methods typically prioritize modeling inter-task heterogeneity (e.g., distinct data distributions and degradation types). However, they largely neglect the inherent homogeneity present in medical images, such as widely shared anatomical structures within and across modalities, which can be leveraged to ease model training and improve generalization. To this end, we propose UniH3, a novel framework that Unifies Hierarchical Homogeneity and Heterogeneity for all-in-one medical image restoration. Specifically, to comprehensively exploit homogeneity, we introduce a Hierarchical Homogeneity Memory (H2M) module that progressively distills intra- and inter-task homogeneity priors from high-quality images during training, and adaptively retrieves the most relevant priors tailored to the input for guided restoration. These retrieved priors are then injected into the restoration pipeline via an efficient Homogeneity-Guided Attention (HGA) mechanism. Furthermore, to comprehensively address heterogeneity, we design a Hierarchical Heterogeneity Balancer (H2B) that mitigates both inter- and intra-task conflicts during optimization, facilitating balanced and effective multi-task learning. Extensive experiments on two large-scale benchmarks, MedIR-2D-500K and MedIR-3D-3K, demonstrate that UniH3 achieves state-of-the-art performance on both all-in-one and single-task medical image restoration. We hope this work establishes a strong benchmark and advances the development of general-purpose medical image restoration models. Code is available at https://github.com/Yaziwel/UniH3.

cs.CV↗

arXiv2026

Assembling Two Parts in One Hand

A hallmark of human dexterity is the cooperative use of fingers, where different fingers take on distinct yet coordinated roles to accomplish fine manipu- lation, such as capping a pen with the hand that holds it. We study this finger-level coordination through in-hand assembly: mating two rigid objects within a single dexterous hand, with no second arm and no fixture. We present a reinforcement learning formulation to solve this problem in a unified framework, which is driven by a goal relative pose between the two parts. Finger coordination is shaped by a function-based auxiliary reward and regularized toward a single human reference pose, while domain randomization and a fusion of historical proprioception and object observation confer robustness to occlusion-induced estimation noise. The same recipe solves three different assembly tasks (Bottle, Syringe, and Marker). Trained purely in simulation, the policies transfer zero-shot to hardware with a single camera, demonstrating robustness to state-estimation errors caused by oc- clusion. Our experiments also reveal that in-hand assembly places demands on hand morphology and can serve as a benchmark for modern robotic hand systems. Videos and code are available at https://ltbgbird.github.io/in-hand-assembly-page/.

cs.RO↗

arXiv2026

Positive biorthogonal curvature on $S^2\times T^2$

We construct explicit Riemannian metrics with positive biorthogonal curvature on $S^2\times T^2$, answering a question of Bettiol. In particular, positive biorthogonal curvature on a closed four-manifold does not force its fundamental group to be virtually free.

math.DG↗

arXiv2026

Agentic Visual Generation: From Generative Models to Agentic Control

Visual generation is evolving from generative models used through a single invocation into agentic control processes that can plan, select tools, inspect intermediate synthesized outputs, revise failures, and reuse prior experience. In most existing systems, the controller is an LLM or VLM, while visual generation models serve as tools or executors. However, existing work lacks a consistent criterion for determining when a generation system becomes agentic. Planning depth, tool use, multi-role collaboration, and reinforcement learning are often treated as evidence of agenticity, even though none of them necessarily determines which generation decisions the controller can make. We organize the field according to what the controller can directly control in the generation process. At L1 Conditioning Control, the controller prepares the input to a predetermined generator but does not control which visual operation is executed. At L2 Execution Control, it selects and invokes actual generation, editing, rendering, or other content-modifying operations. At L3 Outcome-Adaptive Control, it observes an intermediate outcome and uses that observation to change a subsequent operation within the current task. At L4 Experience-Adaptive Control, it retains experience from completed tasks and uses that experience to change decisions on future tasks. L0 Fixed Support separately denotes generators, editors, evaluators, reward models, benchmarks, and fixed pipelines without a deployed controller that makes generation-level decisions. These levels describe a progressively broader decision-making scope rather than model size, system complexity, output quality, tool or role count, or training method. Applying this framework across image, video, editing, 3D, world, slide, and user-interface generation reveals how controller capabilities have evolved and how their mechanisms are distributed across levels.

cs.CV↗

arXiv2026

WeAgent-MMGenEdit: A Full-Stack Recipe for Multimodal Agentic Image Generation and Editing

Image generation and editing models have advanced rapidly, yet remain unreliable when prompts require external world knowledge. Bounded and long-tail parametric knowledge prevents direct or reason-then-generate approaches from recovering the required facts and visual appearances. Existing agentic generation and editing methods mitigate this limitation with retrieval tools, yet remain constrained by insufficient visual verification, overloaded policy models, and weak integration of retrieved textual and visual evidence. To address these limitations, we present WeAgent-MMGenEdit, a full-stack recipe including a multimodal harness, a scalable data construction pipeline, a comprehensive benchmark, and post-training methods for the agent policy and image backend. We first introduce WeAgent-Harness, a multimodal runtime with persistent evidence management and dedicated verification and integration tools that organize retrieved multimodal evidence into a dense carrier. Upon this, we develop a scalable pipeline for prompt synthesis and agentic trajectory collection, yielding 23K supervised trajectories and 14.7K RL tasks with three-layer verifiable checklists. We further introduce WeBench-MMGenEdit, a bilingual benchmark covering both knowledge-intensive image generation and multi-image editing. Finally, a two-sided post-training recipe based on SFT and RL improves the agent policy and image backend. Together, WeAgent-MMGenEdit enables a 30B-total/3B-active policy to outperform similarly sized policy models and approach the performance of a 1T-parameter agent.

cs.CV↗

arXiv2026

Dimensionality-induced critical phase transition in stochastic Lotka-Volterra equation: From statistical averaging to systemic tipping point

By analyzing a stochastic Lotka-Volterra (LV) equation, we show that the underlying logic behind the diversity-stability debate in ecology can be framed as a dimensionality-induced critical phase transition, that is, a transition separating the regime dominated by statistical averaging and a systemic tipping point. This phase transition framework unifies the opposing ecological predictions in the diversity-stability debate and sets an intrinsic diversity ceiling for stochastic ecological communities.

q-bio.PE↗

arXiv2026

WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents

Multimodal search agents extend parametric knowledge with newly emerging and long-tail evidence from the open web. Yet many existing agentic search environments often expose retrieved evidence only as text and omit tool-returned images from subsequent context, reducing visually grounded trajectories to text-only reasoning. Long-horizon interaction also compounds tool-call, response-length, timeout, and budget failures, which can discard salvageable trajectories, waste rollout computation, and disturb policy updates. To address these issues, we introduce WeAgent-Harness, a multimodal agentic harness that supports native text-vision interaction and runtime recovery. Retrieved images receive persistent disk references, allowing the model to inspect, process, and cite them throughout the trajectory. Based on this harness, we develop WeAgent-MMSearch, an integrated system spanning data construction, agentic post-training, and multimodal rollout. For data construction, a strong MLLM uses WeAgent-Harness to discover, synthesize, and verify MMSearch-style tasks and collect expert trajectories. During post-training, our Failure-Aware GSPO (FA-GSPO) recovers salvageable abnormal rollouts and filters invalid ones to improve bounded multimodal planning and search. We also introduce VisTarget-Bench, a 150-task human-verified benchmark that pairs each question with a held-out target image, distinguishing image-retrieval failures from visual-perception failures. Evaluation on VisTarget-Bench and seven public benchmarks shows that agentic post-training improves the average score by 19.22 points, enabling our model to outperform similarly sized open-source models and rival models with roughly ten times its parameter count.

cs.AI↗

arXiv2026

VersaDB: A High-Performance AI Storage Database for Unifying Mutimodal Datasets

The AI field has been rapidly developing, leading to the emergence of a large number of AI training datasets of various types. These datasets contain different modalities, including text, images, audio, etc., and may come in various data storage formats. With the advancement of AI hardware, AI computation units like GPUs, TPUs, and NPUs can greatly accelerate the training speed of AI models, which in turn increases the demand for faster data processing. When using existing AI processing frameworks to handle datasets with different modalities and storage formats, processing speeds may be suboptimal due to issues such as data layout and the way users handle the data. Therefore, using a unified database to store multiple data formats can better manage and optimize data access. In this paper, we introduce VersaDB, a database designed specifically for AI datasets with various modalities. We implemented a page-based storage system, separating structured and unstructured data. Additionally, we generated B+ tree-based index files to accelerate data access. VersaDB supports automatic sharding and maintains a hierarchical metadata management system, with corresponding metadata maintained at the page, shard, and global levels, forming the foundation for the efficient operation of the database. We also focused on ease of use by providing APIs for directly converting datasets into VersaDB, as well as APIs for converting popular AI data storage formats (e.g., CSV, TFRecord, .bin) into VersaDB.Our experiments show that using VersaDB can achieve up to 5.35x acceleration and maintain consistent performance across different parallelism levels.

cs.CV↗

arXiv2026

SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation

Programmable logic controllers (PLCs) run industrial plants, and large language models can already generate independent program organization units (POUs) for them. Whether such logic integrates into an existing PLC project and then runs correctly has been checked only in limited tests. We present \textsc{SemaPLC}, a project-grounded and verification-gated agent harness assembled from conventional tools but governed by a strict completion rule. Rather than stopping when the model judges its own output adequate, \textsc{SemaPLC} declares a task complete only when logged external checks confirm it. Those checks cover the specification, the compilation, and the behavior on a live runtime. On 117 independent-POU tasks matching existing benchmarks, it attains the highest strict verified pass rate on all seven models (72.6\% mean). On a project-context track of 65 tasks whose generated logic must compile and run inside a real project, it attains the highest mean on integrated compilation, static behavior, and dynamic behavior. Of the three layers, dynamic behavior is the most revealing. We measure it by deploying the generated and the reference logic to a live PLC runtime and comparing their executed traces. All methods fall within 10 static points of one another, whereas dynamic scores separate them sharply, from 22.4 to 31.4 for the baselines against 52.2 for \textsc{SemaPLC}. Overall, our verification-gated harness raises the mean at every layer and most sharply at runtime. Execution, not static scoring, is the faithful test of whether generated control logic actually works. \textsc{SemaPLC} is open-sourced at https://github.com/midea-ai/SemaPLC.

cs.SE↗

arXiv2026

Clustering Informed Inverse Probability Weighting Strategies for Causal Effect Estimation in Observational Studies

Inverse probability weighting (IPW) is widely used to estimate causal effects in observational studies but depends on adequate propensity-score specification. We compare three strategies for addressing treatment assignment heterogeneity: standard IPW, clustering augmented IPW with cluster specific propensity score models, and a global propensity score model including estimated cluster membership as a covariate. Through simulations with and without latent cluster structure and under correctly specified and omitted covariate propensity score models, we evaluate bias, mean squared error (MSE), and confidence interval coverage across sample sizes of 100 to 500. Both cluster informed strategies reduced bias and MSE from omitted covariate misspecification relative to standard IPW, but neither uniformly dominated: clustering augmented IPW achieved lower MSE when latent cluster structure was present, whereas the global model generally provided lower bias and better coverage at smaller sample sizes. We also apply the methods to 966 breast cancer patients treated with carboplatin, using generalized propensity scores to estimate the dose response relationship between treatment cycles and hypersensitivity reaction risk. Standard and clustered analyses produced similar pooled estimates, while clustering additionally provided subgroup specific estimates and diagnostic profiles. Overall, cluster informed strategies may improve robustness to propensity score misspecification, with relative performance depending on subgroup structure, sample size, and inferential priorities.

stat.ME↗

arXiv2026

Chemical Potential and Analytic Continuation for Non-Hermitian Lattice Fermions

We introduce a chemical potential for non-Hermitian lattice fermions and show that, for even flavors with degenerate masses and paired chemical potentials $(\mu,-\mu)$ or $(i\mu,i\mu)$, the Hybrid Monte Carlo algorithm is free of the sign problem. For one-dimensional free fermions, we demonstrate that the sign problem is a numerical rather than physical obstruction and derive the exact propagator, which is analytic at finite lattice spacing away from its poles but becomes non-analytic in the continuum limit. Finally, we use AI-assisted fitting to perform analytic continuation from imaginary to real chemical potentials.

hep-lat↗

arXiv2026

Protocol generalisation for brain tissue microstructure estimation via hypernetwork-controlled geometric deep learning

Brain tissue microstructure estimation with machine learning provides higher computational efficiency than conventional fitting. However, machine learning still presents important limitations that hamper its clinical utility. Specifically, current models typically lack generalisation across diffusion MRI acquisition protocols and require retraining whenever b-vectors or b-values change. Moreover, the recent machine learning methods that were developed to address protocol generalisation lack rotational equivariance. Particularly suitable for dMRI parameter estimation is a geometric deep learning model known as spherical convolutional neural network (SCNN), which guarantees rotational equivariance and b-vector generalisation. However, this architecture currently does not account for b-values. Therefore, obtaining a model that combines protocol generalisation and rotational equivariance remains an open challenge. In this paper, we directly address this issue by incorporating explicit b-value dependence into an SCNN architecture via a hypernetwork. This new approach is illustrated using NODDI as an example forward model for estimating brain tissue microstructure. To evaluate b-value generalisation, the original and newly proposed SCNN architectures are trained on synthetic data and tested on both synthetic and real data across different b-value pairs. Results demonstrate that the proposed method achieves reduced RMSE and bias on synthetic data, as well as higher agreement with conventional NODDI fitting on real data, indicating improved robustness to unseen b-values and a reduced need for retraining. By combining generalisation across b-values with generalisation across b-vectors and rotational equivariance, the proposed framework enhances the applicability of deep learning to clinical diffusion MRI parameter estimation. Code available at https://github.com/aerdnairo/arXiv\_generalisedSCNN.

eess.IV↗

arXiv2026

Topological Rainbow Trapping for Spatial-frequency Demultiplexing of Underwater Acoustic Signals

Efficient separation and localization of multifrequency acoustic waves are essential for underwater target recognition and acoustic energy harvesting. The underwater implementation of topological rainbow trapping remains challenging because of complex fluid-solid interactions and the difficulty of integrating long-range transport with frequency-selective localization in an open system. Here, we theoretically develop and experimentally demonstrate two underwater spatial-frequency demultiplexing mechanisms based on the acoustic analogues of the QVHE and QSHE. Both mechanisms employ SSAWs, whose fields are confined near a structured surface and decay evanescently into the surrounding water, enabling experiments without an enclosed waveguide. In the QVHE mechanism, a spatial gradient along a valley-Hall edge channel shifts the local edge-state dispersion, causing different frequency components to become localized at distinct positions and thereby realizing spectral and spatial demultiplexing. In the QSHE mechanism, one-dimensional topological edge states are coupled to frequency-selective zero-dimensional higher-order corner states. Multifrequency signals first propagate robustly along a common boundary and are then transferred to prescribed remote corners according to frequency, producing a transport-then-confinement process. This mechanism combines defect-tolerant edge transport, frequency-selective corner localization, and remote rainbow trapping. Numerical simulations and experiments verify the frequency-dependent localization and the persistence of the designed transport pathways in the presence of structural defects. The proposed open SSAW platform performs robust frequency demultiplexing at the physical layer, reducing reliance on digital signal processing and offering potential for underwater target recognition and frequency-selective acoustic energy harvesting.

physics.app-ph↗

arXiv2026

UniCross: Unified Cross-Skill Dexterous Manipulation Synthesis

Many dexterous manipulation tasks require the object to remain securely held throughout the interaction. From the perspective of hand-object relational motion, such manipulation comprises four canonical skills: grasping, relocation, in-hand rotation, and in-hand translation. Human hands flexibly compose these skills to accomplish complex tasks. Existing approaches, however, model these skills separately with skill-specific action constraints, objectives, or even dedicated hand morphologies, which breaks the compatibility and continuity required for long-horizon composition. In this work, we present a unified framework that models all four skills in a single formulation that shares the same state and action spaces and a common objective structure. This formulation enables straightforward distillation of a single cross-skill policy that performs strongly on every skill, generalizes to unseen objects, stays robust to disturbances, and chains skills seamlessly into long-horizon manipulation. The framework also transfers effectively across different hand morphologies. Overall, our results suggest that different dexterous manipulation skills can be viewed as instantiations of a shared task formulation, revealing the intrinsic consistency across different behaviors.

cs.RO↗

arXiv2026

Eddeep: a deep-learning framework for fast eddy-current distortion correction in diffusion MRI

Diffusion MRI (dMRI) relies on diffusion-weighted echo-planar imaging, which is highly susceptible to eddy-current-induced geometric distortions. These distortions vary across diffusion volumes according to gradient strength and direction, causing between-volume misalignment that can bias downstream microstructural analyses. Current state-of-the-art correction methods, such as FSL Eddy, achieve high-quality correction through iterative prediction-correction schemes but are computationally expensive. We propose Eddeep, a deep-learning framework for fast eddy-current distortion correction in dMRI. Eddeep decomposes the problem into two stages. First, a supervised image translation network standardises the appearance of diffusion-weighted and b=0 images, removing contrast differences that hinder reliable registration. Second, an unsupervised registration network estimates both eddy-current distortion and between-volume head motion parameters under a physics-constrained quadratic distortion model, enabling correction in a single forward pass. The method was trained on UK Biobank data and evaluated on both in-domain (UK Biobank) and out-of-domain (Memodyn) datasets. Across a range of complementary metrics, including between-volume jitter, diffusion kurtosis imaging residuals, signal irregularity, and mutual information, Eddeep achieved correction quality comparable to that of FSL Eddy while substantially reducing inference time. These results demonstrate that deep learning can provide accurate and efficient eddy-current distortion correction without relying on iterative optimisation, supporting the development of faster diffusion MRI processing pipelines for large-scale studies and clinical deployment. The code is available at: https://github.com/CIG-UCL/eddeep.

cs.CV↗

arXiv2026

Elastic Trapped States at Dislocation Defects in Scaled Coupling and Hofstadter Models

Elastic topological dislocations provide a pathway for trapping elastic wave energy at internal defects, rather than being confined solely to external boundaries or corners, which are typically associated with topological insulators (TIs). However, two practical constraints persist. First, highly confined dislocation states based on conventional Su-Schrieffer-Heeger (SSH) dimerization usually require a large coupling contrast and a correspondingly enlarged bandgap, which may be challenging to realize. Second, some Hamiltonians with richer topological physics often contain complex hopping terms, synthetic gauge fields or nonlocal couplings, which substantially increase the geometric complexity of experimental samples. Here, dislocation-induced trapped states are demonstrated in both a scaled coupling (SC) model and a Hofstadter model (HM) within an elastic platform. In the SC model, the trapped mode is treated as a higher localized state in the continuum rather than an in-gap mode in the SSH model. Consequently, the SC-induced dislocation can trap an enhanced mode without the requirement of an enlarged bandgap. For the HM, Householder tridiagonalization is used to map the original tight-binding Hamiltonian with complex hopping terms onto a tridiagonal matrix with only positive-real-valued nearest-neighbour (NN) hopping terms. Truncation at a weak-hopping position preserves the topological phenomena and allows a dislocation defect to be constructed from the shortened aperiodic chain. The results establish a practical route for designing highly localized modes without relying solely on bandgap enlargement or complex couplings, which advance the topological physics of elastic wave systems and promise enhanced possibilities for elastic functional devices.

physics.app-ph↗

arXiv2026

A frugal primal-dual splitting with minimal lifting over arbitrary rooted trees

We develop a frugal primal-dual splitting with minimal lifting for solving structured monotone inclusions, involving cocoercive operators, linear compositions and parallel sums. This is established by defining hierarchical nodes and edges between them over a tree-structured graph, with arbitrary assignments of dual variables and cocoercive elements to primal nodes. This arbitrariness allows a great flexibility in terms of level-synchronous distributed computing, such as centralized or decentralized. The particular instances naturally extend the Douglas--Rachford splitting on various graphs, recover the parallel Chambolle--Pock, and solve a class of structured convex minimization problems. For the pure resolvent convex minimization subclass, we establish an O(1/k) ergodic rate for a restricted primal-dual gap over bounded test sets. Furthermore, we introduce a reformulation technique in a product Hilbert space to facilitate the convergence analysis, specifically to derive the o(1/k)-rate of asymptotic regularity

math.OC↗

arXiv2026

JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models

The post-training of Vision-Language-Action (VLA) models is essential due to the diversity of simulators, robot embodiments, and task objectives. Existing compute services, whether offered as direct accelerator rental or batch-workload submission, typically allocate an exclusive set of GPU and CPU resources to a single tenant. While this paradigm maximizes client flexibility, it burdens users with infrastructure adaptation, and the fixed card-hour accounting model renders short or bursty workloads both expensive for tenants and inefficient for the service provider. To address these challenges, we present JoyNexus, a unified service for multi-tenant VLA supervised fine-tuning, reinforcement learning, and evaluation. JoyNexus decouples the Training Model Service, Inference Model Service, and Environment Service, each accessed through APIs and backed by resident shared base models with tenant-specific slots. Tenants can directly invoke high-level semantic APIs for training, rollout, and evaluation, or compose custom algorithms using lower-level APIs and their assigned endpoints. Multiple tenants submit workloads concurrently; their action modules, optimizers, rollout records, and policy versions remain isolated, and the service is scheduled by the global Training Queue and Inference Queue. To further improve multi-tenant training efficiency, JoyNexus introduces group batching for heterogeneous VLA data schemas that share a compatible model-facing prefix, enabling a single shared backbone forward pass over grouped samples. Finally, we evaluate JoyNexus through workload simulation and a group-batching pipeline in a realistic embodied scenario. Results show that, compared with isolated single-tenant execution, JoyNexus reduces aggregate GPU time and improves service utilization via cross-tenant scheduling on shared resources.

cs.DC↗