arXiv subjects

Hongmin Cai

Publications and source records attributed to Hongmin Cai.

At least 19 recordsLinked to original sources

arXiv2026

RealSimLoop: Online Real-to-Sim Adaptation via Differentiable Reduced-Order Simulation with Vision Feedback

Real-world observations of deformable objects are often sparse or surface-level, while downstream tasks require hidden physical quantities such as internal deformation, stress fields, and interaction forces. Physics-based simulation can recover these quantities, but online real-to-sim adaptation remains challenging due to costly full-space optimization, limited feedback, and time-varying material properties. To address these challenges, we propose RealSimLoop, a differentiable framework for online real-to-sim adaptation using vision data as physical feedback. Our approach achieves quasi-real-time performance by executing differentiable simulation within a reduced-order neural subspace, drastically accelerating the optimization loop. We couple this efficient dynamics model with differentiable rendering, enabling direct gradient backpropagation that leverages high-fidelity pixel data to refine physical parameters such as material stiffness. Furthermore, by employing a sliding-window objective function, RealSimLoop enables robust online adaptation, allowing the system to track time-varying material properties and effectively bridge the real-to-sim gap arising from model reduction or unmodeled dynamics. Extensive experiments demonstrate that our method outperforms conventional offline methods, and we validate the framework's versatility in downstream applications, including external force prediction and 3D stress field reconstruction with novel view synthesis.

cs.GR↗

arXiv2026

DeMixPert: Decomposed Response Modeling with Gaussian Mixtures for OOD Single-Cell Perturbation Prediction

Predicting transcriptome-wide responses to unseen genetic perturbations remains a major computational challenge because accurate prediction requires recovering both perturbation-specific transcriptional shifts and heterogeneous cellular responses. Existing methods often entangle deterministic response structure with stochastic population-level variation, causing dominant shared patterns to mask weaker perturbation-specific signals and impair distributional modeling. To address these challenges, we propose \textbf{DeMixPert}, an approach for Decomposed response Modeling with Gaussian Mixtures for Out-Of-Distribution (OOD) single-cell Perturbation prediction. DeMixPert decomposes perturbation-induced changes into a basal-state-dependent systematic response, a perturbation-specific response, and population-level variation. The systematic component is derived from the basal state encoded from control-cell expression, whereas the perturbation-specific component is inferred from pretrained target embeddings for unseen-target generalization. DeMixPert models population-level variation using a Gaussian prototype Invertible Network and adaptively combines reusable Gaussian prototypes according to the basal state and perturbation condition. The resulting mixture is mapped to a condition-specific variation distribution. Sampled variations are integrated with the systematic and perturbation-specific components, followed by joint decoding with the basal state to reconstruct perturbed-cell gene expression. Experimental results show that DeMixPert effectively captures heterogeneous single-cell perturbation responses and achieves superior performance across unseen-perturbation settings. The source code is made publicly available upon publication.

cs.LG↗

arXiv2026

EfficientSync: Real-Time Lip Synchronization via Deformation-Based Reference Texture Mixing

Audio-driven lip synchronization manipulates the mouth region of a talking-face video to match the driving audio while preserving head pose, identity, and background. Although the task is inherently local editing, prevailing approaches reconstruct the entire lower face with heavy GAN- or diffusion-based decoders, incurring substantial latency and, more critically, hallucinating intra-oral details such as teeth and lip wrinkles instead of preserving authentic textures. We contend that the bottleneck in identity preservation is not the scarcity of reference frames, but the lack of a mechanism that faithfully transfers the genuine textures they already contain. We therefore present EfficientSync, a real-time deformation-based framework that retains reference textures rather than resynthesizing them. First, the Dynamic Texture Mixer reformulates multi-reference fusion as channel-wise selection, evaluating each spatially aligned reference in a global context and aggregating them by channel-wise weighted summation, preserving textural integrity at low cost. Second, Spatio-Temporal Shifted Adaptive Masking decomposes the source frame into lip-generation conditions and an independent background prior, suppressing lower-face leakage while blending the synthesized mouth seamlessly into the background. Third, STAR Sampling, a zero-overhead pre-processing step, retrieves the sharpest and most topologically diverse reference frames. Experiments on HDTF and VFHQ show state-of-the-art visual quality and identity preservation at 166 FPS on a single GPU. Video demos: https://alunaticat.github.io/EfficientSync/index.html.

cs.CV↗

arXiv2026

S$^3$-Diff: Structural Semantic Synergy Diffusion Model for High Fidelity Super Resolution of Pathological Images

Digital pathology relies on high-resolution whole slide images for accurate diagnosis, yet limitations in imaging devices, storage, and transmission often make lower-resolution pathology images more common in clinical workflows. Current super-resolution techniques often tend to smooth diagnostically relevant morphology, leading to over-smoothed textures and semantic drift that compromise downstream clinical interpretation. To this end, we develop the Structural Semantic Synergy Diffusion Model (S3-Diff), a diffusion framework for high-fidelity super-resolution of pathological images. The core of S3-Diff is Specimen-aware Structural Anchoring (SSA), which combines prognosis-aware tissue support extracted by a fixed SAM with LR-HR gradient discrepancies to generate a specimen-specific structural anchor to preserve pathological morphology. Concurrently, we introduce Structure-guided Semantic Fidelity Tuning (SSFT) to adapt DINOv3 representations using SSA-derived structural supervision. SSFT combines the adapted semantic energy with LR-derived edge and grayscale cues. The resulting control guides denoising to suppress stochastic artifacts and maintain structural consistency. Extensive experimental results demonstrate that S3-Diff consistently outperforms state-of-the-art methods in both reconstruction quality and downstream survival analysis performance. The source code will be made public.

cs.CV↗

arXiv2026

Morphology-Aware Implicit Super-Resolution Network for Pathological Images

Accurate diagnosis in Digital Pathology (DP) relies on high-resolution whole-slide images, yet clinical deployment is often limited by hardware costs. Super-Resolution (SR) offers a promising alternative by computationally enhancing low-resolution acquisitions. However, existing SR methods frequently struggle to preserve fine-grained cellular morphology, leading to texture oversmoothing and blurred structural boundaries under complex tissue variability. To address this issue, we propose Morph-ISR, a morphology-aware implicit super-resolution framework for DP that restores diagnostically relevant details with sub-pixel precision. Morph-ISR reformulates SR as a continuous coordinate-based reconstruction problem and integrates an Implicit Position-aware Kernel Generator (IPKG) to adaptively model spatially varying tissue morphology. To further enhance structural fidelity, a Morphological Fidelity Prior (MFP) is introduced, leveraging semantic guidance from a pre-trained cell segmentation network to enforce boundary-preserving and region-aware reconstruction, thereby improving the representation of critical cellular boundaries and nuclear textures. Experiments on TCGA and SurGen datasets show that Morph-ISR achieves the best LPIPS and ST-LPIPS among the evaluated methods, reducing them by up to 38.37% and 39.55%, respectively, over the second-best methods while maintaining strong PSNR and SSIM. These results demonstrate superior preservation of diagnostically relevant cellular boundaries and nuclear textures, while compact parameterization and high throughput support efficient edge deployment. Code and trained models will be released upon publication.

cs.CV↗

arXiv2026

CHM-Net: Center Heatmap-driven Macro-Micro Modeling Network for MRI-based Microbial Density Stratification

Microbial density is clinically important for tumor assessment and treatment decision-making, and recent advances in deep learning suggest that it can be non-invasively inferred from multimodal MRI. In this work, MRI-based Microbial Density Stratification (MRI-MDS) is first investigated as a patient-level representation learning task, and Center Heatmap-driven Macro-micro modeling Network (CHM-Net) is introduced for this task. CHM-Net first establishes the link between imaging phenotypes and microbial states through center heatmap-guided small-lesion response localization. Building upon this, it constructs patient-level macro-micro evidence from localized heatmap responses for microbial density prediction. Experiments on the novel GBNPC 2026 dataset constructed for MRI-MDS demonstrate the effectiveness of CHM-Net, achieving superior performance over representative baselines with a 12.06% absolute ACC gain over the strongest competing result. Additionally, auxiliary validation on two 3D medical image datasets further verifies its robustness across volumetric medical image classification scenarios. The project is available at https://anonymous.4open.science/r/CHM-Net-942E/.

eess.IV↗

arXiv2026

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

We present PEAM, a Parametric Embodied Agent Memory framework in Minecraft that transforms agent memory from inference-time retrieval into parameter-resident skills internalized through experience. PEAM pairs a slow deliberative LLM for open-ended reasoning with a fast parametric module for reflexive execution of consolidated skills. The fast module is a multimodal Mixture-of-Experts LoRA architecture with per-category physically isolated adapters, enabling parameter-level continual learning without catastrophic forgetting. We treat failure as a first-class training signal: failure--correction trajectory pairs are internalized through a joint behavioral-cloning and contrastive objective, so the agent learns not only what succeeds but also how corrected actions differ from failed ones. To govern consolidation, PEAM introduces a parameterization-worthiness score for deciding which experience should be internalized, and a scale-free self-triggered consolidation mechanism for deciding when to internalize without task-specific hand-tuned thresholds, making the agent self-evolving as the trigger transfers across task distributions without re-tuning. Experiments in Minecraft show that PEAM improves long-horizon task performance, mitigates forgetting on previously consolidated skills, and improves parametric-versus-retrieval efficiency over retrieval-based embodied agents and parametric memory variants.

cs.AI↗

arXiv2026

Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought

Recent segmentation models couple large language models (LLMs) with mask decoders to ground complex language expressions into masks, yet their instructions remain target-referential: they describe, constrain, or imply the region to be segmented. However, in real-world embodied interaction, human instructions are often at the intent-level, which includes the desired outcome without naming the region that enables it. To bridge this gap, we introduce SegWorld, where the model reasons about the scene through a multi-level visual chain-of-thought (CoT) before committing to a mask. Before receiving any instructions, it proactively observes the scene, describing visible objects and inferring plausible events they may support. Given an instruction, it continues the chain: from the object relevant to the intent, through the action that satisfies it, to the physical interaction site, the object part that affords the action. We formalize SegWorld as probabilistic inference, in which proactive observation supplies a linguistic scene context that improves mask prediction when instructions are given at the level of intent. We construct an intent-to-part benchmark for evaluating affordance-bearing part segmentation from high-level goals. Experiments show SegWorld matches instruction-driven baselines on target-referential instructions and improves substantially on intent-level ones.

cs.CV↗

arXiv2026

SplitAvatar: One-shot Head Avatar with Autoregressive Gaussian Splitting

3D Gaussian Splatting (3DGS) provides an efficient method for high-quality scene reconstruction using anisotropic Gaussians. Recently, 3DGS-based methods have significantly improved the rendering quality of human avatars while enabling real-time performance. However, existing methods suffer from a magnitude mismatch in the number of Gaussians generated by image-based and 3DMM-based approaches. This discrepancy results in reconstructed expressions that lack fine-grained detail. In this paper, we introduce a novel method for reconstructing an animatable head avatar from a single image. We propose a Graph splitting network to progressively generate Gaussians from coarse to fine using an autoregressive architecture. To address the graph inconsistency caused by split Gaussians, we employ a mesh topology extension method to align the GNN's connectivity with the increased Gaussian count. Furthermore, we introduce a novel density control method that includes a gating mechanism that generates soft masks for Gaussians, preventing over-densification after the splitting operation. This allows for dynamic control over Gaussian density across different facial regions. For smooth and rapid training, we employ a delayed filtering strategy to avoid re-computing the graph topology during training. Experimental results demonstrate that our autoregressive structure effectively improves expression representation ability by progressively splitting Gaussians. This process, enabled by the GNN-guided splitting, synthesizes more precise facial details and achieves higher reconstruction quality.

cs.CV↗

arXiv2026

LumiVideo: An Intelligent Agentic System for Video Color Grading

Video color grading is a critical post-production process that transforms flat, log-encoded raw footage into emotionally resonant cinematic visuals. Existing automated methods act as static, black-box executors that directly output edited pixels, lacking both interpretability and the iterative control required by professionals. We introduce LumiVideo, an agentic system that mimics the cognitive workflow of professional colorists through four stages: Perception, Reasoning, Execution, and Reflection. Given only raw log video, LumiVideo autonomously produces a cinematic base grade by analyzing the scene's physical lighting and semantic content. Its Reasoning engine synergizes an LLM's internalized cinematic knowledge with a Retrieval-Augmented Generation (RAG) framework via a Tree of Thoughts (ToT) search to navigate the non-linear color parameter space. Rather than generating pixels, the system compiles the deduced parameters into industry-standard ASC-CDL configurations and a globally consistent 3D LUT, analytically guaranteeing temporal consistency. An optional Reflection loop then allows creators to refine the result via natural language feedback. We further introduce LumiGrade, the first log-encoded video benchmark for evaluating automated grading. Experiments show that LumiVideo approaches human expert quality in fully automatic mode while enabling precise iterative control when directed.

cs.CV↗

arXiv2025

MM-UNet: Morph Mamba U-shaped Convolutional Networks for Retinal Vessel Segmentation

Accurate detection of retinal vessels plays a critical role in reflecting a wide range of health status indicators in the clinical diagnosis of ocular diseases. Recently, advances in deep learning have led to a surge in retinal vessel segmentation methods, which have significantly contributed to the quantitative analysis of vascular morphology. However, retinal vasculature differs significantly from conventional segmentation targets in that it consists of extremely thin and branching structures, whose global morphology varies greatly across images. These characteristics continue to pose challenges to segmentation precision and robustness. To address these issues, we propose MM-UNet, a novel architecture tailored for efficient retinal vessel segmentation. The model incorporates Morph Mamba Convolution layers, which replace pointwise convolutions to enhance branching topological perception through morph, state-aware feature sampling. Additionally, Reverse Selective State Guidance modules integrate reverse guidance theory with state-space modeling to improve geometric boundary awareness and decoding efficiency. Extensive experiments conducted on two public retinal vessel segmentation datasets demonstrate the superior performance of the proposed method in segmentation accuracy. Compared to the existing approaches, MM-UNet achieves F1-score gains of 1.64 % on DRIVE and 1.25 % on STARE, demonstrating its effectiveness and advancement. The project code is public via https://github.com/liujiawen-jpg/MM-UNet.

cs.CV↗

arXiv2025

Evolvable Graph Diffusion Optimal Transport with Pattern-Specific Alignment for Brain Connectome Modeling

Network analysis of human brain connectivity indicates that individual differences in cognitive abilities arise from neurobiological mechanisms inherent in structural and functional brain networks. Existing studies routinely treat structural connectivity (SC) as optimal or fixed topological scaffolds for functional connectivity (FC), often overlooking higher-order dependencies between brain regions and limiting the modeling of complex cognitive processes. Besides, the distinct spatial organizations of SC and FC complicate direct integration, as naive alignment may distort intrinsic nonlinear patterns of brain connectivity. In this study, we propose a novel framework called Evolvable Graph Diffusion Optimal Transport with Pattern-Specific Alignment (EDT-PA), designed to identify disease-specific connectome patterns and classify brain disorders. To accurately model high-order structural dependencies, EDT-PA incorporates a spectrum of evolvable modeling blocks to dynamically capture high-order dependencies across brain regions. Additionally, a Pattern-Specific Alignment mechanism employs optimal transport to align structural and functional representations in a geometry-aware manner. By incorporating a Kolmogorov-Arnold network for flexible node aggregation, EDT-PA is capable of modeling complex nonlinear interactions among brain regions for downstream classification. Extensive evaluations on the REST-meta-MDD and ADNI datasets demonstrate that EDT-PA outperforms state-of-the-art methods, offering a more effective framework for revealing structure-function misalignments and disorder-specific subnetworks in brain disorders. The project of this work is released via this link.

q-bio.NC↗

arXiv2025

HWA-UNETR: Hierarchical Window Aggregate UNETR for 3D Multimodal Gastric Lesion Segmentation

Multimodal medical image segmentation faces significant challenges in the context of gastric cancer lesion analysis. This clinical context is defined by the scarcity of independent multimodal datasets and the imperative to amalgamate inherently misaligned modalities. As a result, algorithms are constrained to train on approximate data and depend on application migration, leading to substantial resource expenditure and a potential decline in analysis accuracy. To address those challenges, we have made two major contributions: First, we publicly disseminate the GCM 2025 dataset, which serves as the first large-scale, open-source collection of gastric cancer multimodal MRI scans, featuring professionally annotated FS-T2W, CE-T1W, and ADC images from 500 patients. Second, we introduce HWA-UNETR, a novel 3D segmentation framework that employs an original HWA block with learnable window aggregation layers to establish dynamic feature correspondences between different modalities' anatomical structures, and leverages the innovative tri-orientated fusion mamba mechanism for context modeling and capturing long-range spatial dependencies. Extensive experiments on our GCM 2025 dataset and the publicly BraTS 2021 dataset validate the performance of our framework, demonstrating that the new approach surpasses existing methods by up to 1.68\% in the Dice score while maintaining solid robustness. The dataset and code are public via https://github.com/JeMing-creater/HWA-UNETR.

eess.IV↗

arXiv2025

FunduSAM: A Specialized Deep Learning Model for Enhanced Optic Disc and Cup Segmentation in Fundus Images

The Segment Anything Model (SAM) has gained popularity as a versatile image segmentation method, thanks to its strong generalization capabilities across various domains. However, when applied to optic disc (OD) and optic cup (OC) segmentation tasks, SAM encounters challenges due to the complex structures, low contrast, and blurred boundaries typical of fundus images, leading to suboptimal performance. To overcome these challenges, we introduce a novel model, FunduSAM, which incorporates several Adapters into SAM to create a deep network specifically designed for OD and OC segmentation. The FunduSAM utilizes Adapter into each transformer block after encoder for parameter fine-tuning (PEFT). It enhances SAM's feature extraction capabilities by designing a Convolutional Block Attention Module (CBAM), addressing issues related to blurred boundaries and low contrast. Given the unique requirements of OD and OC segmentation, polar transformation is used to convert the original fundus OD images into a format better suited for training and evaluating FunduSAM. A joint loss is used to achieve structure preservation between the OD and OC, while accurate segmentation. Extensive experiments on the REFUGE dataset, comprising 1,200 fundus images, demonstrate the superior performance of FunduSAM compared to five mainstream approaches.

cs.CV↗

arXiv2024

Multi-RoI Human Mesh Recovery with Camera Consistency and Contrastive Losses

Besides a 3D mesh, Human Mesh Recovery (HMR) methods usually need to estimate a camera for computing 2D reprojection loss. Previous approaches may encounter the following problem: both the mesh and camera are not correct but the combination of them can yield a low reprojection loss. To alleviate this problem, we define multiple RoIs (region of interest) containing the same human and propose a multiple-RoI-based HMR method. Our key idea is that with multiple RoIs as input, we can estimate multiple local cameras and have the opportunity to design and apply additional constraints between cameras to improve the accuracy of the cameras and, in turn, the accuracy of the corresponding 3D mesh. To implement this idea, we propose a RoI-aware feature fusion network by which we estimate a 3D mesh shared by all RoIs as well as local cameras corresponding to the RoIs. We observe that local cameras can be converted to the camera of the full image through which we construct a local camera consistency loss as the additional constraint imposed on local cameras. Another benefit of introducing multiple RoIs is that we can encapsulate our network into a contrastive learning framework and apply a contrastive loss to regularize the training of our network. Experiments demonstrate the effectiveness of our multi-RoI HMR method and superiority to recent prior arts. Our code is available at https://github.com/CptDiaos/Multi-RoI.

cs.CV↗

arXiv2024

Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection

Video Anomaly Detection (VAD) has been extensively studied under the settings of One-Class Classification (OCC) and Weakly-Supervised learning (WS), which however both require laborious human-annotated normal/abnormal labels. In this paper, we study Unsupervised VAD (UVAD) that does not depend on any label by combining OCC and WS into a unified training framework. Specifically, we extend OCC to weighted OCC (wOCC) and propose a wOCC-WS interleaving training module, where the two models automatically generate pseudo-labels for each other. We face two challenges to make the combination effective: (1) Models' performance fluctuates occasionally during the training process due to the inevitable randomness of the pseudo labels. (2) Thresholds are needed to divide pseudo labels, making the training depend on the accuracy of user intervention. For the first problem, we propose to use wOCC requiring soft labels instead of OCC trained with hard zero/one labels, as soft labels exhibit high consistency throughout different training cycles while hard labels are prone to sudden changes. For the second problem, we repeat the interleaving training module multiple times, during which we propose an adaptive thresholding strategy that can progressively refine a rough threshold to a relatively optimal threshold, which reduces the influence of user interaction. A benefit of employing OCC and WS methods to compose a UVAD method is that we can incorporate the most recent OCC or WS model into our framework. Experiments demonstrate the effectiveness of the proposed UVAD framework.

cs.CV↗

arXiv2024

Fuse4Seg: Image Fusion for Multi-Modal Medical Segmentation via Bi-level Optimization

Multi-modal medical image fusion is traditionally optimized for human visual perception, aiming to maximize generic contrast and structural fidelity. However, when these visually pleasing fused images are deployed in automated clinical workflows, this visual-semantic discrepancy causes task-agnostic feature degradation, inadvertently smoothing out critical, high-frequency tumor boundaries. To bridge this semantic gap, we propose Fuse4Seg, a novel framework that reformulates multi-modal fusion as a cooperative bi-level optimization problem with medical segmentation. Rather than relying on rigid visual metrics, our fusion leader dynamically updates its feature extraction strategy driven directly by semantic gradients backpropagated from the downstream segmentation follower. To guarantee robust physical fidelity alongside semantic utility, we design a frequency-decoupled architecture stringently regularized by a Frequency Decomposition Loss and a Spatial Gradient Loss. This explicit physical anchor prevents anatomical distortion and ensures the lossless preservation of task-critical details. Extensive experiments demonstrate that our task-aware, single-channel fused prior generalizes seamlessly across diverse multi-scale modalities. More impressively, it remarkably surpasses contemporary dual-channel segmentation state-of-the-arts while explicitly providing a readable, "glass-box" physical image to foster clinical visual interpretability and trust.

cs.CV↗

arXiv2024

Accelerate Neural Subspace-Based Reduced-Order Solver of Deformable Simulation by Lipschitz Optimization

Reduced-order simulation is an emerging method for accelerating physical simulations with high DOFs, and recently developed neural-network-based methods with nonlinear subspaces have been proven effective in diverse applications as more concise subspaces can be detected. However, the complexity and landscape of simulation objectives within the subspace have not been optimized, which leaves room for enhancement of the convergence speed. This work focuses on this point by proposing a general method for finding optimized subspace mappings, enabling further acceleration of neural reduced-order simulations while capturing comprehensive representations of the configuration manifolds. We achieve this by optimizing the Lipschitz energy of the elasticity term in the simulation objective, and incorporating the cubature approximation into the training process to manage the high memory and time demands associated with optimizing the newly introduced energy. Our method is versatile and applicable to both supervised and unsupervised settings for optimizing the parameterizations of the configuration manifolds. We demonstrate the effectiveness of our approach through general cases in both quasi-static and dynamics simulations. Our method achieves acceleration factors of up to 6.83 while consistently preserving comparable simulation accuracy in various cases, including large twisting, bending, and rotational deformations with collision handling. This novel approach offers significant potential for accelerating physical simulations, and can be a good add-on to existing neural-network-based solutions in modeling complex deformable objects.

cs.LG↗