arXiv subjects

Zhen Yu

Publications and source records attributed to Zhen Yu.

At least 19 recordsLinked to original sources

arXiv2026

HandMimicX: Learning Human-Like Dexterous Manipulation via an Object-Centric Policy from Egocentric Videos

Learning dexterous manipulation from human videos remains an open challenge, particularly in the context of transferring a single demonstration into a spatially generalizable robotic skill and maintaining physically plausible human-like interactions. Unlike prior works that emphasize hand-motion imitation, we introduce an object-centric framework for acquiring dexterous skills from egocentric human RGB-D videos. Within our framework, we formulate the reinforcement learning (RL) objective in terms of object motion to decouple the underlying skill from the specific hand trajectory and impose constraints on hand-object interaction states to promote more anatomically natural hand configurations. Extensive experiments in simulation and on real robots demonstrate that our method enables efficient learning from human videos and generalizable skill transfer across novel spatial configurations.

cs.RO↗

arXiv2026

A generalizable structural brain MRI foundation model via dual-priority federated pretraining

Foundation models hold promise for generalizable analysis of structural brain magnetic resonance imaging (MRI) scans across diverse populations and imaging conditions. However, existing models typically rely on centralized pretraining using data pooled across cohorts, which is constrained by privacy and data-governance requirements. Moreover, larger cohorts can dominate optimization, underutilizing anatomical information from smaller cohorts and limiting generalization. Here we present BrainFedFM, a structural brain MRI foundation model federatively pretrained on 164,707 three-dimensional scans drawn from diverse real-world data distributions and organized across 42 federated sites. BrainFedFM uses dual-priority federated pretraining, in which spatial-priority masking emphasizes informative anatomical regions during local training, while site-priority aggregation adaptively weights contributions during global aggregation. Across 20 downstream datasets spanning 17 classification, regression and segmentation tasks, BrainFedFM achieved the state-of-the-art performance across seven foundation models, including four centralized models, while showing consistent advantages in classification and regression tasks and strong robustness under underrepresented populations and challenging imaging conditions. These findings demonstrate the generalizability of BrainFedFM and highlight federated pretraining as a practical strategy for developing neuroimaging foundation models from distributed data without pooling raw images.

cs.CV↗

arXiv2026

Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT

Image Bitstream Fine-grained Understanding (IBFU) aims to directly perform fine-grained classification and semantic description generation from encoded image byte sequences. In contrast to conventional pixel-domain visual understanding, IBFU conducts semantic analysis without fully decoding images into the pixel domain. Since pixel-level visual content is not explicitly reconstructed during inference, this paradigm reduces visual exposure within the processing pipeline and suits privacy-friendly Artificial Intelligence of Things (AIoT) applications. In this paper, we propose Bitstream Fine-grained Generator (BFG), a novel foundation model tailored for IBFU. BFG consists of two main components: a Bitstream Semantic Encoder (BSeE) and a Fine-grained Semantic Generator (FSeG). BSeE directly models semantic representations from encoded image bitstreams without explicit pixel reconstruction, while FSeG transforms the extracted bitstream semantics into detailed natural-language descriptions through autoregressive generation. To train BFG and comprehensively evaluate IBFU in practical AIoT scenarios, where image bitstreams may suffer corruption during transmission and storage, we construct a large-scale Corrupted-bitstream Fine-grained Understanding dataset (CFU-D), containing both intact bitstreams and corrupted variants across multiple corruption types and severity levels. Experiments show that BFG maintains stable fine-grained caption generation under bitstream corruption. For example, the performance only has slight change from 0.6339 to 0.6077 in terms of average CIDEr score on Stanford Dogs Caption dataset, while vision-language models, such as Qwen-VL-Chat, BLIP-2, GLM, Gemini, and GPT suffer severe performance decrease. This paper provides a practical paradigm for privacy-friendly fine-grained understanding in AIoT.

cs.CV↗

arXiv2026

BiNar: Bitstream Native Restorer for Bitstream-corrupted Image Restoration

Bitstream-corrupted image restoration (BCIR) aims to reconstruct faithful images from corrupted compressed bitstreams. However, corruption occurs in bitstream-domain may lead to unpredictable error propagation and distortion amplification in pixel-domain, and even result in complete undecodability by standard decoders, posing significant challenge to existing image restoration paradigms. To address this challenge, we propose Bitstream Native Restorer (BiNar), a generative restoration framework that leverages fine-grained bitstream-native semantics to guide bitstream-corrupted image restoration. In BiNar, Bitstream Semantic Modeling (BSeM) extracts robust informative semantics and models sequential bytes directly from corrupted bitstream, enabling to generate fine-grained bitstream descriptions without relying on pixel decoding. Based on the descriptions,the Corruption-adaptive Multimodal Semantic Aggregation (CMSA) further extracts adaptive visual modal cues in decoded corrupted images and aggregates to bitstream descriptions. The multimodal aggregated fine-grained descriptions can serve as coherent restoration guidance. Finally, Blind Corruption Localization (BCoL) exploits the segmentation prior of visual foundation models to identify and locate error regions that requires recovery in corrupted images. The located error regions and the fine-grained descriptions jointly serve as visual prompt and language prompt of diffusion models image restoration, respectively. Extensive experiments under diverse bitstream corruption conditions show that BiNar outperforms all State-of-the-arts image restoration models regardless of perceptual quality or objective quality. Ablation studies demonstrate the effectiveness of fine-grained bitstream-native semantics in BCIR task.

cs.CV↗

arXiv2026

ByteAction: Byte-space Action Recognition Foundation Model

Byte-space Action Recognition (BAR) aims to recognize human actions directly from compressed image bitstreams without any pixel decoding. By operating entirely in byte space, BAR is inherently independent of file integrity and pixel-level reconstruction, making it naturally applicable to privacy-sensitive scenarios and robust against bitstream corruption. In this paper, we propose ByteAction, a BAR foundation model that achieves accurate action recognition on corrupted image bitstreams. ByteAction follows a dual-view byte-level recognition framework. It constructs weakly and strongly corrupted bitstream views, which are augmented by Bitstream Pattern Augmentation (BPA) and encoded with a shared ByteFormer backbone. The model is optimized with both classification and corruption consistency objectives. Specifically, we propose Bitstream Pattern Augmentation (BPA), which reshapes one-dimensional byte sequences into two-dimensional byte matrix and applies region-level erasure to encourage the model to learn robust cross-region byte dependencies. We further propose a Corruption Consistency Training strategy that constrains the model to maintain stable predictions across different corruption severities through bidirectional KL divergence. Experiments on the image bitstream from Stanford40, PPMI, and PASCAL VOC 2012 Action demonstrate that ByteAction achieves state-of-the-art corruption robustness across all scenarios while maintaining competitive intact bitstream performance.

cs.CV↗

arXiv2026

Latent Ordinal Evidence, Misaligned Outputs: Inference-Time Ordinal Lens Alignment for Multimodal LLMs

Multimodal LLMs apply the language model interface to visual inputs, where ordinal regression tasks such as age estimation, image quality assessment, and disease grading require autoregressive decisions over ordered class labels. We ask whether MLLMs reliably convert internal ordinal evidence into ordered digit-token outputs. Across four ordinal benchmarks and four MLLM backbones, ordinal labels are linearly recoverable from hidden states with Spearman correlation up to 0.938, and a task-designed prompt further sharpens this structure. Yet native digit-token outputs weakly expose it: the unembedding matrix filters the ordinal direction, and the digit-token row space retains below 1.15% across all 16 model-dataset combinations, with a 16 to 77 absolute-point accuracy gap between linear-probe and native outputs. We introduce Ordinal Lens Alignment (OLA), a frozen-backbone inference-time method that trains lightweight W_S-anchored lenses on mid-to-deep decoder layers, fuses them into an ordinal distribution, and corrects only digit-token logits at generation. OLA outperforms the SOTA LoRA-tuned OrderChain baseline in most settings while keeping the MLLM frozen, surpasses discriminative ordinal baselines in most cells, and improves over an offline lens in every setting.

cs.CV↗

arXiv2026

Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training

While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing multimodal pre-training methods underutilize this potential due to semantic-agnostic designs that treat tabular inputs as flat vectors and employ unstable continuous regression objectives. To overcome this, we propose a novel semantic-aware framework explicitly modeling the intrinsic two-dimensional structure of tabular data. First, addressing the inter-feature hierarchy of varying diagnostic importance, we introduce Importance-Aware Adaptive Masking to construct a label-free curriculum prioritizing salient features. Second, addressing the intra-feature continuity-discreteness duality, we propose a Soft-Label Discretized Module that replaces unstable numerical regression with stable distribution matching, thereby mathematically preserving ordinal relationships. Extensive experiments across large-scale dermatology (SLICE-3D, HOP) and ophthalmology (EyePACS) datasets establish a new state-of-the-art (SOTA), demonstrating exceptional robustness and cross-domain generalizability.

cs.CV↗

arXiv2026

MambaLSTM: A Spatio-Temporal Framework for Enhanced Traffic Accident Risk Prediction

In traffic accident risk prediction, most studies overlook the extra noise that could be incorporated when fusing temporal features into spatial features, and some models struggle to capture global correlations among spatial regions. To address these challenges, we propose a novel traffic accident risk prediction framework named MambaLSTM. First, we develop a squeeze-and-excitation temporal feature fusion module to integrate temporal information without compromising spatio-temporal integrity. Second, we introduce a new patch embedding module for effectively capturing semantic relationships among spatially adjacent regions. Additionally, we introduce a Mamba block based on state-space models to model global spatial semantics in urban regions. Finally, we propose a MambaLSTM unit to efficiently capture long- and short-term temporal dependencies for identifying dynamic risk patterns. Extensive experiments on real-world datasets demonstrate the proposed model's superiority over state-of-the-art methods. The code is released at https://github.com/Zhenzovo/MambaLSTM.

cs.LG↗

arXiv2026

RoadFed: A Multimodal Federated Learning System for Improving Road Safety

Internet of Things (IoTs) have been widely applied in Collaborative Intelligent Transportation Systems (C-ITS) for the prevention of road accidents. As one of the primary causes of road accidents in C-ITS, the efficient detection and early alarm of road hazards are of paramount importance. Given the importance, extensive research has explored this topic and obtained favorable results. However, most existing solutions only explore single-modality data, struggle with high computation and communication overhead, or suffer from the curse of high dimensionality in their privacy-preserving methodologies. To overcome these obstacles, in this paper, we introduce RoadFed, an innovative and private multimodal Federated learning-based system tailored for intelligent Road hazard detection and alarm. This framework encompasses an innovative Multimodal Road Hazard Detector, a communication-efficient federated learning approach, and a customized low-error-rate local differential privacy method crafted for high dimensional multimodal data. Experimental results reveal that the proposed RoadFed surpasses most existing systems in the self-gathered real-world and CrisisMMD public datasets. In particular, RoadFed achieves an accuracy of 96.42% with a mere 0.0351 seconds of latency and its communication cost is up to 1,000 times lower than existing systems in this field. It facilitates collaborative training with non-iid high dimensional multimodal real-world data across various data modalities on multiple edges while ensuring privacy preservation for road users.

cs.CE↗

arXiv2026

Interpretable Machine Learning for Antepartum Prediction of Pregnancy-Associated Thrombotic Microangiopathy Using Routine Longitudinal Laboratory Data

Background: Pregnancy-associated thrombotic microangiopathy (P-TMA) is rare but life-threatening. Early risk prediction before overt clinical presentation remains challenging, as the associated laboratory abnormalities are subtle, multidimensional, and frequently masked by common physiological changes such as gestational thrombocytopenia and pregnancy-related proteinuria, thus overlapping heavily with benign obstetric and renal conditions. This complexity is poorly captured by univariate or rule-based approaches; however, it is addressable by machine learning, which can extract latent, time-dependent risk signatures from longitudinal clinical tests. Methods: This retrospective study included 300 pregnancies comprising 142 P-TMA cases and 158 controls. After exclusion of identifiers and non-informative variables, 146 longitudinal laboratory predictors were retained. Participants were divided into a training cohort (80%) and a held-out test cohort (20%) using stratified sampling. Five algorithms were evaluated: logistic regression, support vector machine with radial basis function kernel, random forest, extra trees, and gradient boosting. The final model was selected by mean cross-validated AUROC, refitted on the full training cohort, and evaluated once in the held-out test cohort. Interpretability analyses examined global feature importance and distributional patterns of leading predictors. Results: Gradient boosting was prespecified by cross-validation in the training cohort. The model achieved an AUROC of 0.872 (95% CI: 0.769-0.952) and an AUPRC of 0.883 (95% CI: 0.780-0.959) in a held-out test cohort, with sensitivity of 0.750 and specificity of 0.812. Conclusions: Longitudinal clinical laboratory tests obtained during routine care contained informative and clinically plausible signals for P-TMA risk. Notably, cystatin C at week 6 showed promise as an early monitoring indicator.

cs.LG↗

arXiv2025

Magnetism and Correlated Electrons in LaCr$_2$Ge$_2$N

We report the synthesis, structure and physical properties of a new quaternary nitride LaCr$_2$Ge$_2$N. The compound crystallizes in the CeCr$_2$Si$_2$C-type structure (P4/mmm), featuring distinctive Cr$_2$N square sheets within Cr$_2$Ge$_2$N block layers. Physical characterizations reveal enhanced electron correlations evidenced by a Sommerfeld coefficient substantially larger than band calculations and pressure-induced deviation from Fermi-liquid behavior. Magnetic measurements show short-range antiferromagnetic correlations developing around 460 K, followed by long-range magnetic ordering at 14 K. Additionally, subtle anomalies at 378 K suggest possible electronic ordering. First-principles calculations reveal nearly-flat Cr-3d bands near the Fermi level and predict a striped antiferromagnetic ground state. This work demonstrates how electron count variation in the CeCr$_2$Si$_2$C-type structure family leads to magnetic ordering in LaCr$_2$Ge$_2$N, contrasting with the paramagnetic behavior of LnCr$_2$Si$_2$C compounds.

cond-mat.str-el↗

arXiv2025

FedAPTA: Federated Multi-task Learning for Heterogeneous Devices with Adaptive Layer-wise Pruning and Task-aware Aggregation

Federated Learning (FL) has shown considerable promise in Machine Learning (ML) across numerous devices for privacy protection, efficient data utilization, and dynamic collaboration. However, mobile devices typically have limited and heterogeneous computational capabilities, and different devices may even have different tasks. This client heterogeneity is a major bottleneck hindering the practical application of FL. Existing work mainly focuses on mitigating FL's computation and communication overhead of a single task while overlooking the computing resource heterogeneity issue of different devices in FL. To tackle this, we design FedAPTA, a federated multi-task learning framework. FedAPTA overcomes computing resource heterogeneity through the developed layer-wise model pruning technique, which reduces local model size while considering both data and device heterogeneity. To aggregate structurally heterogeneous local models of different tasks, we introduce a heterogeneous model recovery strategy and a task-aware model aggregation method that enables the aggregation through infilling local model architecture with the shared global model and clustering local models according to their specific tasks. We deploy FedAPTA on a realistic FL platform and benchmark it against nine SOTA FL methods. The experimental outcomes demonstrate that the proposed FedAPTA considerably outperforms the state-of-the-art FL methods by up to 4.23\%. Our code is available at https://github.com/Zhenzovo/FedAPTA.

cs.DC↗

arXiv2025

RetinaGuard: Obfuscating Retinal Age in Fundus Images for Biometric Privacy Preserving

The integration of AI with medical images enables the extraction of implicit image-derived biomarkers for a precise health assessment. Recently, retinal age, a biomarker predicted from fundus images, is a proven predictor of systemic disease risks, behavioral patterns, aging trajectory and even mortality. However, the capability to infer such sensitive biometric data raises significant privacy risks, where unauthorized use of fundus images could lead to bioinformation leakage, breaching individual privacy. In response, we formulate a new research problem of biometric privacy associated with medical images and propose RetinaGuard, a novel privacy-enhancing framework that employs a feature-level generative adversarial masking mechanism to obscure retinal age while preserving image visual quality and disease diagnostic utility. The framework further utilizes a novel multiple-to-one knowledge distillation strategy incorporating a retinal foundation model and diverse surrogate age encoders to enable a universal defense against black-box age prediction models. Comprehensive evaluations confirm that RetinaGuard successfully obfuscates retinal age prediction with minimal impact on image quality and pathological feature representation. RetinaGuard is also flexible for extension to other medical image derived biomarkers. RetinaGuard is also flexible for extension to other medical image biomarkers.

cs.CV↗

arXiv2025

Controllable Skin Synthesis via Lesion-Focused Vector Autoregression Model

Skin images from real-world clinical practice are often limited, resulting in a shortage of training data for deep-learning models. While many studies have explored skin image synthesis, existing methods often generate low-quality images and lack control over the lesion's location and type. To address these limitations, we present LF-VAR, a model leveraging quantified lesion measurement scores and lesion type labels to guide the clinically relevant and controllable synthesis of skin images. It enables controlled skin synthesis with specific lesion characteristics based on language prompts. We train a multiscale lesion-focused Vector Quantised Variational Auto-Encoder (VQVAE) to encode images into discrete latent representations for structured tokenization. Then, a Visual AutoRegressive (VAR) Transformer trained on tokenized representations facilitates image synthesis. Lesion measurement from the lesion region and types as conditional embeddings are integrated to enhance synthesis fidelity. Our method achieves the best overall FID score (average 0.74) among seven lesion types, improving upon the previous state-of-the-art (SOTA) by 6.3%. The study highlights our controllable skin synthesis model's effectiveness in generating high-fidelity, clinically relevant synthetic skin images. Our framework code is available at https://github.com/echosun1996/LF-VAR.

cs.CV↗

arXiv2025

Flexible Sampling for Long-tailed Skin Lesion Classification

Most of the medical tasks naturally exhibit a long-tailed distribution due to the complex patient-level conditions and the existence of rare diseases. Existing long-tailed learning methods usually treat each class equally to re-balance the long-tailed distribution. However, considering that some challenging classes may present diverse intra-class distributions, re-balancing all classes equally may lead to a significant performance drop. To address this, in this paper, we propose a curriculum learning-based framework called Flexible Sampling for the long-tailed skin lesion classification task. Specifically, we initially sample a subset of training data as anchor points based on the individual class prototypes. Then, these anchor points are used to pre-train an inference model to evaluate the per-class learning difficulty. Finally, we use a curriculum sampling module to dynamically query new samples from the rest training samples with the learning difficulty-aware sampling probability. We evaluated our model against several state-of-the-art methods on the ISIC dataset. The results with two long-tailed settings have demonstrated the superiority of our proposed training strategy, which achieves a new benchmark for long-tailed skin lesion classification.

cs.CV↗

arXiv2025

MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment

Dermatological diagnosis represents a complex multimodal challenge that requires integrating visual features with specialized clinical knowledge. While vision-language pretraining (VLP) has advanced medical AI, its effectiveness in dermatology is limited by text length constraints and the lack of structured texts. In this paper, we introduce MAKE, a Multi-Aspect Knowledge-Enhanced vision-language pretraining framework for zero-shot dermatological tasks. Recognizing that comprehensive dermatological descriptions require multiple knowledge aspects that exceed standard text constraints, our framework introduces: (1) a multi-aspect contrastive learning strategy that decomposes clinical narratives into knowledge-enhanced sub-texts through large language models, (2) a fine-grained alignment mechanism that connects subcaptions with diagnostically relevant image features, and (3) a diagnosis-guided weighting scheme that adaptively prioritizes different sub-captions based on clinical significance prior. Through pretraining on 403,563 dermatological image-text pairs collected from education resources, MAKE significantly outperforms state-of-the-art VLP models on eight datasets across zero-shot skin disease classification, concept annotation, and cross-modal retrieval tasks. Our code will be made publicly available at https: //github.com/SiyuanYan1/MAKE.

cs.CV↗

arXiv2025

A Multimodal Vision Foundation Model for Clinical Dermatology

Diagnosing and treating skin diseases require advanced visual skills across domains and the ability to synthesize information from multiple imaging modalities. While current deep learning models excel at specific tasks like skin cancer diagnosis from dermoscopic images, they struggle to meet the complex, multimodal requirements of clinical practice. Here, we introduce PanDerm, a multimodal dermatology foundation model pretrained through self-supervised learning on over 2 million real-world skin disease images from 11 clinical institutions across 4 imaging modalities. We evaluated PanDerm on 28 diverse benchmarks, including skin cancer screening, risk stratification, differential diagnosis of common and rare skin conditions, lesion segmentation, longitudinal monitoring, and metastasis prediction and prognosis. PanDerm achieved state-of-the-art performance across all evaluated tasks, often outperforming existing models when using only 10% of labeled data. We conducted three reader studies to assess PanDerm's potential clinical utility. PanDerm outperformed clinicians by 10.2% in early-stage melanoma detection through longitudinal analysis, improved clinicians' skin cancer diagnostic accuracy by 11% on dermoscopy images, and enhanced non-dermatologist healthcare providers' differential diagnosis by 16.5% across 128 skin conditions on clinical photographs. These results demonstrate PanDerm's potential to improve patient care across diverse clinical scenarios and serve as a model for developing multimodal foundation models in other medical specialties, potentially accelerating the integration of AI support in healthcare. The code can be found at https://github.com/SiyuanYan1/PanDerm.

cs.CV↗

arXiv2025

scDD: Latent Codes Based scRNA-seq Dataset Distillation with Foundation Model Knowledge

Single-cell RNA sequencing (scRNA-seq) technology has profiled hundreds of millions of human cells across organs, diseases, development and perturbations to date. However, the high-dimensional sparsity, batch effect noise, category imbalance, and ever-increasing data scale of the original sequencing data pose significant challenges for multi-center knowledge transfer, data fusion, and cross-validation between scRNA-seq datasets. To address these barriers, (1) we first propose a latent codes-based scRNA-seq dataset distillation framework named scDD, which transfers and distills foundation model knowledge and original dataset information into a compact latent space and generates synthetic scRNA-seq dataset by a generator to replace the original dataset. Then, (2) we propose a single-step conditional diffusion generator named SCDG, which perform single-step gradient back-propagation to help scDD optimize distillation quality and avoid gradient decay caused by multi-step back-propagation. Meanwhile, SCDG ensures the scRNA-seq data characteristics and inter-class discriminability of the synthetic dataset through flexible conditional control and generation quality assurance. Finally, we propose a comprehensive benchmark to evaluate the performance of scRNA-seq dataset distillation in different data analysis tasks. It is validated that our proposed method can achieve 7.61% absolute and 15.70% relative improvement over previous state-of-the-art methods on average task.

cs.LG↗