arXiv subjects

Fan Zhang

Publications and source records attributed to Fan Zhang.

At least 307 records · Page 17Linked to original sources

arXiv2025

FunOTTA: On-the-Fly Adaptation on Cross-Domain Fundus Image via Stable Test-time Training

Fundus images are essential for the early screening and detection of eye diseases. While deep learning models using fundus images have significantly advanced the diagnosis of multiple eye diseases, variations in images from different imaging devices and locations (known as domain shifts) pose challenges for deploying pre-trained models in real-world applications. To address this, we propose a novel Fundus On-the-fly Test-Time Adaptation (FunOTTA) framework that effectively generalizes a fundus image diagnosis model to unseen environments, even under strong domain shifts. FunOTTA stands out for its stable adaptation process by performing dynamic disambiguation in the memory bank while minimizing harmful prior knowledge bias. We also introduce a new training objective during adaptation that enables the classifier to incrementally adapt to target patterns with reliable class conditional estimation and consistency regularization. We compare our method with several state-of-the-art test-time adaptation (TTA) pipelines. Experiments on cross-domain fundus image benchmarks across two diseases demonstrate the superiority of the overall framework and individual components under different backbone networks. Code is available at https://github.com/Casperqian/FunOTTA.

cs.CV↗

arXiv2025

Affordance-based Robot Manipulation with Flow Matching

We present a framework for assistive robot manipulation, which focuses on two fundamental challenges: first, efficiently adapting large-scale models to downstream scene affordance understanding tasks, especially in daily living scenarios where gathering multi-task data involving humans requires strenuous effort; second, effectively learning robot action trajectories by grounding the visual affordance model. We tackle the first challenge by employing a parameter-efficient prompt tuning method that prepends learnable text prompts to the frozen vision model to predict manipulation affordances in multi-task scenarios. Then we propose to learn robot action trajectories guided by affordances in a supervised flow matching method. Flow matching represents a robot visuomotor policy as a conditional process of flowing random waypoints to desired robot action trajectories. Finally, we introduce a real-world dataset with 10 tasks across Activities of Daily Living to test our framework. Our extensive evaluation highlights that the proposed prompt tuning method for learning manipulation affordance achieves competitive performance and even outperforms some other finetuning protocols across data scales, while satisfying parameter efficiency. Learning multi-task robot action trajectories with flow matching leads to consistently favorable results in several robot manipulation benchmarks than some alternative behavior cloning methods. This includes more stable training and evaluation, and noticeably faster inference, while maintaining comparable generalization performance to diffusion policy, where flow matching performs marginally better in most cases. Our framework seamlessly unifies affordance learning and action generation with flow matching for robot manipulation.

cs.RO↗

arXiv2025

DMVFC: Deep Learning Based Functionally Consistent Tractography Fiber Clustering Using Multimodal Diffusion MRI and Functional MRI

Tractography fiber clustering using diffusion MRI (dMRI) is a crucial method for white matter (WM) parcellation to enable analysis of brains structural connectivity in health and disease. Current fiber clustering strategies primarily use the fiber geometric characteristics (i.e., the spatial trajectories) to group similar fibers into clusters, while neglecting the functional and microstructural information of the fiber tracts. There is increasing evidence that neural activity in the WM can be measured using functional MRI (fMRI), providing potentially valuable multimodal information for fiber clustering to enhance its functional coherence. Furthermore, microstructural features such as fractional anisotropy (FA) can be computed from dMRI as additional information to ensure the anatomical coherence of the clusters. In this paper, we develop a novel deep learning fiber clustering framework, namely Deep Multi-view Fiber Clustering (DMVFC), which uses joint multi-modal dMRI and fMRI data to enable functionally consistent WM parcellation. DMVFC can effectively integrate the geometric and microstructural characteristics of the WM fibers with the fMRI BOLD signals along the fiber tracts. DMVFC includes two major components: (1) a multi-view pretraining module to compute embedding features from each source of information separately, including fiber geometry, microstructure measures, and functional signals, and (2) a collaborative fine-tuning module to simultaneously refine the differences of embeddings. In the experiments, we compare DMVFC with two state-of-the-art fiber clustering methods and demonstrate superior performance in achieving functionally meaningful and consistent WM parcellation results.

eess.IV↗

arXiv2025

Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond

Multimodal Large Language Models (MLLMs) have revolutionized numerous research fields, including computer vision and affective computing. As a pivotal challenge in this interdisciplinary domain, facial expression recognition (FER) has evolved from separate, domain-specific models to more unified approaches. One promising avenue to unify FER tasks is converting conventional FER datasets into visual question-answering (VQA) formats, enabling the direct application of powerful generalist MLLMs for inference. However, despite the success of cutting-edge MLLMs in various tasks, their performance on FER tasks remains largely unexplored. To address this gap, we provide FERBench, a systematic benchmark that incorporates 20 state-of-the-art MLLMs across four widely used FER datasets. Our results reveal that, while MLLMs exhibit good classification performance, they still face significant limitations in reasoning and interpretability. To this end, we introduce post-training strategies aimed at enhancing the facial expression reasoning capabilities of MLLMs. Specifically, we curate two high-quality and large-scale datasets: UniFER-CoT-230K for cold-start initialization and UniFER-RLVR-360K for reinforcement learning with verifiable rewards (RLVR), respectively. Building upon them, we develop a unified and interpretable FER foundation model termed UniFER-7B, which outperforms many open-sourced and closed-source generalist MLLMs (e.g., Gemini-2.5-Pro and Qwen2.5-VL-72B).

cs.CV↗

arXiv2025

Robust Super-Capacity SRS Channel Inpainting via Diffusion Models

Accurate channel state information (CSI) is essential for reliable multiuser MIMO operation. In 5G NR, reciprocity-based beamforming via uplink Sounding Reference Signals (SRS) face resource and coverage constraints, motivating sparse non-uniform SRS allocation. Prior masked-autoencoder (MAE) approaches improve coverage but overfit to training masks and degrade under unseen distortions (e.g., additional masking, interference, clipping, non-Gaussian noise). We propose a diffusion-based channel inpainting framework that integrates system-model knowledge at inference via a likelihood-gradient term, enabling a single trained model to adapt across mismatched conditions. On standardized CDL channels, the score-based diffusion variant consistently outperforms a UNet score-model baseline and the one-step MAE under distribution shift, with improvements up to 14 dB NMSE in challenging settings (e.g., Laplace noise, user interference), while retaining competitive accuracy under matched conditions. These results demonstrate that diffusion-guided inpainting is a robust and generalizable approach for super-capacity SRS design in 5G NR systems.

eess.SP↗

arXiv2025

Emu3.5: Native Multimodal Models are World Learners

We introduce Emu3.5, a large-scale multimodal world model that natively predicts the next state across vision and language. Emu3.5 is pre-trained end-to-end with a unified next-token prediction objective on a corpus of vision-language interleaved data containing over 10 trillion tokens, primarily derived from sequential frames and transcripts of internet videos. The model naturally accepts interleaved vision-language inputs and generates interleaved vision-language outputs. Emu3.5 is further post-trained with large-scale reinforcement learning to enhance multimodal reasoning and generation. To improve inference efficiency, we propose Discrete Diffusion Adaptation (DiDA), which converts token-by-token decoding into bidirectional parallel prediction, accelerating per-image inference by about 20x without sacrificing performance. Emu3.5 exhibits strong native multimodal capabilities, including long-horizon vision-language generation, any-to-image (X2I) generation, and complex text-rich image generation. It also exhibits generalizable world-modeling abilities, enabling spatiotemporally consistent world exploration and open-world embodied manipulation across diverse scenarios and tasks. For comparison, Emu3.5 achieves performance comparable to Gemini 2.5 Flash Image (Nano Banana) on image generation and editing tasks and demonstrates superior results on a suite of interleaved generation tasks. We open-source Emu3.5 at https://github.com/baaivision/Emu3.5 to support community research.

cs.CV↗

arXiv2025

FedMAP: Personalised Federated Learning for Real Large-Scale Healthcare Systems

Federated learning (FL) promises to enable collaborative machine learning across healthcare sites whilst preserving data privacy. Practical deployment remains limited by statistical heterogeneity arising from differences in patient demographics, treatments, and outcomes, and infrastructure constraints. We introduce FedMAP, a personalised FL (PFL) framework that addresses heterogeneity through local Maximum a Posteriori (MAP) estimation with Input Convex Neural Network priors. These priors represent global knowledge gathered from other sites that guides the model while adapting to local data, and we provide a formal proof of convergence. Unlike many PFL methods that rely on fixed regularisation, FedMAP's prior adaptively learns patterns that capture complex inter-site relationships. We demonstrate improved performance compared to local training, FedAvg, and several PFL methods across three large-scale clinical datasets: 10-year cardiovascular risk prediction (CPRD, 387 general practitioner practices, 258,688 patients), iron deficiency detection (INTERVAL, 4 donor centres, 31,949 blood donors), and mortality prediction (eICU, 150 hospitals, 44,842 patients). FedMAP incorporates a three-tier design that enables participation across healthcare sites with varying infrastructure and technical capabilities, from full federated training to inference-only deployment. Geographical analysis reveals substantial equity improvements, with underperforming regions achieving up to 14.3% performance gains. This framework provides the first practical pathway for large-scale healthcare FL deployment, which ensures clinical sites at all scales can benefit, equity is enhanced, and privacy is retained.

cs.LG↗

arXiv2025

Uniform Discrete Diffusion with Metric Path for Video Generation

Continuous-space video generation has advanced rapidly, while discrete approaches lag behind due to error accumulation and long-context inconsistency. In this work, we revisit discrete generative modeling and present Uniform discRete diffuSion with metric pAth (URSA), a simple yet powerful framework that bridges the gap with continuous approaches for the scalable video generation. At its core, URSA formulates the video generation task as an iterative global refinement of discrete spatiotemporal tokens. It integrates two key designs: a Linearized Metric Path and a Resolution-dependent Timestep Shifting mechanism. These designs enable URSA to scale efficiently to high-resolution image synthesis and long-duration video generation, while requiring significantly fewer inference steps. Additionally, we introduce an asynchronous temporal fine-tuning strategy that unifies versatile tasks within a single model, including interpolation and image-to-video generation. Extensive experiments on challenging video and image generation benchmarks demonstrate that URSA consistently outperforms existing discrete methods and achieves performance comparable to state-of-the-art continuous diffusion methods. Code and models are available at https://github.com/baaivision/URSA

cs.CV↗

arXiv2025

CCDP: Composition of Conditional Diffusion Policies with Guided Sampling

Imitation Learning offers a promising approach to learn directly from data without requiring explicit models, simulations, or detailed task definitions. During inference, actions are sampled from the learned distribution and executed on the robot. However, sampled actions may fail for various reasons, and simply repeating the sampling step until a successful action is obtained can be inefficient. In this work, we propose an enhanced sampling strategy that refines the sampling distribution to avoid previously unsuccessful actions. We demonstrate that by solely utilizing data from successful demonstrations, our method can infer recovery actions without the need for additional exploratory behavior or a high-level controller. Furthermore, we leverage the concept of diffusion model decomposition to break down the primary problem, which may require long-horizon history to manage failures, into multiple smaller, more manageable sub-problems in learning, data collection, and inference, thereby enabling the system to adapt to variable failure counts. Our approach yields a low-level controller that dynamically adjusts its sampling space to improve efficiency when prior samples fall short. We validate our method across several tasks, including door opening with unknown directions, object manipulation, and button-searching scenarios, demonstrating that our approach outperforms traditional baselines.

cs.RO↗

arXiv2025

A Gravity-informed Spatiotemporal Transformer for Human Activity Intensity Prediction

Human activity intensity prediction is crucial to many location-based services. Despite tremendous progress in modeling dynamics of human activity, most existing methods overlook physical constraints of spatial interaction, leading to uninterpretable spatial correlations and over-smoothing phenomenon. To address these limitations, this work proposes a physics-informed deep learning framework, namely Gravity-informed Spatiotemporal Transformer (Gravityformer) by integrating the universal law of gravitation to refine transformer attention. Specifically, it (1) estimates two spatially explicit mass parameters based on spatiotemporal embedding feature, (2) models the spatial interaction in end-to-end neural network using proposed adaptive gravity model to learn the physical constraint, and (3) utilizes the learned spatial interaction to guide and mitigate the over-smoothing phenomenon in transformer attention. Moreover, a parallel spatiotemporal graph convolution transformer is proposed for achieving a balance between coupled spatial and temporal learning. Systematic experiments on six real-world large-scale activity datasets demonstrate the quantitative and qualitative superiority of our model over state-of-the-art benchmarks. Additionally, the learned gravity attention matrix can be not only disentangled and interpreted based on geographical laws, but also improved the generalization in zero-shot cross-region inference. This work provides a novel insight into integrating physical laws with deep learning for spatiotemporal prediction.

cs.LG↗

arXiv2025

HoMer: Addressing Heterogeneities by Modeling Sequential and Set-wise Contexts for CTR Prediction

Click-through rate (CTR) prediction, which models behavior sequence and non-sequential features (e.g., user/item profiles or cross features) to infer user interest, underpins industrial recommender systems. However, most methods face three forms of heterogeneity that degrade predictive performance: (i) Feature Heterogeneity persists when limited sequence side features provide less granular interest representation compared to extensive non-sequential features, thereby impairing sequence modeling performance; (ii) Context Heterogeneity arises because a user's interest in an item will be influenced by other items, yet point-wise prediction neglects cross-item interaction context from the entire item set; (iii) Architecture Heterogeneity stems from the fragmented integration of specialized network modules, which compounds the model's effectiveness, efficiency and scalability in industrial deployments. To tackle the above limitations, we propose HoMer, a Homogeneous-Oriented TransforMer for modeling sequential and set-wise contexts. First, we align sequence side features with non-sequential features for accurate sequence modeling and fine-grained interest representation. Second, we shift the prediction paradigm from point-wise to set-wise, facilitating cross-item interaction in a highly parallel manner. Third, HoMer's unified encoder-decoder architecture achieves dual optimization through structural simplification and shared computation, ensuring computational efficiency while maintaining scalability with model size. Without arduous modification to the prediction pipeline, HoMer successfully scales up and outperforms our industrial baseline by 0.0099 in the AUC metric, and enhances online business metrics like CTR/RPM by 1.99%/2.46%. Additionally, HoMer saves 27% of GPU resources via preliminary engineering optimization, further validating its superiority and practicality.

cs.IR↗

arXiv2025

A Generative Framework for Personalized Sticker Retrieval

Formulating information retrieval as a variant of generative modeling, specifically using autoregressive models to generate relevant identifiers for a given query, has recently attracted considerable attention. However, its application to personalized sticker retrieval remains largely unexplored and presents unique challenges: existing relevance-based generative retrieval methods typically lack personalization, leading to a mismatch between diverse user expectations and the retrieved results. To address this gap, we propose PEARL, a novel generative framework for personalized sticker retrieval, and make two key contributions: (i) To encode user-specific sticker preferences, we design a representation learning model to learn discriminative user representations. It is trained on three prediction tasks that leverage personal information and click history; and (ii) To generate stickers aligned with a user's query intent, we propose a novel intent-aware learning objective that prioritizes stickers associated with higher-ranked intents. Empirical results from both offline evaluations and online tests demonstrate that PEARL significantly outperforms state-of-the-art methods.

cs.IR↗

arXiv2025

A Multimodal Deep Learning Approach for White Matter Shape Prediction in Diffusion MRI Tractography

Shape measures have emerged as promising descriptors of white matter tractography, offering complementary insights into anatomical variability and associations with cognitive and clinical phenotypes. However, conventional methods for computing shape measures are computationally expensive and time-consuming for large-scale datasets due to reliance on voxel-based representations. We propose Tract2Shape, a novel multimodal deep learning framework that leverages geometric (point cloud) and scalar (tabular) features to predict ten white matter tractography shape measures. To enhance model efficiency, we utilize a dimensionality reduction algorithm for the model to predict five primary shape components. The model is trained and evaluated on two independently acquired datasets, the HCP-YA dataset, and the PPMI dataset. We evaluate the performance of Tract2Shape by training and testing it on the HCP-YA dataset and comparing the results with state-of-the-art models. To further assess its robustness and generalization ability, we also test Tract2Shape on the unseen PPMI dataset. Tract2Shape outperforms SOTA deep learning models across all ten shape measures, achieving the highest average Pearson's r and the lowest nMSE on the HCP-YA dataset. The ablation study shows that both multimodal input and PCA contribute to performance gains. On the unseen testing PPMI dataset, Tract2Shape maintains a high Pearson's r and low nMSE, demonstrating strong generalizability in cross-dataset evaluation. Tract2Shape enables fast, accurate, and generalizable prediction of white matter shape measures from tractography data, supporting scalable analysis across datasets. This framework lays a promising foundation for future large-scale white matter shape analysis.

eess.IV↗

arXiv2025

Aria Gen 2 Pilot Dataset

The Aria Gen 2 Pilot Dataset (A2PD) is an egocentric multimodal open dataset captured using the state-of-the-art Aria Gen 2 glasses. To facilitate timely access, A2PD is released incrementally with ongoing dataset enhancements. The initial release features Dia'ane, our primary subject, who records her daily activities alongside friends, each equipped with Aria Gen 2 glasses. It encompasses five primary scenarios: cleaning, cooking, eating, playing, and outdoor walking. In each of the scenarios, we provide comprehensive raw sensor data and output data from various machine perception algorithms. These data illustrate the device's ability to perceive the wearer, the surrounding environment, and interactions between the wearer and the environment, while maintaining robust performance across diverse users and conditions. The A2PD is publicly available at projectaria.com, with open-source tools and usage examples provided in Project Aria Tools.

cs.CV↗

arXiv2025

Agora: Trust Less and Open More in Verification for Confidential Computing

Binary verification plays a pivotal role in software security, yet building a verification service that is both open and trustworthy poses a formidable challenge. In this paper, we introduce a novel binary verification service, AGORA, scrupulously designed to overcome the challenge. At the heart of this approach lies a strategic insight: certain tasks can be delegated to untrusted entities, while the corresponding validators are securely housed within the trusted computing base (TCB). AGORA can validate untrusted assertions generated for versatile policies. Through a novel blockchain-based bounty task manager, it also utilizes crowdsourcing to remove trust in theorem provers. These synergistic techniques successfully ameliorate the TCB size burden associated with two procedures: binary analysis and theorem proving. The design of AGORA allows untrusted parties to participate in these complex processes. Moreover, based on running the optimized TCB within trusted execution environments and recording the verification process on a blockchain, the public can audit the correctness of verification results. By implementing verification workflows for software-based fault isolation policy and side-channel mitigation, our evaluation demonstrates the efficacy of AGORA.

cs.CR↗

arXiv2025

Blind Video Super-Resolution based on Implicit Kernels

Blind video super-resolution (BVSR) is a low-level vision task which aims to generate high-resolution videos from low-resolution counterparts in unknown degradation scenarios. Existing approaches typically predict blur kernels that are spatially invariant in each video frame or even the entire video. These methods do not consider potential spatio-temporal varying degradations in videos, resulting in suboptimal BVSR performance. In this context, we propose a novel BVSR model based on Implicit Kernels, BVSR-IK, which constructs a multi-scale kernel dictionary parameterized by implicit neural representations. It also employs a newly designed recurrent Transformer to predict the coefficient weights for accurate filtering in both frame correction and feature alignment. Experimental results have demonstrated the effectiveness of the proposed BVSR-IK, when compared with four state-of-the-art BVSR models on three commonly used datasets, with BVSR-IK outperforming the second best approach, FMA-Net, by up to 0.59 dB in PSNR. Source code will be available at https://github.com/QZ1-boy/BVSR-IK.

cs.CV↗

arXiv2025

FCVSR: A Frequency-aware Method for Compressed Video Super-Resolution

Compressed video super-resolution (SR) aims to generate high-resolution (HR) videos from the corresponding low-resolution (LR) compressed videos. Recently, some compressed video SR methods attempt to exploit the spatio-temporal information in the frequency domain, showing great promise in super-resolution performance. However, these methods do not differentiate various frequency subbands spatially or capture the temporal frequency dynamics, potentially leading to suboptimal results. In this paper, we propose a deep frequency-based compressed video SR model (FCVSR) consisting of a motion-guided adaptive alignment (MGAA) network and a multi-frequency feature refinement (MFFR) module. Additionally, a frequency-aware contrastive loss is proposed for training FCVSR, in order to reconstruct finer spatial details. The proposed model has been evaluated on three public compressed video super-resolution datasets, with results demonstrating its effectiveness when compared to existing works in terms of super-resolution performance (up to a 0.14dB gain in PSNR over the second-best model) and complexity.

cs.CV↗

arXiv2025

Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models

To address the dual challenges of inherent stochasticity and non-differentiable metrics in physical spatiotemporal forecasting, we propose Spatiotemporal Forecasting as Planning (SFP), a new paradigm grounded in Model-Based Reinforcement Learning. SFP constructs a novel Generative World Model to simulate diverse, high-fidelity future states, enabling an "imagination-based" environmental simulation. Within this framework, a base forecasting model acts as an agent, guided by a beam search-based planning algorithm that leverages non-differentiable domain metrics as reward signals to explore high-return future sequences. These identified high-reward candidates then serve as pseudo-labels to continuously optimize the agent's policy through iterative self-training, significantly reducing prediction error and demonstrating exceptional performance on critical domain metrics like capturing extreme events.

cs.LG↗