Jingjing Zhang

Feng Zhu, Jingjing Zhang, Shengyun Liu et al.

Local stochastic gradient descent (SGD) is a fundamental approach in achieving communication efficiency in Federated Learning (FL) by allowing individual workers to perform local updates. However, the presence of heterogeneous data distributions across working nodes causes each worker to update its local model towards a local optimum, leading to the phenomenon known as ``client-drift" and resulting in slowed convergence. To address this issue, previous works have explored methods that either introduce communication overhead or suffer from unsteady performance. In this work, we introduce a novel metric called ``degree of divergence," quantifying the angle between the local gradient and the global reference direction. Leveraging this metric, we propose the divergence-based adaptive aggregation (DRAG) algorithm, which dynamically ``drags" the received local updates toward the reference direction in each round without requiring extra communication overhead. Furthermore, we establish a rigorous convergence analysis for DRAG, proving its ability to achieve a sublinear convergence rate. Compelling experimental results are presented to illustrate DRAG's superior performance compared to state-of-the-art algorithms in effectively managing the client-drift phenomenon. Additionally, DRAG exhibits remarkable resilience against certain Byzantine attacks. By securely sharing a small sample of the client's data with the FL server, DRAG effectively counters these attacks, as demonstrated through comprehensive experiments.

Feng Zhu, Jingjing Zhang, Xin Wang

Synchronous local stochastic gradient descent (local SGD) suffers from some workers being idle and random delays due to slow and straggling workers, as it waits for the workers to complete the same amount of local updates. In this paper, to mitigate stragglers and improve communication efficiency, a novel local SGD strategy, named STSyn, is developed. The key point is to wait for the $K$ fastest workers, while keeping all the workers computing continually at each synchronization round, and making full use of any effective (completed) local update of each worker regardless of stragglers. An analysis of the average wall-clock time, average number of local updates and average number of uploading workers per round is provided to gauge the performance of STSyn. The convergence of STSyn is also rigorously established even when the objective function is nonconvex. Experimental results show the superiority of the proposed STSyn against state-of-the-art schemes through utilization of the straggler-tolerant technique and additional effective local updates at each worker, and the influence of system parameters is studied. By waiting for faster workers and allowing heterogeneous synchronization with different numbers of local updates across workers, STSyn provides substantial improvements both in time and communication efficiency.

Tao Lin, Yilei Zhong, Yuxin Du et al.

Vision-Language-Action (VLA) models have emerged as a powerful framework that unifies perception, language, and control, enabling robots to perform diverse tasks through multimodal understanding. However, current VLA models typically contain massive parameters and rely heavily on large-scale robot data pretraining, leading to high computational costs during training, as well as limited deployability for real-time inference. Moreover, most training paradigms often degrade the perceptual representations of the vision-language backbone, resulting in overfitting and poor generalization to downstream tasks. In this work, we present Evo-1, a lightweight VLA model that reduces computation and improves deployment efficiency, while maintaining strong performance without pretraining on robot data. Evo-1 builds on a native multimodal Vision-Language model (VLM), incorporating a novel cross-modulated diffusion transformer along with an optimized integration module, together forming an effective architecture. We further introduce a two-stage training paradigm that progressively aligns action with perception, preserving the representations of the VLM. Notably, with only 0.77 billion parameters, Evo-1 achieves state-of-the-art results on the Meta-World and RoboTwin suite, surpassing the previous best models by 12.4% and 6.9%, respectively, and also attains a competitive result of 94.8% on LIBERO. In real-world evaluations, Evo-1 attains a 78% success rate with high inference frequency and low memory overhead, outperforming all baseline methods. We release code, data, and model weights to facilitate future research on lightweight and efficient VLA models.

Yaxi Chen, Simin Ni, Jingjing Zhang et al.

Classical radiomic features are designed to quantify image appearance and intensity patterns. Compared with end-to-end deep learning (DL) models trained for disease classification, radiomics pipelines with low-dimensional parametric classifiers offer enhanced transparency and interpretability, yet often underperform because of the reliance on population-level predefined feature sets. Recent work on adaptive radiomics uses DL to predict feature weights over a radiomic pool, then thresholds these weights to retain the top-k features from large radiomic pool F (often ~10^3). However, such marginal ranking can over-admit redundant descriptors and overlook complementary feature interactions. We propose a patient-specific feature-set selection framework that predicts a single compact feature set per subject, targeting complementary and diverse evidence rather than marginal top-k features. To overcome the intractable combinatorial search space of F choose k features, our method utilizes a 2-stage retrieval strategy: randomly sample diverse candidate feature sets, then rank these sets with a learned scoring function to select a high-performing feature set for the specific patient. The system consists of a feature-set scorer, and a classifier that performs the final diagnosis. We empirically show that the proposed two-stage retrieval approximates the original exhaustive all k-feature selection. Validating on tasks including ACL tear detection and KL grading for osteoarthritis, the experimental results achieve diagnostic performance, outperforming the top-k approach with the same k values, and competitive with end-to-end DL models while maintaining high transparency. The model generates auditable feature sets that link clinical outcomes to specific anatomical regions and radiomic families, allowing clinicians to inspect which anatomical structures and quantitative descriptors drive the prediction.

Xinyi Chen, Yilun Chen, Yanwei Fu et al.

We introduce InternVLA-M1, a unified framework for spatial grounding and robot control that advances instruction-following robots toward scalable, general-purpose intelligence. Its core idea is spatially guided vision-language-action training, where spatial grounding serves as the critical link between instructions and robot actions. InternVLA-M1 employs a two-stage pipeline: (i) spatial grounding pre-training on over 2.3M spatial reasoning data to determine ``where to act'' by aligning instructions with visual, embodiment-agnostic positions, and (ii) spatially guided action post-training to decide ``how to act'' by generating embodiment-aware actions through plug-and-play spatial prompting. This spatially guided training recipe yields consistent gains: InternVLA-M1 outperforms its variant without spatial guidance by +14.6% on SimplerEnv Google Robot, +17% on WidowX, and +4.3% on LIBERO Franka, while demonstrating stronger spatial reasoning capability in box, point, and trace prediction. To further scale instruction following, we built a simulation engine to collect 244K generalizable pick-and-place episodes, enabling a 6.2% average improvement across 200 tasks and 3K+ objects. In real-world clustered pick-and-place, InternVLA-M1 improved by 7.3%, and with synthetic co-training, achieved +20.6% on unseen objects and novel configurations. Moreover, in long-horizon reasoning-intensive scenarios, it surpassed existing works by over 10%. These results highlight spatially guided training as a unifying principle for scalable and resilient generalist robots. Code and models are available at https://github.com/InternRobotics/InternVLA-M1.

Kun Zhang, Jingyu Li, Zhe Li et al.

The burgeoning volume of multi-modal data necessitates advanced retrieval paradigms beyond unimodal and cross-modal approaches. Composed Multi-modal Retrieval (CMR) emerges as a pivotal next-generation technology, enabling users to query images or videos by integrating a reference visual input with textual modifications, thereby achieving unprecedented flexibility and precision. This paper provides a comprehensive survey of CMR, covering its fundamental challenges, technical advancements, and applications. CMR is categorized into supervised, zero-shot, and semi-supervised learning paradigms. We discuss key research directions, including data construction, model architecture, and loss optimization in supervised CMR, as well as transformation frameworks and linear integration in zero-shot CMR, and semi-supervised CMR that leverages generated pseudo-triplets while addressing data noise/uncertainty. Additionally, we extensively survey the diverse application landscape of CMR, highlighting its transformative potential in e-commerce, social media, search engines, public security, etc. Seven high impact application scenarios are explored in detail with benchmark data sets and performance analysis. Finally, we further provide new potential research directions with the hope of inspiring exploration in other yet-to-be-explored fields. A curated list of works is available at: https://github.com/kkzhang95/Awesome-Composed-Multi-modal-Retrieval

Yuting Tan, Xilong Cheng, Yunxiao Qin et al.

Humans develop visual intelligence through perceiving and interacting with their environment - a self-supervised learning process grounded in egocentric experience. Inspired by this, we ask how can artificial systems learn stable object representations from continuous, uncurated first-person videos without relying on manual annotations. This setting poses challenges of separating, recognizing, and persistently tracking objects amid clutter, occlusion, and ego-motion. We propose EgoViT, a unified vision Transformer framework designed to learn stable object representations from unlabeled egocentric video. EgoViT bootstraps this learning process by jointly discovering and stabilizing "proto-objects" through three synergistic mechanisms: (1) Proto-object Learning, which uses intra-frame distillation to form discriminative representations; (2) Depth Regularization, which grounds these representations in geometric structure; and (3) Teacher-Filtered Temporal Consistency, which enforces identity over time. This creates a virtuous cycle where initial object hypotheses are progressively refined into stable, persistent representations. The framework is trained end-to-end on unlabeled first-person videos and exhibits robustness to geometric priors of varied origin and quality. On standard benchmarks, EgoViT achieves +8.0% CorLoc improvement in unsupervised object discovery and +4.8% mIoU improvement in semantic segmentation, demonstrating its potential to lay a foundation for robust visual abstraction in embodied intelligence.

Rongji Huang, Yifeng Ye, Gerui Wang et al.

Due to regulatory compliance and governance management, modern (permissioned) blockchains require flexible endorsement, which allows the endorsement policy for each contract or state object to be individually defined. To enable flexible endorsement, Hyperledger Fabric employs an execute-order-validate (EOV) paradigm, in which transactions first undergo speculative execution and endorsement, and are only then ordered and validated. Meanwhile, most blockchain systems, including the platform targeted in this work (i.e., ChainMaker), still follow a conflict-free order-execute framework. We argue that the EOV paradigm still faces several limitations, notably high abort rates in high-contention workloads such as those in Decentralized Finance (DeFi). To avoid refactoring our system and better suit DeFi applications, we try to integrate flexible endorsement into the classical order-execute architecture and accordingly propose a new framework. The key challenge is to deterministically remove problematic transactions from an ordered list, while preserving censorship resistance and decentralization for the remaining ones. We instantiate this framework on top of Tendermint, a seminal Byzantine fault-tolerant (BFT) protocol adopted in our system, and thereby propose FlexTender. By elegantly embedding endorsements into consensus, FlexTender incurs no additional messaging overhead in the normal case. Empirical evaluation using an Ethereum USDT workload demonstrates that FlexTender achieves up to $10.6\times$ speedup in throughput over an EOV simulation on the same platform.

Wenxi Wu, Jingjing Zhang, Martim Brandão

Understanding user instructions and object spatial relations in surrounding environments is crucial for intelligent robot systems to assist humans in various tasks. The natural language and spatial reasoning capabilities of Vision-Language Models (VLMs) have the potential to enhance the generalization of robot planners on new tasks, objects, and motion specifications. While foundation models have been applied to task planning, it is still unclear the degree to which they have the capability of spatial reasoning required to enforce user preferences or constraints on motion, such as desired distances from objects, topological properties, or motion style preferences. In this paper, we evaluate the capability of four state-of-the-art VLMs at spatial reasoning over robot motion, using four different querying methods. Our results show that, with the highest-performing querying method, Qwen2.5-VL achieves 71.4% accuracy zero-shot and 75% on a smaller model after fine-tuning, and GPT-4o leads to lower performance. We evaluate two types of motion preferences (object-proximity and path-style), and we also analyze the trade-off between accuracy and computation cost in number of tokens. This work shows some promise in the potential of VLM integration with robot motion planning pipelines.

Nishchal Sapkota, Yejia Zhang, Sirui Li et al.

Male infertility accounts for about one-third of global infertility cases. Manual assessment of sperm abnormalities through head morphology analysis encounters issues of observer variability and diagnostic discrepancies among experts. Its alternative, Computer-Assisted Semen Analysis (CASA), suffers from low-quality sperm images, small datasets, and noisy class labels. We propose a new approach for sperm head morphology classification, called SHMC-Net, which uses segmentation masks of sperm heads to guide the morphology classification of sperm images. SHMC-Net generates reliable segmentation masks using image priors, refines object boundaries with an efficient graph-based method, and trains an image network with sperm head crops and a mask network with the corresponding masks. In the intermediate stages of the networks, image and mask features are fused with a fusion scheme to better learn morphological features. To handle noisy class labels and regularize training on small datasets, SHMC-Net applies Soft Mixup to combine mixup augmentation and a loss function. We achieve state-of-the-art results on SCIAN and HuSHeM datasets, outperforming methods that use additional pre-training or costly ensembling techniques.

Bingnan Xiao, Jingjing Zhang, Wei Ni et al.

Wireless federated learning (WFL) suffers from heterogeneity prevailing in the data distributions, computing powers, and channel conditions of participating devices. This paper presents a new Federated Learning with Adjusted leaRning ratE (FLARE) framework to mitigate the impact of the heterogeneity. The key idea is to allow the participating devices to adjust their individual learning rates and local training iterations, adapting to their instantaneous computing powers. The convergence upper bound of FLARE is established rigorously under a general setting with non-convex models in the presence of non-i.i.d. datasets and imbalanced computing powers. By minimizing the upper bound, we further optimize the scheduling of FLARE to exploit the channel heterogeneity. A nested problem structure is revealed to facilitate iteratively allocating the bandwidth with binary search and selecting devices with a new greedy method. A linear problem structure is also identified and a low-complexity linear programming scheduling policy is designed when training models have large Lipschitz constants. Experiments demonstrate that FLARE consistently outperforms the baselines in test accuracy, and converges much faster with the proposed scheduling policy.

Jiasheng Wu, Jingjing Zhang, Zheng Lin et al.

Recently, the rapid development of LEO satellite networks spurs another widespread concern-data processing at satellites. However, achieving efficient computation at LEO satellites in highly dynamic satellite networks is challenging and remains an open problem when considering the constrained computation capability of LEO satellites. For the first time, we propose a novel distributed learning framework named SFL-LEO by combining Federated Learning (FL) with Split Learning (SL) to accommodate the high dynamics of LEO satellite networks and the constrained computation capability of LEO satellites by leveraging the periodical orbit traveling feature. The proposed scheme allows training locally by introducing an asynchronous training strategy, i.e., achieving local update when LEO satellites disconnect with the ground station, to provide much more training space and thus increase the training performance. Meanwhile, it aggregates client-side sub-models at the ground station and then distributes them to LEO satellites by borrowing the idea from the federated learning scheme. Experiment results driven by satellite-ground bandwidth measured in Starlink demonstrate that SFL-LEO provides a similar accuracy performance with the conventional SL scheme because it can perform local training even within the disconnection duration.

Lin Wang, Jiasheng Wu, Yue Gao et al.

Cloud native technology has revolutionized 5G beyond and 6G communication networks, offering unprecedented levels of operational automation, flexibility, and adaptability. However, the vast array of cloud native services and applications presents a new challenge in resource allocation for dynamic cloud computing environments. To tackle this challenge, we investigate a cloud native wireless architecture that employs container-based virtualization to enable flexible service deployment. We then study two representative use cases: network slicing and Multi-Access Edge Computing. To optimize resource allocation in these scenarios, we leverage deep reinforcement learning techniques and introduce two model-free algorithms capable of monitoring the network state and dynamically training allocation policies. We validate the effectiveness of our algorithms in a testbed developed using Free5gc. Our findings demonstrate significant improvements in network efficiency, underscoring the potential of our proposed techniques in unlocking the full potential of cloud native wireless networks.

Yejia Zhang, Jingjing Zhang, Xiaomin Zha et al.

With rising male infertility, sperm head morphology classification becomes critical for accurate and timely clinical diagnosis. Recent deep learning (DL) morphology analysis methods achieve promising benchmark results, but leave performance and robustness on the table by relying on limited and possibly noisy class labels. To address this, we introduce a new DL training framework that leverages anatomical and image priors from human sperm microscopy crops to extract useful features without additional labeling cost. Our core idea is to distill sperm head information with reliably-generated pseudo-masks and unsupervised spatial prediction tasks. The predicted foreground masks from this distillation step are then leveraged to regularize and reduce image and label noise in the tuning stage. We evaluate our new approach on two public sperm datasets and achieve state-of-the-art performances (e.g. 65.9% SCIAN accuracy and 96.5% HuSHeM accuracy).

Feng Zhu, Jingjing Zhang, Osvaldo Simeone et al.

Wall-clock convergence time and communication load are key performance metrics for the distributed implementation of stochastic gradient descent (SGD) in parameter server settings. Communication-adaptive distributed Adam (CADA) has been recently proposed as a way to reduce communication load via the adaptive selection of workers. CADA is subject to performance degradation in terms of wall-clock convergence time in the presence of stragglers. This paper proposes a novel scheme named grouping-based CADA (G-CADA) that retains the advantages of CADA in reducing the communication load, while increasing the robustness to stragglers at the cost of additional storage at the workers. G-CADA partitions the workers into groups of workers that are assigned the same data shards. Groups are scheduled adaptively at each iteration, and the server only waits for the fastest worker in each selected group. We provide analysis and experimental results to elaborate the significant gains on the wall-clock time, as well as communication load and computation load, of G-CADA over other benchmark schemes.

Gediminas Adomavicius, Dietmar Jannach, Stephan Leitner et al.

Today's research in recommender systems is largely based on experimental designs that are static in a sense that they do not consider potential longitudinal effects of providing recommendations to users. In reality, however, various important and interesting phenomena only emerge or become visible over time, e.g., when a recommender system continuously reinforces the popularity of already successful artists on a music streaming site or when recommendations that aim at profit maximization lead to a loss of consumer trust in the long run. In this paper, we discuss how Agent-Based Modeling and Simulation (ABM) techniques can be used to study such important longitudinal dynamics of recommender systems. To that purpose, we provide an overview of the ABM principles, outline a simulation framework for recommender systems based on the literature, and discuss various practical research questions that can be addressed with such an ABM-based simulation framework.

Haotian Xie, Yong Zhang, Jun Wang et al.

The Gleason grading system using histological images is the most powerful diagnostic and prognostic predictor of prostate cancer. The current standard inspection is evaluating Gleason H&E-stained histopathology images by pathologists. However, it is complicated, time-consuming, and subject to observers. Deep learning (DL) based-methods that automatically learn image features and achieve higher generalization ability have attracted significant attention. However, challenges remain especially using DL to train the whole slide image (WSI), a predominant clinical source in the current diagnostic setting, containing billions of pixels, morphological heterogeneity, and artifacts. Hence, we proposed a convolutional neural network (CNN)-based automatic classification method for accurate grading of PCa using whole slide histopathology images. In this paper, a data augmentation method named Patch-Based Image Reconstruction (PBIR) was proposed to reduce the high resolution and increase the diversity of WSIs. In addition, a distribution correction (DC) module was developed to enhance the adaption of pretrained model to the target dataset by adjusting the data distribution. Besides, a Quadratic Weighted Mean Square Error (QWMSE) function was presented to reduce the misdiagnosis caused by equal Euclidean distances. Our experiments indicated the combination of PBIR, DC, and QWMSE function was necessary for achieving superior expert-level performance, leading to the best results (0.8885 quadratic-weighted kappa coefficient).

Zhongwu Xie, Weipeng Cao, Xizhao Wang et al.

Most of the Zero-Shot Learning (ZSL) algorithms currently use pre-trained models as their feature extractors, which are usually trained on the ImageNet data set by using deep neural networks. The richness of the feature information embedded in the pre-trained models can help the ZSL model extract more useful features from its limited training samples. However, sometimes the difference between the training data set of the current ZSL task and the ImageNet data set is too large, which may lead to the use of pre-trained models has no obvious help or even negative impact on the performance of the ZSL model. To solve this problem, this paper proposes a biologically inspired feature enhancement framework for ZSL. Specifically, we design a dual-channel learning framework that uses auxiliary data sets to enhance the feature extractor of the ZSL model and propose a novel method to guide the selection of the auxiliary data sets based on the knowledge of biological taxonomy. Extensive experimental results show that our proposed method can effectively improve the generalization ability of the ZSL model and achieve state-of-the-art results on three benchmark ZSL tasks. We also explained the experimental phenomena through the way of feature visualization.

Jingjing Zhang, Osvaldo Simeone, Zoran Cvetkovic et al.

Quantifying the directionality of information flow is instrumental in understanding, and possibly controlling, the operation of many complex systems, such as transportation, social, neural, or gene-regulatory networks. The standard Transfer Entropy (TE) metric follows Granger's causality principle by measuring the Mutual Information (MI) between the past states of a source signal $X$ and the future state of a target signal $Y$ while conditioning on past states of $Y$. Hence, the TE quantifies the improvement, as measured by the log-loss, in the prediction of the target sequence $Y$ that can be accrued when, in addition to the past of $Y$, one also has available past samples from $X$. However, by conditioning on the past of $Y$, the TE also measures information that can be synergistically extracted by observing both the past of $X$ and $Y$, and not solely the past of $X$. Building on a private key agreement formulation, the Intrinsic TE (ITE) aims to discount such synergistic information to quantify the degree to which $X$ is \emph{individually} predictive of $Y$, independent of $Y$'s past. In this paper, an estimator of the ITE is proposed that is inspired by the recently proposed Mutual Information Neural Estimation (MINE). The estimator is based on variational bound on the KL divergence, two-sample neural network classifiers, and the pathwise estimator of Monte Carlo gradients.

YongJie Ye, Jingjing Zhang, Weigang Wu et al.

The payment channel, which allows two parties to perform micropayments without involving the blockchain, has become a promising proposal to improve the scalability of decentralized ledgers such as Bitcoin and Ethereum. Payment channels have been extended to the payment network, through which users can utilize existing channels as intermediary links to route coins to others. However, routing payments through multiple channels bears nontrivial overheads. It requires every intermediary channel to lock a portion of its available capacity until the payment is settled. This may lead to deadlock in a concurrent situation. The intermediary nodes in a payment path may also charge fees for routing a payment. The longer the routing path, the more serious the above problems. In this paper, we design and develop a novel off-chain system to shorten the routing path for the payment network. In particular, we propose the channel hub, which is an extension of the payment hub, to allows transferring coins directly from one payment channel to another within the same hub. That is, the channel hub can be viewed as a shortcut device for the underlying payment network. We design a new protocol named Boros to perform secure off-chain cross-channel transfers through the channel hub. We not only present the security definition of the Boros protocol formally but also prove its security using the UC-framework. To demonstrate the feasibility of the Boros protocol, we develop a proof-of-concept prototype running on the Ethereum. Our evaluation shows that our system can effectively shorten the off-chain routing path.

Jingjing Zhang, Osvaldo Simeone

Gradient-based distributed learning in Parameter Server (PS) computing architectures is subject to random delays due to straggling worker nodes, as well as to possible communication bottlenecks between PS and workers. Solutions have been recently proposed to separately address these impairments based on the ideas of gradient coding, worker grouping, and adaptive worker selection. This paper provides a unified analysis of these techniques in terms of wall-clock time, communication, and computation complexity measures. Furthermore, in order to combine the benefits of gradient coding and grouping in terms of robustness to stragglers with the communication and computation load gains of adaptive selection, novel strategies, named Lazily Aggregated Gradient Coding (LAGC) and Grouped-LAG (G-LAG), are introduced. Analysis and results show that G-LAG provides the best wall-clock time and communication performance, while maintaining a low computational cost, for two representative distributions of the computing times of the worker nodes.

Melvin Leok, Jingjing Zhang

We consider the continuous and discrete-time Hamilton's variational principle on phase space, and characterize the exact discrete Hamiltonian which provides an exact correspondence between discrete and continuous Hamiltonian mechanics. The variational characterization of the exact discrete Hamiltonian naturally leads to a class of generalized Galerkin Hamiltonian variational integrators, which include the symplectic partitioned Runge-Kutta methods. We also characterize the group invariance properties of discrete Hamiltonians which lead to a discrete Noether's theorem.