Chen Peng

Hong Wang, Yuanzhi Zhou, Chi Zhang et al.

This paper introduces XFL, an industrial-grade federated learning project. XFL supports training AI models collaboratively on multiple devices, while utilizes homomorphic encryption, differential privacy, secure multi-party computation and other security technologies ensuring no leakage of data. XFL provides an abundant algorithms library, integrating a large number of pre-built, secure and outstanding federated learning algorithms, covering both the horizontally and vertically federated learning scenarios. Numerical experiments have shown the prominent performace of these algorithms. XFL builds a concise configuration interfaces with presettings for all federation algorithms, and supports the rapid deployment via docker containers.Therefore, we believe XFL is the most user-friendly and easy-to-develop federated learning framework. XFL is open-sourced, and both the code and documents are available at https://github.com/paritybit-ai/XFL.

Dongqi Cai, Shangguang Wang, Chen Peng et al. · cambridge

Human memory is inherently prone to forgetting. To address this, multimodal embedding models have been introduced, which transform diverse real-world data into a unified embedding space. These embeddings can be retrieved efficiently, aiding mobile users in recalling past information. However, as model complexity grows, so do its resource demands, leading to reduced throughput and heavy computational requirements that limit mobile device implementation. In this paper, we introduce RECALL, a novel on-device multimodal embedding system optimized for resource-limited mobile environments. RECALL achieves high-throughput, accurate retrieval by generating coarse-grained embeddings and leveraging query-based filtering for refined retrieval. Experimental results demonstrate that RECALL delivers high-quality embeddings with superior throughput, all while operating unobtrusively with minimal memory and energy consumption.

Chen Peng, Zhikang Ge, Wenwu Lu et al.

Ground robots often carry payloads, implements, or other attachments that turn their effective footprint into complex, non-convex shapes. Navigating safely through clutter then requires reasoning about this true geometry, yet most local planners simplify it with convex or inflated proxies and rasterize sensor data into occupancy grids or distance fields. Both choices eliminate feasible motions when clearance is comparable to the footprint geometry. We present EXACT-MPPI, a training-free local navigation framework that maps local point-cloud observations and sparse guidance directly to motion commands, without any intermediate map representation. The framework embeds an analytic, exact signed-distance evaluator into a Model Predictive Path Integral (MPPI) controller. The footprint is represented as a simple polygon for general convex or concave planar shapes, with a rectangle-cover specialization for faster evaluation of rectilinear footprints, enabling footprint-aware collision costs without convex decomposition, inflation, or learned encoders. During each MPPI rollout, observed obstacle points are transformed into the predicted body frame and evaluated against the footprint. All operations are batched in JAX, leveraging GPU parallelism for real-time receding-horizon control. Experiments show that EXACT-MPPI accelerates batched distance evaluation over a learned point-to-robot baseline, preserves feasible motion where convex-footprint planners fail, and remains robust under dense static and moving obstacles. The same framework deploys on differential-drive, Ackermann, omnidirectional, and hybrid-mode platforms by changing only the footprint description and motion model without per-platform training. Pairing exact footprint geometry with sampling-based predictive control thus offers a practical, training-free path to footprint-aware local navigation across diverse robots.

Huang Chenyu, Zhang Fan, Du Minxin et al.

Structured data is well handled by gradient-boosted decision trees (GBDT), which are usually trained on vertically partitioned features across mutually distrustful parties. High speed and interpretability make GBDTs popular in finance and healthcare, where neural networks may fall short. Enabling secure computation for GBDTs poses unique challenges, requiring secure record alignment for comparison. Relying on private set intersection (PSI) is a de facto approach. Mistaking PSI for a safety measure actually exposes which record identifiers (IDs) are shared between the datasets. Although circuit-PSI could help, it is costly for generic uses. New ideas are needed to efficiently train in a "dark forest". Aiming to hide the IDs, we initiate the study of anonymous GBDT training on split data held by two parties. Dual circuit-PSI in our design lets the parties alternate as receiver to run pick-then-sum over local features. Via oblivious programmable pseudorandom functions, we propagate circuit-PSI outputs as shared state across runs. Avoiding universal alignment, we resolve the neglected dilemma that ID hiding incurs a cost that scales with domain size. Next, we halve the cost of ciphertext packing used to convert single-instruction multiple-data homomorphic encryption from (ring) learning with errors in prior secure GBDT (Usenix Security' 23) and related secure machine-learning computations. Comparative experiments show our protocol remains competitive with leaky approaches in efficiency. Enabling ID-hiding aggregation, our techniques can extend to other vertically partitioned analytics.

Yanlin Zhou, Chen Peng, Qing Hui

This article proposes a novel collective decision making scheme to solve the multi-agent drift-diffusion-model problem with the help of spiking neural networks. The exponential integrate-and-fire model is used here to capture the individual dynamics of each agent in the system, and we name this new model as Exponential Decision Making (EDM) model. We demonstrate analytically and experimentally that the gating variable for instantaneous activation follows Boltzmann probability distribution, and the collective system reaches meta-stable critical states under the Markov chain premises. With mean field analysis, we derive the global criticality from local dynamics and achieve a power law distribution. Critical behavior of EDM exhibits the convergence dynamics of Boltzmann distribution, and we conclude that the EDM model inherits the property of self-organized criticality, that the system will eventually evolve toward criticality.

Yunhe Yan, Shihe Wang, Jiajun Du et al.

(M)LLM-powered computer use agents (CUA) are emerging as a transformative technique to automate human-computer interaction. However, existing CUA benchmarks predominantly target GUI agents, whose evaluation methods are susceptible to UI changes and ignore function interactions exposed by application APIs, e.g., Model Context Protocol (MCP). To this end, we propose MCPWorld, the first automatic CUA testbed for API, GUI, and API-GUI hybrid agents. A key principle of MCPWorld is the use of "white-box apps", i.e., those with source code availability and can be revised/re-compiled as needed (e.g., adding MCP support), with two notable advantages: (1) It greatly broadens the design space of CUA, such as what and how the app features to be exposed/extracted as CUA-callable APIs. (2) It allows MCPWorld to programmatically verify task completion by directly monitoring application behavior through techniques like dynamic code instrumentation, offering robust, accurate CUA evaluation decoupled from specific agent implementations or UI states. Currently, MCPWorld includes 201 well curated and annotated user tasks, covering diversified use cases and difficulty levels. MCPWorld is also fully containerized with GPU acceleration support for flexible adoption on different OS/hardware environments. Our preliminary experiments, using a representative LLM-powered CUA framework, achieve 75.12% task completion accuracy, simultaneously providing initial evidence on the practical effectiveness of agent automation leveraging MCP. Overall, we anticipate MCPWorld to facilitate and standardize the benchmarking of next-generation computer use agents that can leverage rich external tools. Our code and dataset are publicly available at https://github.com/SAAgent/MCPWorld.

Chen Peng, Di Zhang, Urbashi Mitra

In this paper, the causal bandit problem is investigated, with the objective of maximizing the long-term reward by selecting an optimal sequence of interventions on nodes in an unknown causal graph. It is assumed that both the causal topology and the distribution of interventions are unknown. First, based on the difference between the two types of graph identification errors (false positives and negatives), a causal graph learning method is proposed. Numerical results suggest that this method has a much lower sample complexity relative to the prior art by learning sub-graphs. However, we note that a sample complexity analysis for the new algorithm has not been undertaken, as of yet. Under the assumption of minimum-mean squared error weight estimation, a new uncertainty bound tailored to the causal bandit problem is derived. This uncertainty bound drives an upper confidence bound-based intervention selection to optimize the reward. Further, we consider a particular instance of non-stationary bandits wherein both the causal topology and interventional distributions can change. Our solution is the design of a sub-graph change detection mechanism that requires a modest number of samples. Numerical results compare the new methodology to existing schemes and show a substantial performance improvement in stationary and non-stationary settings. Averaged over 100 randomly generated causal bandits, the proposed scheme takes significantly fewer samples to learn the causal structure and achieves a reward gain of 85% compared to existing approaches.

Mehdi Firouznia, Chen Peng, Qing Hui

This work proposes a novel approach to include a model of making decision in human brain into the control loop. Employing the methodology developed in mathematical neuroscience, we construct a model that accounts for quality of human decision in supervisory tasks. We specifically focus on adaptive gain theory and the strategy selection problem. The proposed model is shown to be capable of explaining the change of a strategy from compensatory to heuristics in different conditions. We also propose a method to incorporate the effect of internal and external parameters such as stress level and emergencies in the decision model. The model is employed in a supervisory controller that dispatches the jobs between autonomy and a human supervisor in an efficient way.

Chen Peng, Zhengqi Dai, Guangping Xia et al.

Machine learning systems have been extensively used as auxiliary tools in domains that require critical decision-making, such as healthcare and criminal justice. The explainability of decisions is crucial for users to develop trust on these systems. In recent years, the globally-consistent rule-based summary-explanation and its max-support (MS) problem have been proposed, which can provide explanations for particular decisions along with useful statistics of the dataset. However, globally-consistent summary-explanations with limited complexity typically have small supports, if there are any. In this paper, we propose a relaxed version of summary-explanation, i.e., the $q$-consistent summary-explanation, which aims to achieve greater support at the cost of slightly lower consistency. The challenge is that the max-support problem of $q$-consistent summary-explanation (MSqC) is much more complex than the original MS problem, resulting in over-extended solution time using standard branch-and-bound solvers. To improve the solution time efficiency, this paper proposes the weighted column sampling~(WCS) method based on solving smaller problems by sampling variables according to their simplified increase support (SIS) values. Experiments verify that solving MSqC with the proposed SIS-based WCS method is not only more scalable in efficiency, but also yields solutions with greater support and better global extrapolation effectiveness.

Chen Peng

DEKL 2.0 is a dependent type-theoretic framework for trace-indexed knowledge evolution. Its central claim is that the proof calculus remains monotone under standard structural rules, while non-monotonic behavior arises semantically from trace extension. Finite and infinite traces are first-class objects in the computational universe; knowledge is interpreted as a presheaf over the finite-trace category; and proposition-level reasoning is handled categorically with fixed-point support. We establish trace--reachability correspondence and completeness, characterize non-monotonicity by non-surjective restriction maps, and present a semantic interpretation based on the free category generated by a transition system. The framework unifies executable traces, typed witnesses, and knowledge revision in one dependent language.

Peng Wei, Chen Peng, Stavros Vougioukas

Autonomous and safe navigation of tractor-trailer systems requires accurate, real-time collision avoidance and dynamically feasible control, particularly in cluttered and complex agricultural environments. This is challenging due to their articulated, deformable geometries and nonlinear dynamics. Traditional methods oversimplify vehicle geometry or rely on precomputed distance fields that assume a known map, limiting their applicability in dynamic, partially unknown environments. To address these limitations, we propose a geometric neural encoder that provides fast and accurate distance estimates between the full tractor-trailer body and raw LiDAR perception, enabling real-time, map-free geometric reasoning. These learned distances are integrated into a Model Predictive Path Integral (MPPI) controller, allowing the system to incorporate true articulated geometry directly into its cost evaluation and enabling more responsive navigation in challenging agricultural settings. Simulation results demonstrate that the proposed framework generates dynamically feasible and safe trajectories for navigating tractor-trailer systems in cluttered and complex environments.

Chen Peng, Xianzhong Long, Yun Li

Self-supervised methods based on contrastive learning have achieved great success in unsupervised visual representation learning. However, most methods under this framework suffer from the problem of false negative samples. Inspired by the mean shift for self-supervised learning, we propose a new simple framework, namely Multiple Sample Views and Queues (MSVQ). We jointly construct three soft labels on-the-fly by utilizing two complementary and symmetric approaches: multiple augmented positive views and two momentum encoders that generate various semantic features for negative samples. Two teacher networks perform similarity relationship calculations with negative samples and then transfer this knowledge to the student network. Let the student network mimic the similarity relationships between the samples, thus giving the student network a more flexible ability to identify false negative samples in the dataset. The classification results on four benchmark image datasets demonstrate the high effectiveness and efficiency of our approach compared to some classical methods. Source code and pretrained models are available \href{https://github.com/pc-cp/MSVQ}{here}.

Linhao Qu, Chengsheng Zhang, Guihui Li et al.

Breast cancer presents a significant healthcare challenge globally, demanding precise diagnostics and effective treatment strategies, where histopathological examination of Hematoxylin and Eosin (H&E) stained tissue sections plays a central role. Despite its importance, evaluating specific biomarkers like Human Epidermal Growth Factor Receptor 2 (HER2) for personalized treatment remains constrained by the resource-intensive nature of Immunohistochemistry (IHC). Recent strides in deep learning, particularly in image-to-image translation, offer promise in synthesizing IHC-HER2 slides from H\&E stained slides. However, existing methodologies encounter challenges, including managing multiple magnifications in pathology images and insufficient focus on crucial information during translation. To address these issues, we propose a novel model integrating attention mechanisms and multi-magnification information processing. Our model employs a multi-magnification processing strategy to extract and utilize information from various magnifications within pathology images, facilitating robust image translation. Additionally, an attention module within the generative network prioritizes critical information for image distribution translation while minimizing less pertinent details. Rigorous testing on a publicly available breast cancer dataset demonstrates superior performance compared to existing methods, establishing our model as a state-of-the-art solution in advancing pathology image translation from H&E to IHC staining.

Xianzhong Long, Chen Peng, Yun Li

In contrastive self-supervised learning, positive samples are typically drawn from the same image but in different augmented views, resulting in a relatively limited source of positive samples. An effective way to alleviate this problem is to incorporate the relationship between samples, which involves including the top-K nearest neighbors of positive samples. However, the problem of false neighbors (i.e., neighbors that do not belong to the same category as the positive sample) is an objective but often overlooked challenge due to the query of neighbor samples without supervision information. In this paper, we present a simple self-supervised learning framework called Mixed Nearest-Neighbors for Self-Supervised Learning (MNN). MNN optimizes the influence of neighbor samples on the semantics of positive samples through an intuitive weighting approach and image mixture operations. The results demonstrate that MNN exhibits exceptional generalization performance and training efficiency on four benchmark datasets.

Chen Peng, Zhiqin Qian, Kunyu Wang et al.

Biomedical image segmentation is a very important part in disease diagnosis. The term "colonic polyps" refers to polypoid lesions that occur on the surface of the colonic mucosa within the intestinal lumen. In clinical practice, early detection of polyps is conducted through colonoscopy examinations and biomedical image processing. Therefore, the accurate polyp image segmentation is of great significance in colonoscopy examinations. Convolutional Neural Network (CNN) is a common automatic segmentation method, but its main disadvantage is the long training time. Transformer utilizes a self-attention mechanism, which essentially assigns different importance weights to each piece of information, thus achieving high computational efficiency during segmentation. However, a potential drawback is the risk of information loss. In the study reported in this paper, based on the well-known hybridization principle, we proposed a method to combine CNN and Transformer to retain the strengths of both, and we applied this method to build a system called MugenNet for colonic polyp image segmentation. We conducted a comprehensive experiment to compare MugenNet with other CNN models on five publicly available datasets. The ablation experiment on MugentNet was conducted as well. The experimental results show that MugenNet achieves significantly higher processing speed and accuracy compared with CNN alone. The generalized implication with our work is a method to optimally combine two complimentary methods of machine learning.

Chen Peng

Mechanizing the manual harvesting of fresh market fruits constitutes one of the biggest challenges to the sustainability of the fruit industry. During manual harvesting of some fresh-market crops like strawberries and table grapes, pickers spend significant amounts of time walking to carry full trays to a collection station at the edge of the field. A step toward increasing harvest automation for such crops is to deploy harvest-aid collaborative robots (co-bots) that transport the empty and full trays, thus increasing harvest efficiency by reducing pickers' non-productive walking times. This work presents the development of a co-robotic harvest-aid system and its evaluation during commercial strawberry harvesting. At the heart of the system lies a predictive stochastic scheduling algorithm that minimizes the expected non-picking time, thus maximizing the harvest efficiency. During the evaluation experiments, the co-robots improved the mean harvesting efficiency by around 10% and reduced the mean non-productive time by 60%, when the robot-to-picker ratio was 1:3. The concepts developed in this work can be applied to robotic harvest-aids for other manually harvested crops that involve walking for crop transportation.

Chen Peng, Stavros Vougioukas, David Slaughter et al.

Mechanizing the manual harvesting of fresh market fruits constitutes one of the biggest challenges to the sustainability of the fruit industry. During manual harvesting of some fresh-market crops like strawberries and table grapes, pickers spend significant amounts of time walking to carry full trays to a collection station at the edge of the field. A step toward increasing harvest automation for such crops is to deploy harvest-aid collaborative robots (co-bots) that transport the empty and full trays, thus increasing harvest efficiency by reducing pickers' non-productive walking times. This work presents the development of a co-robotic harvest-aid system and its evaluation during commercial strawberry harvesting. At the heart of the system lies a predictive stochastic scheduling algorithm that minimizes the expected non-picking time, thus maximizing the harvest efficiency. During the evaluation experiments, the co-robots improved the mean harvesting efficiency by around 10% and reduced the mean non-productive time by 60%, when the robot-to-picker ratio was 1:3. The concepts developed in this work can be applied to robotic harvest-aids for other manually harvested crops that involve walking for crop transportation.

Ying Huang, Jiyang Dai, Chen Peng

A new method is developed to deal with the problem that a complex decentralized control system needs to keep centralized control performance. The systematic procedure emphasizes quickly finding the decentralized subcontrollers that matching the closed-loop performance and robustness characteristics of the centralized controller, which is featured by the fact that GA is used to optimize the design of centralized H-infinity controller K(s) and decentralized engine subcontroller KT(s), and that only one interface variable needs to satisfy decentralized control system requirement according to the proposed selection principle. The optimization design is motivated by the implementation issues where it is desirable to reduce the time in trial and error process and accurately find the best decentralized subcontrollers. The method is applied to decentralized control system design for a short takeoff and landing fighter. By comparing the simulation results of the decentralized control system with those of the centralized control system, the target of the decentralized control attains the performance and robustness of centralized control is validated.

Leye Wang, Xu Geng, Jintao Ke et al.

Ridesourcing platforms like Uber and Didi are getting more and more popular around the world. However, unauthorized ridesourcing activities taking advantages of the sharing economy can greatly impair the healthy development of this emerging industry. As the first step to regulate on-demand ride services and eliminate black market, we design a method to detect ridesourcing cars from a pool of cars based on their trajectories. Since licensed ridesourcing car traces are not openly available and may be completely missing in some cities due to legal issues, we turn to transferring knowledge from public transport open data, i.e, taxis and buses, to ridesourcing detection among ordinary vehicles. We propose a two-stage transfer learning framework. In Stage 1, we take taxi and bus data as input to learn a random forest (RF) classifier using trajectory features shared by taxis/buses and ridesourcing/other cars. Then, we use the RF to label all the candidate cars. In Stage 2, leveraging the subset of high confident labels from the previous stage as input, we further learn a convolutional neural network (CNN) classifier for ridesourcing detection, and iteratively refine RF and CNN, as well as the feature set, via a co-training process. Finally, we use the resulting ensemble of RF and CNN to identify the ridesourcing cars in the candidate pool. Experiments on real car, taxi and bus traces show that our transfer learning framework, with no need of a pre-labeled ridesourcing dataset, can achieve similar accuracy as the supervised learning methods.