Qi Lu

Wan Liu, Qi Lu, ZhiZheng Zhuo et al.

Deep learning based methods have achieved state-of-the-art performance for automated white matter (WM) tract segmentation. In these methods, the segmentation model needs to be trained with a large number of manually annotated scans, which can be accumulated throughout time. When novel WM tracts, i.e., tracts not included in the existing annotated WM tracts, are to be segmented, additional annotations of these novel WM tracts need to be collected. Since tract annotation is time-consuming and costly, it is desirable to make only a few annotations of novel WM tracts for training the segmentation model, and previous work has addressed this problem by transferring the knowledge learned for segmenting existing WM tracts to the segmentation of novel WM tracts. However, accurate segmentation of novel WM tracts can still be challenging in the one-shot setting, where only one scan is annotated for the novel WM tracts. In this work, we explore the problem of one-shot segmentation of novel WM tracts. Since in the one-shot setting the annotated training data is extremely scarce, based on the existing knowledge transfer framework, we propose to further perform extensive data augmentation for the single annotated scan, where synthetic annotated training data is produced. We have designed several different strategies that mask out regions in the single annotated scan for data augmentation. Our method was evaluated on public and in-house datasets. The experimental results show that our method improves the accuracy of one-shot segmentation of novel WM tracts.

Qi Lu

In this paper, we establish a global Carleman estimate for stochastic parabolic equations. Based on this estimate, we solve two inverse problems for stochastic parabolic equations. One is concerned with a determination problem of the history of a stochastic heat process through the observation at the final time $T$, for which we obtain a conditional stability estimate. The other is an inverse source problem with observation on the lateral boundary. We derive the uniqueness of the source.

Qi Arturo Gonzalez, Yifeng Gao, Li Zhang et al.

The complete collection of sparse resources in large, unknown environments remains a challenging problem for autonomous robot swarms. Previous studies have shown that a substantial portion of total mission time is consumed during the final stage of collection, where only a small fraction of randomly scattered resources remain. Consequently, many existing swarm foraging algorithms (search and collection) focus on collecting most resources within a limited time window, rather than improving end-stage efficiency for collecting all resources. We propose a grid-based stochastic foraging strategy that explicitly reduces redundant visits and accelerates late-stage collection. The unknown search area is partitioned into a grid map, which is maintained by a lightweight central server. To maintain scalability, both robots and the server operate within limited memory and computational constraints. The server updates the grid-level visitation counts based on robot-reported locations, producing a global estimate of the exploration density. For each new foraging trip, a robot selects its next search area from a local 3 X 3 neighborhood of grids probabilistically with the lowest visitation count, thus biasing exploration toward under-visited regions while maintaining stochasticity. Extensive simulation experiments demonstrate that the proposed strategy consistently outperforms the canonical centrally placed baseline foraging algorithm (CPFA). Compared to CPFA, the proposed method reduces the total collection time by up to 33% and improves collection efficiency by more than 48% during the final stage of the mission. These results indicate that the proposed strategy is robust, flexible, and scalable for near-complete and complete resource collection in robot swarms and can serve as a general enhancement for stochastic swarm foraging methods under limited onboard resources.

Jose Rodriguez, Constantine Tarawneh, Sven Koenig et al.

Multi-Robot Task Allocation (MRTA) is a central challenge in decentralized multi-agent systems, where teams of robots must cooperatively assign and execute tasks under limited communication while optimizing global performance objectives. Auction-consensus algorithms, such as the Consensus-Based Bundle Algorithm (CBBA), provide scalable decentralized coordination with provable convergence, but rely on hand-crafted greedy scoring functions that often lead to suboptimal task allocations. This paper proposes a learning-enhanced auction-consensus framework in which CBBA's deterministic bidding mechanism is replaced by a neural bidding policy trained using reinforcement learning. Under a centralized training and decentralized execution paradigm, agents learn to compute task bids from partial local observations while retaining the standard auction and consensus phases for decentralized coordination. The learned bidding policy is trained using Proximal Policy Optimization with rewards shaped by proximity to globally optimal solutions obtained via mixed-integer linear programming. Multiple neural architectures are evaluated, including a Neural Additive Model, the Long Short-Term Memory (LSTM) model, and the Set Transformer Model. Experimental results across varying swarm sizes demonstrate that learned bidding policies can improve solution quality over classical CBBA while preserving decentralized execution. The proposed approach highlights the effectiveness of integrating reinforcement learning with classical distributed coordination algorithms, offering a scalable pathway toward higher-quality decentralized multi-robot task allocation.

Javier Becerril, Maximiliano Vargas, Jennifer Herrera et al.

This paper presents a non-contact approach for vibration-based structural damage detection using an autonomous and customized cost-effective unmanned aerial vehicle (UAV). Vibration signals are extracted from video recordings through vision-based motion tracking to identify shifts in natural frequencies indicative of structural degradation. A laboratory-scale frame structure is evaluated under healthy and simulated-damage conditions. The proposed system is validated through an experimental study involving two smartphones, a USB camera, and a custom-built low-cost UAV equipped with an onboard camera and an autonomous alignment system for operation in GPS-denied environments. The displacement time is extracted and analyzed in the frequency domain and compared to reference measurements from contact accelerometers and a finite element model. Experimental results show that all platforms successfully capture the fundamental frequency and its shift due to damage. Although the UAV exhibits slightly higher errors (up to 5.7%) due to platform-induced disturbances and sensing limitations, it reliably detects damage-induced frequency changes. Compared to commercial UAV systems, the proposed platform achieves comparable inspection performance at significantly lower cost. These results demonstrate that low-cost autonomous UAVs provide a practical, flexible, and scalable solution for structural health monitoring, particularly in scenarios where contact-based sensing is impractical. The findings also support the potential for the deployment of multiple cooperative UAVs to further enhance inspection coverage and robustness.

Jianping Zhao, Qiong Zhou, Tian Wang et al.

MolProphecy is a human-in-the-loop (HITL) multi-modal framework designed to integrate chemists' domain knowledge into molecular property prediction models. While molecular pre-trained models have enabled significant gains in predictive accuracy, they often fail to capture the tacit, interpretive reasoning central to expert-driven molecular design. To address this, MolProphecy employs ChatGPT as a virtual chemist to simulate expert-level reasoning and decision-making. The generated chemist knowledge is embedded by the large language model (LLM) as a dedicated knowledge representation and then fused with graph-based molecular features through a gated cross-attention mechanism, enabling joint reasoning over human-derived and structural features. Evaluated on four benchmark datasets (FreeSolv, BACE, SIDER, and ClinTox), MolProphecy outperforms state-of-the-art (SOTA) models, achieving a 15.0 percent reduction in RMSE on FreeSolv and a 5.39 percent improvement in AUROC on BACE. Analysis reveals that chemist knowledge and structural features provide complementary contributions, improving both accuracy and interpretability. MolProphecy offers a practical and generalizable approach for collaborative drug discovery, with the flexibility to incorporate real chemist input in place of the current simulated proxy--without the need for model retraining. The implementation is publicly available at https://github.com/zhangruochi/MolProphecy.

Peihan Li, Joanna Gutierrez, Fabian Hernandez et al.

Swarm foraging algorithms, such as the central-place foraging algorithm (CPFA), typically rely on offline parameter optimization using genetic algorithms (GA) or reinforcement learning, yielding policies tightly coupled to a specific combination of team size, arena size, and resource distribution. When deployment conditions change, performance degrades, and retraining is computationally expensive. We propose LLM-Foraging, a decentralized swarm controller that augments the CPFA state machine with a large language model (LLM) tactical decision-maker at three structured decision points, namely post-deposit, central-zone arrival, and search starvation. Each robot runs its own LLM client and queries it using only locally observable state, while the existing CPFA motion and sensing stack executes the selected action. Because the LLM serves as a general decision policy rather than parameters fitted to a single configuration, the controller is training-free at deployment and transfers across configurations without re-optimization. We evaluate LLM-Foraging in Gazebo with TurtleBot3 robots across 36 configurations spanning team sizes of 4 to 10 robots, arena sizes from 6x6 to 10x10 meters, and three resource distributions (clustered, powerlaw, random). LLM-Foraging collects more resources than the GA-tuned CPFA baseline across the evaluated configurations and is more consistent, a property that the GA's single-configuration tuning does not transfer.

Yufei Song, Ziqi Zhou, Qi Lu et al.

Segmentation models exhibit significant vulnerability to adversarial examples in white-box settings, but existing adversarial attack methods often show poor transferability across different segmentation models. While some researchers have explored transfer-based adversarial attack (i.e., transfer attack) methods for segmentation models, the complex contextual dependencies within these models and the feature distribution gaps between surrogate and target models result in unsatisfactory transfer success rates. To address these issues, we propose SegTrans, a novel transfer attack framework that divides the input sample into multiple local regions and remaps their semantic information to generate diverse enhanced samples. These enhanced samples replace the original ones for perturbation optimization, thereby improving the transferability of adversarial examples across different segmentation models. Unlike existing methods, SegTrans only retains local semantic information from the original input, rather than using global semantic information to optimize perturbations. Extensive experiments on two benchmark datasets, PASCAL VOC and Cityscapes, four different segmentation models, and three backbone networks show that SegTrans significantly improves adversarial transfer success rates without introducing additional computational overhead. Compared to the current state-of-the-art methods, SegTrans achieves an average increase of 8.55% in transfer attack success rate and improves computational efficiency by more than 100%.

Juntao Zhao, Qi Lu, Wei Jia et al.

Modern frameworks for training large foundation models (LFMs) employ dataloaders in a data-parallel manner, with each loader processing a disjoint subset of training data. Under multisource preprocessing, two fundamental challenges exist. First, due to the quadratic computational complexity of the attention operator, the non-uniform sample distribution over data-parallel ranks leads to significant workload imbalance among dataloaders, degrading the training efficiency. Second, supporting diverse data sources requires per-dataset file access states that are redundantly replicated across parallel loaders, consuming excessive memory. This also hinders dynamic data mixing (e.g., curriculum learning) and causes redundant access/memory overhead in hybrid parallelism. We present Omniload, an industrial-grade distributed data loading architecture for LFMs, with four innovations: (1) Disaggregated data preprocessing via role-specific actors (Source Loaders/Data Constructors) to eliminate source and parallelism redundant data access and ensure multisource scalability. (2) Centralized and declarative data plane for elastic multisource orchestration, such as long-short context, multimodality, and curriculum learning. (3) Multi-level auto-partitioning and scaling mechanism for source loaders under heterogeneous preprocessing costs. (4) Shadow loaders with differential checkpointing for fault recovery without workflow interruption. Deployed on production clusters scaling to multi-thousand GPUs, Omniload achieves: (1) 4.5x end-to-end training throughput improvement, (2) 13.5x reduction in CPU memory usage.

Sicheng Lu, Zikai Xiao, Jianhui Wei et al.

Surgical video understanding is essential for computer-assisted interventions, yet existing surgical foundation models remain constrained by limited data scale, procedural diversity, and inconsistent evaluation, often lacking a reproducible training pipeline. We propose SurgRec, a scalable and reproducible pretraining recipe for surgical video understanding, instantiated with two variants: SurgRec-MAE and SurgRec-JEPA. We curate a large multi-source corpus of 10,535 videos and 214.5M frames spanning endoscopy, laparoscopy, cataract, and robotic surgery. Building on this corpus, we develop a unified pretraining pipeline with balanced sampling and standardize a reproducible benchmark across 16 downstream datasets and four clinical domains with consistent data splits. Across extensive comparisons against SSL baselines and vision-language models, SurgRec consistently achieves superior performance across downstream datasets. In contrast, VLMs prove unreliable for fine-grained temporal recognition, exhibiting both performance gaps and sensitivity to prompt phrasing. Our work provides a reproducible, scalable foundation for the community to build more general surgical video models. All code, models, and data will be publicly released.

Yusi Fan, Tian Wang, Zhiying Yan et al.

Feature selection is a combinatorial optimization problem that is NP-hard. Conventional approaches often employ heuristic or greedy strategies, which are prone to premature convergence and may fail to capture subtle yet informative features. This limitation becomes especially critical in high-dimensional datasets, where complex and interdependent feature relationships prevail. We introduce the HeFS (Helper-Enhanced Feature Selection) framework to refine feature subsets produced by existing algorithms. HeFS systematically searches the residual feature space to identify a Helper Set - features that complement the original subset and improve classification performance. The approach employs a biased initialization scheme and a ratio-guided mutation mechanism within a genetic algorithm, coupled with Pareto-based multi-objective optimization to jointly maximize predictive accuracy and feature complementarity. Experiments on 18 benchmark datasets demonstrate that HeFS consistently identifies overlooked yet informative features and achieves superior performance over state-of-the-art methods, including in challenging domains such as gastric cancer classification, drug toxicity prediction, and computer science applications. The code and datasets are available at https://healthinformaticslab.org/supp/.

Yinuo Zhao, Kun Wu, Zhiyuan Xu et al.

Vision-based autonomous urban driving in dense traffic is quite challenging due to the complicated urban environment and the dynamics of the driving behaviors. Widely-applied methods either heavily rely on hand-crafted rules or learn from limited human experience, which makes them hard to generalize to rare but critical scenarios. In this paper, we present a novel CAscade Deep REinforcement learning framework, CADRE, to achieve model-free vision-based autonomous urban driving. In CADRE, to derive representative latent features from raw observations, we first offline train a Co-attention Perception Module (CoPM) that leverages the co-attention mechanism to learn the inter-relationships between the visual and control information from a pre-collected driving dataset. Cascaded by the frozen CoPM, we then present an efficient distributed proximal policy optimization framework to online learn the driving policy under the guidance of particularly designed reward functions. We perform a comprehensive empirical study with the CARLA NoCrash benchmark as well as specific obstacle avoidance scenarios in autonomous urban driving tasks. The experimental results well justify the effectiveness of CADRE and its superiority over the state-of-the-art by a wide margin.

Qi Lu, Chuyang Ye

Convolutional neural networks (CNNs) have achieved stateof-the-art performance for white matter (WM) tract segmentation based on diffusion magnetic resonance imaging (dMRI). These CNNs require a large number of manual delineations of the WM tracts of interest for training, which are generally labor-intensive and costly. The expensive manual delineation can be a particular disadvantage when novel WM tracts, i.e., tracts that have not been included in existing manual delineations, are to be analyzed. To accurately segment novel WM tracts, it is desirable to transfer the knowledge learned about existing WM tracts, so that even with only a few delineations of the novel WM tracts, CNNs can learn adequately for the segmentation. In this paper, we explore the transfer of such knowledge to the segmentation of novel WM tracts in the few-shot setting. Although a classic fine-tuning strategy can be used for the purpose, the information in the last task-specific layer for segmenting existing WM tracts is completely discarded. We hypothesize that the weights of this last layer can bear valuable information for segmenting the novel WM tracts and thus completely discarding the information is not optimal. In particular, we assume that the novel WM tracts can correlate with existing WM tracts and the segmentation of novel WM tracts can be predicted with the logits of existing WM tracts. In this way, better initialization of the last layer than random initialization can be achieved for fine-tuning. Further, we show that a more adaptive use of the knowledge in the last layer for segmenting existing WM tracts can be conveniently achieved by simply inserting a warmup stage before classic fine-tuning. The proposed method was evaluated on a publicly available dMRI dataset, where we demonstrate the benefit of our method for few-shot segmentation of novel WM tracts.

Jason Dai, Yiheng Wang, Xin Qiu et al.

This paper presents BigDL (a distributed deep learning framework for Apache Spark), which has been used by a variety of users in the industry for building deep learning applications on production big data platforms. It allows deep learning applications to run on the Apache Hadoop/Spark cluster so as to directly process the production data, and as a part of the end-to-end data analysis pipeline for deployment and management. Unlike existing deep learning frameworks, BigDL implements distributed, data parallel training directly on top of the functional compute model (with copy-on-write and coarse-grained operations) of Spark. We also share real-world experience and "war stories" of users that have adopted BigDL to address their challenges(i.e., how to easily build end-to-end data analysis and deep learning pipelines for their production data).

Qi Lu, Melanie E. Moses, Joshua P. Hecker

Individual robots are not effective at exploring large unmapped areas. An alternate approach is to use a swarm of simple robots that work together, rather than a single highly capable robot. The central-place foraging algorithm (CPFA) is effective for coordinating robot swarm search and collection tasks. Robots start at a centrally placed location (nest), explore potential targets in the area without global localization or central control, and return the targets to the nest. The scalability of the CPFA is limited because large numbers of robots produce more inter-robot collisions and large search areas result in substantial travel costs. We address these problems with the multiple-place foraging algorithm (MPFA), which uses multiple nests distributed throughout the search area. Robots start from a randomly assigned home nest but return to the closest nest with found targets. We simulate the foraging behavior of robot swarms in the robot simulator ARGoS and employ a genetic algorithm to discover different optimized foraging strategies as swarm sizes and the number of targets are scaled up. In our experiments, the MPFA always produces higher foraging rates, fewer collisions, and lower travel and search time compared to the CPFA for the partially clustered targets distribution. The main contribution of this paper is that we systematically quantify the advantages of the MPFA (reduced travel time and collisions), the potential disadvantages (less communication among robots), and the ability of a genetic algorithm to tune MPFA parameters to mitigate search inefficiency due to less communication.