Large Language Models (LLMs) hold significant potential for enhancing healthcare applications, yet their deployment is hindered by high computational and memory demands. Model compression techniques offer solutions to reduce these demands, but their impact on medical LLMs remains underexplored. In this paper, we introduce CMedBench, the first comprehensive benchmark for evaluating compressed LLMs in medical contexts. CMedBench assesses five core dimensions: Medical Knowledge Ability, Medical Application Ability, Trustworthiness Maintenance, Compression Cross Combination, and Computational Efficiency. Through extensive empirical studies, we analyze the trade-offs between model efficiency and clinical performance across diverse models, datasets, and compression strategies. Our findings highlight critical limitations in current evaluation practices and provide a robust framework for aligning compression strategies with medical requirements. CMedBench serves as a vital resource for researchers and practitioners, guiding the development of efficient, trustworthy, and clinically effective LLMs for healthcare applications.

To address growing concerns about data privacy on mobile devices, the federated learning (FL) paradigm enables clients to collaboratively train models while sharing only local model updates. However, privacy risks remain in FL, as adversaries can still infer sensitive information from these updates. To enhance secure aggregation in FL, various protection mechanisms combining encryption and multi-party computation (MPC) have been proposed. These approaches, however, often introduce substantial communication and computational overhead, making secure aggregation impractical on resource-constrained devices, e.g., smart phones. To tackle these efficiency challenges, we are among the first to propose the integration of differential privacy (DP) with encryption and MPC for secure aggregation. Our proposed protocol, Federated Learning with Noise-based Secure Aggregation (FedNSA), injects noise through DP to obfuscate individual model updates. Encryption is employed to correlate the noise across different clients, while MPC ensures perfect noise cancellation at the server side. Finally, we theoretically analyze its advantages and conduct extensive experiments on public datasets to demonstrate the superiority of our approach across multiple dimensions in comparison with the state-of-the-art baselines.

The scarcity data of medical field brings the collaborative training in medical vision-language pre-training (VLP) cross different clients. Therefore, the collaborative training in medical VLP faces two challenges: First, the medical data requires privacy, thus can not directly shared across different clients. Second, medical data distribution across institutes is typically heterogeneous, hindering local model alignment and representation capabilities. To simultaneously overcome these two challenges, we propose the framework called personalized model selector with fused multimodal information (PMS-FM). The contribution of PMS-FM is two-fold: 1) PMS-FM uses embeddings to represent information in different formats, allowing for the fusion of multimodal data. 2) PMS-FM adapts to personalized data distributions by training multiple models. A model selector then identifies and selects the best-performing model for each individual client. Extensive experiments with multiple real-world medical datasets demonstrate the superb performance of PMS-FM over existing federated learning methods on different zero-shot classification tasks.

Optimization and sampling based algorithms are two branches of methods in machine learning, while existing safe reinforcement learning (RL) algorithms are mainly based on optimization, it is still unclear whether sampling based methods can lead to desirable performance with safe policy. This paper formulates the Langevin policy for safe RL, and proposes Langevin Actor-Critic (LAC) to accelerate the process of policy inference. Concretely, instead of parametric policy, the proposed Langevin policy provides a stochastic process that directly infers actions, which is the numerical solver to the Langevin dynamic of actions on the continuous time. Furthermore, to make Langevin policy practical on RL tasks, the proposed LAC accumulates the transitions induced by Langevin policy and reproduces them with a generator. Finally, extensive empirical results show the effectiveness and superiority of LAC on the MuJoCo-based and Safety Gym tasks.

3D object detection is one of the most important tasks in autonomous driving and robotics. Our research focuses on tackling low efficiency issue of point-based methods, and we propose a novel Instance-Centroid Faster Point Sampling (IC-FPS) framework. We design a Neighboring Feature Diffusion Module (NFDM) to extract local features for the purpose of efficiently distinguishing the foreground from the background. Considering Farthest Point Sampling (FPS) strategy for downsampling is computationally intensive, we propose the Centroid-Instance Sampling Strategy (CISS). CISS samples center point in large-scale point cloud by rapidly sampling the centroid and instance points of the foreground block. The proposed IC-FPS framework can be inserted into every point-based model and effectively replace the first Set Abstraction (SA) layer. Extensive experiments on several public benchmarks demonstrate the superior performance of our proposed IC-FPS. On the Waymo dataset, IC-FPS significantly improves performance of the benchmark model and increases inference speed by 3.8 times. And real-time detection of point-based methods is realized for the first time, which is meaningful for industrial applications.

In the point cloud analysis task, the existing local feature aggregation descriptors (LFAD) do not fully utilize the neighborhood information of center points. Previous methods only use the distance information to constrain the local aggregation process, which is easy to be affected by abnormal points and cannot adequately fit the original geometry of the point cloud. This paper argues that fine-grained geometric information (FGGI) plays an important role in the aggregation of local features. Based on this, we propose a gradient-based local attention module to address the above problem, which is called Gradient Attention Module (GAM). GAM simplifies the process of extracting the gradient information in the neighborhood to explicit representation using the Zenith Angle matrix and Azimuth Angle matrix, which makes the module 35X faster. The comprehensive experiments on the ScanObjectNN dataset, ShapeNet dataset, S3DIS dataset, Modelnet40 dataset, and KITTI dataset demonstrate the effectiveness, efficientness, and generalization of our newly proposed GAM for 3D point cloud analysis. Especially in S3DIS, GAM achieves the highest index in the current point-based model with mIoU/OA/mAcc of 74.4%/90.6%/83.2%.

The convolutional-based methods provide good segmentation performance in the medical image segmentation task. However, those methods have the following challenges when dealing with the edges of the medical images: (1) Previous convolutional-based methods do not focus on the boundary relationship between foreground and background around the segmentation edge, which leads to the degradation of segmentation performance when the edge changes complexly. (2) The inductive bias of the convolutional layer cannot be adapted to complex edge changes and the aggregation of multiple-segmented areas, resulting in its performance improvement mostly limited to segmenting the body of segmented areas instead of the edge. To address these challenges, we propose the CM-MLP framework on MFI (Multiscale Feature Interaction) block and ACRE (axial context relation encoder) block for accurate segmentation of the edge of medical image. In the MFI block, we propose the cascade multi-scale MLP (Cascade MLP) to process all local information from the deeper layers of the network simultaneously and utilize a cascade multiscale mechanism to fuse discrete local information gradually. Then, the ACRE block is used to make the deep supervision focus on exploring the boundary relationship between foreground and background to modify the edge of the medical image. The segmentation accuracy (Dice) of our proposed CM-MLP framework reaches 96.96%, 96.76%, and 82.54% on three benchmark datasets: CVC-ClinicDB dataset, sub-Kvasir dataset, and our inhouse dataset, respectively, which significantly outperform the state-of-the-art method. The source code and trained models will be available at https://github.com/ProgrammerHyy/CM-MLP.

In the author list, "Ferry Sansoto" should be Ferry Susanto.• To reflect more accurately the contribution of the article, the title should be changed to "A permutation and equinumerosity based polynomial-time algorithm for simple undirected graph isomorphism."• In the abstract, the "Pythagorean Triples Theorem" should be removed.• In the abstract, "squared sums of elements" should be "nth power sums."• In Section 2.2, "and the sum of the individual squared elements.By checking two sums," should be ", the sum of the individual squared elements and until the sum of the nth power of the nth element in the array.By checking these sums,"• In Section 2.2, "For both vertex and edge arrays of row/column sum based on the vertex and edge adjacency matrices, if and only if one array is a permutation of another one, the corresponding two graphs are isomorphic."should be "For both the vertex and edge arrays of row/column sum based on the vertex and edge adjacency matrices, if and only if one array is a permutation of another one and the corresponding edge and vertex's adjacent relationship has been preserved, the corresponding two graphs are isomorphic."

Summary The graph isomorphism problem is to determine two finite graphs that are isomorphic which is not known with a polynomial‐time solution. This paper solves the simple undirected graph isomorphism problem with an algorithmic approach as NP=P and proposes a polynomial‐time solution to check if two simple undirected graphs are isomorphic or not. Three new representation methods of a graph as vertex/edge adjacency matrix and triple tuple are proposed. A duality of edge and vertex and a reflexivity between vertex adjacency matrix and edge adjacency matrix were first introduced to present the core idea. Beyond this, the mathematical approval is based on an equivalence between permutation and bijection. Because only addition and multiplication operations satisfy the commutative law, we propose a permutation theorem to check fast whether one of two sets of arrays is a permutation of another or not. The permutation theorem was mathematically approved by Integer Factorization Theory, Pythagorean Triples Theorem, and Fundamental Theorem of Arithmetic. For each of two n ‐ary arrays, the linear and squared sums of elements were respectively calculated to produce the results.

Recently, dense video captioning has made attractive progress in detecting and captioning all events in a long untrimmed video. Despite promising results were achieved, most existing methods do not sufficiently explore the scene evolution within an event temporal proposal for captioning, and therefore perform less satisfactorily when the scenes and objects change over a relatively long proposal. To address this problem, we propose a graph-based partition-and-summarization (GPaS) framework for dense video captioning within two stages. For the “partition” stage, a whole event proposal is split into short video segments for captioning at a finer level. For the “summarization” stage, the generated sentences carrying rich description information for each segment are summarized into one sentence to describe the whole event. We particularly focus on the “summarization” stage, and propose a framework that effectively exploits the relationship between semantic words for summarization. We achieve this goal by treating semantic words as the nodes in a graph and learning their interactions by coupling Graph Convolutional Network (GCN) and Long Short Term Memory (LSTM), with the aid of visual cues. Two schemes of GCN-LSTM Interaction (GLI) modules are proposed for seamless integration of GCN and LSTM. The effectiveness of our approach is demonstrated via an extensive comparison with the state-of-the-arts methods on the two benchmarks ActivityNet Captions dataset and YouCook II dataset.

The topological distance is to measure the structural difference between two graphs in a metric space. Graphs are ubiquitous, and topological measurements over graphs arise in diverse areas, including, e.g. COVID-19 structural analysis, DNA/RNA alignment, discovering the Isomers, checking the code plagiarism. Unfortunately, popular distance scores used in these applications, that scale over large graphs, are not metrics, and the computation usually becomes NP-hard. While, fuzzy measurement is an uncertain representation to apply for a polynomial-time solution for undirected multigraph isomorphism. But the graph isomorphism problem is to determine two finite graphs that are isomorphic, which is not known with a polynomial-time solution. This paper solves the undirected multigraph isomorphism problem with an algorithmic approach as NP=P and proposes a polynomial-time solution to check if two undirected multigraphs are isomorphic or not. Based on the solution, we define a new fuzzy measurement based on graph isomorphism for topological distance/structural similarity between two graphs. Thus, this paper proposed a fuzzy measure of the topological distance between two undirected multigraphs. If two graphs are isomorphic, the topological distance is 0; if not, we will calculate the Euclidean distance among eight extracted features and provide the fuzzy distance. The fuzzy measurement executes more efficiently and accurately than the current methods.

In this work, we propose a division-and-summarization (DaS) framework for dense video captioning. After partitioning each untrimmed long video as multiple event proposals, where each event proposal consists of a set of short video segments, we extract visual feature (e.g., C3D feature) from each segment and use the existing image/video captioning approach to generate one sentence description for this segment. Considering that the generated sentences contain rich semantic descriptions about the whole event proposal, we formulate the dense video captioning task as a visual cue aided sentence summarization problem and propose a new two stage Long Short Term Memory (LSTM) approach equipped with a new hierarchical attention mechanism to summarize all generated sentences as one descriptive sentence with the aid of visual features. Specifically, the first-stage LSTM network takes all semantic words from the generated sentences and the visual features from all segments within one event proposal as the input, and acts as the encoder to effectively summarize both semantic and visual information related to this event proposal. The second-stage LSTM network takes the output from the first-stage LSTM network and the visual features from all video segments within one event proposal as the input, and acts as the decoder to generate one descriptive sentence for this event proposal. Our comprehensive experiments on the ActivityNet Captions dataset demonstrate the effectiveness of our newly proposed DaS framework for dense video captioning.

Excessive lose of customer account is becoming a major headache for VIP E-Mail hosting companies. Analysis of what kind of customer is more prone to lose and finding the appropriate measures to sustain those customers has become urgent needs. Recentl