Search

Private data, when published online, may be collected by unauthorized parties to train deep neural networks (DNNs). To protect privacy, defensive noises can be added to original samples to degrade their learnability by DNNs. Recently, unlearnable examples are proposed to minimize the training loss such that the model learns almost nothing. However, raw data are often pre-processed before being used for training, which may restore the private information of protected data. In this paper, we reveal the data privacy violation induced by data augmentation, a commonly used data pre-processing technique to improve model generalization capability, which is the first of its kind as far as we are concerned. We demonstrate that data augmentation can significantly raise the accuracy of the model trained on unlearnable examples from 21.3% to 66.1%. To address this issue, we propose a defense framework, dubbed ARMOR, to protect data privacy from potential breaches of data augmentation. To overcome the difficulty of having no access to the model training process, we design a non-local module-assisted surrogate model that better captures the effect of data augmentation. In addition, we design a surrogate augmentation selection strategy that maximizes distribution alignment between augmented and non-augmented samples, to choose the optimal augmentation strategy for each class. We also use a dynamic step size adjustment algorithm to enhance the defensive noise generation process. Extensive experiments are conducted on 4 datasets and 5 data augmentation methods to verify the performance of ARMOR. Comparisons with 6 state-of-the-art defense methods have demonstrated that ARMOR can preserve the unlearnability of protected private data under data augmentation. ARMOR reduces the test accuracy of the model trained on augmented protected samples by as much as 60% more than baselines.

Facial recognition models are increasingly employed by commercial enterprises, government agencies, and cloud service providers for identity verification, consumer services, and surveillance. These models are often trained using vast amounts of facial data processed and stored in cloud-based platforms, raising significant privacy concerns. Users' facial images may be exploited without their consent, leading to potential data breaches and misuse. This survey presents a comprehensive review of current methods aimed at preserving facial image privacy in cloud-based services. We categorize these methods into two primary approaches: image obfuscation-based protection and adversarial perturbation-based protection. We provide an in-depth analysis of both categories, offering qualitative and quantitative comparisons of their effectiveness. Additionally, we highlight unresolved challenges and propose future research directions to improve privacy preservation in cloud computing environments.

Coverage optimization generally involves deploying a set of facilities (e.g., sensors) to best satisfy the demands of specified points, with wide applications in fields such as location science and sensor networks. In practical applications, coverage optimization focuses on target coverage, which is typically formulated as Mixed-Variable Optimization Problems (MVOPs) due to complex real-world constraints. Meanwhile, high-fidelity discretization and visibility analysis may bring additional calculations, which significantly increases the computational cost. These factors pose significant challenges for fitness evaluations (FEs) in canonical Evolutionary Algorithms (EAs), and evolve the coverage problem into an Expensive Mixed-Variable Optimization Problem (EMVOP). To address these issues, we propose the RankNet-Inspired Surrogate-assisted Hybrid Metaheuristic (RI-SHM), an extension of our previous work. RI-SHM integrates three key components: (1) a RankNet-based pairwise global surrogate that innovatively predicts rankings between pairs of individuals, bypassing the challenges of fitness estimation in discontinuous solution space; (2) a surrogate-assisted local Estimation of Distribution Algorithm (EDA) that enhances local exploitation and helps escape from local optima; and (3) a fitness diversity-driven switching strategy that dynamically balances exploration and exploitation. Experiments demonstrate that our algorithm can effectively handle large-scale coverage optimization tasks of up to 300 dimensions and more than 1,800 targets within desirable runtime. Compared to state-of-the-art algorithms for EMVOPs, RI-SHM consistently outperforms them by up to 56.5$\%$ across all tested instances.

Quasar outflows often consist of two clouds with velocity separations matching the doublet spacings of common UV resonance transitions, a phenomenon known as line-locking, which is commonly observed in quasar spectra. Multiple clouds can be locked together through multi-ion doublets, forming 'line-locking web'. In the second paper of the TOLL project, we present discovery of one of the largest 'line-locking web' known to date from the VLT/UVES spectra of QSO J151352+085555. We identify 12 associated narrow absorption line systems through the C IV, N V, Si IV, O VI, and multiple Lyman lines (Ly${\alpha}$ to Ly${\epsilon}$), and find 10 out of the 12 absorbers are line-locked together by comparing velocity separations between different absorption systems. By conducting photoionization modeling with CLOUDY, we measure the total hydrogen column densities, metallicities, and ionization parameters of these absorbers, which suggests the absorbers likely have sub-solar metallicities. A preliminary statistical analysis demonstrates the shadowed clouds tend to have similar ionization states comparing to the shadowing ones. Identification of one of the largest line-locking webs implies that radiative acceleration plays an important role in sorting out cloud velocities in quasar outflows, and highlights the need for more sophisticated theoretical models to explain its formation and evolution., Comment: 17 pages, 12 figures, 1 table, accepted by ApJ

Transient astrophysical events are characterized by short timescales, high energy, and multi-wavelength radiation, often accompanied by violent energy releases. These phenomena are a major focus of modern astronomical research. To reveal their underlying physical mechanisms, near-real-time, multi-wavelength, and multi-messenger follow-up observations are essential. However, current transient alert systems face multiple challenges, including fragmented messages, inconsistent formats, and difficulties in retrospective analysis, all of which hinder the efficiency of triggering observations. This paper presents \textbf{TransientVerse}, an innovative real-time database platform to integrate and disseminate transient alerts. The platform uses an automated pipeline to integrate real-time alerts from multiple sources (e.g., ATel, VOEvent, and GCN). It structures unstructured text data into a dual-format database for transient alerts by using open-source large language models. TransientVerse offers retrospective searches, data visualization, literature reviews, and customized subscriptions for efficient event tracking and analysis. Additionally, for Fast Radio Bursts (FRBs), the platform provides real-time statistics on repeat burst rates across different time intervals and alerts astronomers about high-frequency burst sources, enabling rapid follow-up observations and optimizing the use of limited observation windows. TransientVerse improves the efficiency of acquiring transient events in real time, lowers the technical barriers for simultaneous observations, and provides robust technical support for multi-wavelength, multi-messenger time-domain astronomy and astrophysics studies.

6-Degree of Freedom (6DoF) motion estimation with a combination of visual and inertial sensors is a growing area with numerous real-world applications. However, precise calibration of the time offset between these two sensor types is a prerequisite for accurate and robust tracking. To address this, we propose a universal online temporal calibration strategy for optimization-based visual-inertial navigation systems. Technically, we incorporate the time offset td as a state parameter in the optimization residual model to align the IMU state to the corresponding image timestamp using td, angular velocity and translational velocity. This allows the temporal misalignment td to be optimized alongside other tracking states during the process. As our method only modifies the structure of the residual model, it can be applied to various optimization-based frameworks with different tracking frontends. We evaluate our calibration method with both EuRoC and simulation data and extensive experiments demonstrate that our approach provides more accurate time offset estimation and faster convergence, particularly in the presence of noisy sensor data., Comment: 7 pages

Transformer-based human skeleton action recognition has been developed for years. However, the complexity and high parameter count demands of these models hinder their practical applications, especially in resource-constrained environments. In this work, we propose FreqMixForemrV2, which was built upon the Frequency-aware Mixed Transformer (FreqMixFormer) for identifying subtle and discriminative actions with pioneered frequency-domain analysis. We design a lightweight architecture that maintains robust performance while significantly reducing the model complexity. This is achieved through a redesigned frequency operator that optimizes high-frequency and low-frequency parameter adjustments, and a simplified frequency-aware attention module. These improvements result in a substantial reduction in model parameters, enabling efficient deployment with only a minimal sacrifice in accuracy. Comprehensive evaluations of standard datasets (NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets) demonstrate that the proposed model achieves a superior balance between efficiency and accuracy, outperforming state-of-the-art methods with only 60% of the parameters., Comment: IEEE FG2025

Human pose estimation (HPE) has received increasing attention recently due to its wide application in motion analysis, virtual reality, healthcare, etc. However, it suffers from the lack of labeled diverse real-world datasets due to the time- and labor-intensive annotation. To cope with the label deficiency issue, one common solution is to train the HPE models with easily available synthetic datasets (source) and apply them to real-world data (target) through domain adaptation (DA). Unfortunately, prevailing domain adaptation techniques within the HPE domain remain predominantly fixated on effecting alignment and aggregation between source and target features, often sidestepping the crucial task of excluding domain-specific representations. To rectify this, we introduce a novel framework that capitalizes on both representation aggregation and segregation for domain adaptive human pose estimation. Within this framework, we address the network architecture aspect by disentangling representations into distinct domain-invariant and domain-specific components, facilitating aggregation of domain-invariant features while simultaneously segregating domain-specific ones. Moreover, we tackle the discrepancy measurement facet by delving into various keypoint relationships and applying separate aggregation or segregation mechanisms to enhance alignment. Extensive experiments on various benchmarks, e.g., Human3.6M, LSP, H3D, and FreiHand, show that our method consistently achieves state-of-the-art performance. The project is available at \url{https://github.com/davidpengucf/EPIC}., Comment: accepted by the 2025 IEEE International Conference on Automatic Face and Gesture Recognition (FG 2025)

Interconnection is crucial for computing systems. However, the current interconnection performance between processors and devices, such as memory devices and accelerators, significantly lags behind their computing performance, severely limiting the overall performance. To address this challenge, Intel proposes Compute Express Link (CXL), an open industry-standard interconnection. With memory semantics, CXL offers low-latency, scalable, and coherent interconnection between processors and devices. This paper introduces recent advances in CXL-based interconnection systems with memory semantics. We classify the existing research into three categories: Pooling Memory, Distributed Shared Memory, and Unified Memory. Pooling Memory interconnects processors and memory, aims to address memory wall challenge. Distributed shared memory interconnects processors across nodes, aims to synchronize the cluster. Unified memory interconnects processors and accelerators, aims to enhance collaboration in heterogeneous computing systems. Finally, we discuss the future research and envision memory-centric computing with CXL., Comment: 14 pages

To improve the efficiency of warehousing system and meet huge customer orders, we aim to solve the challenges of dimension disaster and dynamic properties in hyper scale multi-robot task planning (MRTP) for robotic mobile fulfillment system (RMFS). Existing research indicates that hierarchical reinforcement learning (HRL) is an effective method to reduce these challenges. Based on that, we construct an efficient multi-stage HRL-based multi-robot task planner for hyper scale MRTP in RMFS, and the planning process is represented with a special temporal graph topology. To ensure optimality, the planner is designed with a centralized architecture, but it also brings the challenges of scaling up and generalization that require policies to maintain performance for various unlearned scales and maps. To tackle these difficulties, we first construct a hierarchical temporal attention network (HTAN) to ensure basic ability of handling inputs with unfixed lengths, and then design multi-stage curricula for hierarchical policy learning to further improve the scaling up and generalization ability while avoiding catastrophic forgetting. Additionally, we notice that policies with hierarchical structure suffer from unfair credit assignment that is similar to that in multi-agent reinforcement learning, inspired of which, we propose a hierarchical reinforcement learning algorithm with counterfactual rollout baseline to improve learning performance. Experimental results demonstrate that our planner outperform other state-of-the-art methods on various MRTP instances in both simulated and real-world RMFS. Also, our planner can successfully scale up to hyper scale MRTP instances in RMFS with up to 200 robots and 1000 retrieval racks on unlearned maps while keeping superior performance over other methods.

Federated Graph Learning (FGL) enables multiple clients to jointly train powerful graph learning models, e.g., Graph Neural Networks (GNNs), without sharing their local graph data for graph-related downstream tasks, such as graph property prediction. In the real world, however, the graph data can suffer from significant distribution shifts across clients as the clients may collect their graph data for different purposes. In particular, graph properties are usually associated with invariant label-relevant substructures (i.e., subgraphs) across clients, while label-irrelevant substructures can appear in a client-specific manner. The issue of distribution shifts of graph data hinders the efficiency of GNN training and leads to serious performance degradation in FGL. To tackle the aforementioned issue, we propose a novel FGL framework entitled FedVN that eliminates distribution shifts through client-specific graph augmentation strategies with multiple learnable Virtual Nodes (VNs). Specifically, FedVN lets the clients jointly learn a set of shared VNs while training a global GNN model. To eliminate distribution shifts, each client trains a personalized edge generator that determines how the VNs connect local graphs in a client-specific manner. Furthermore, we provide theoretical analyses indicating that FedVN can eliminate distribution shifts of graph data across clients. Comprehensive experiments on four datasets under five settings demonstrate the superiority of our proposed FedVN over nine baselines., Comment: Accepted by AAAI 2025

High-fidelity speech enhancement often requires sophisticated modeling to capture intricate, multiscale patterns. Standard activation functions, while introducing nonlinearity, lack the flexibility to fully address this complexity. Kolmogorov-Arnold Networks (KAN), an emerging methodology that employs learnable activation functions on graph edges, present a promising alternative. This work investigates two novel KAN variants based on rational and radial basis functions for speech enhancement. We integrate the rational variant into the 1D CNN blocks of Demucs and the GRU-Transformer blocks of MP-SENet, while the radial variant is adapted to the 2D CNN-based decoders of MP-SENet. Experiments on the VoiceBank-DEMAND dataset show that replacing standard activations with KAN-based activations improves speech quality across both the time-domain and time-frequency domain methods with minimal impact on model size and FLOP, underscoring KAN's potential to improve speech enhancement models., Comment: 5 pages, 2 figure, 4 tables

Functional Magnetic Resonance Image (fMRI) is commonly employed to study human brain activity, since it offers insight into the relationship between functional fluctuations and human behavior. To enhance analysis and comprehension of brain activity, Graph Neural Networks (GNNs) have been widely applied to the analysis of functional connectivities (FC) derived from fMRI data, due to their ability to capture the synergistic interactions among brain regions. However, in the human brain, performing complex tasks typically involves the activation of certain pathways, which could be represented as paths across graphs. As such, conventional GNNs struggle to learn from these pathways due to the long-range dependencies of multiple pathways. To address these challenges, we introduce a novel framework BrainMAP to learn Multiple Activation Pathways in Brain networks. BrainMAP leverages sequential models to identify long-range correlations among sequentialized brain regions and incorporates an aggregation module based on Mixture of Experts (MoE) to learn from multiple pathways. Our comprehensive experiments highlight BrainMAP's superior performance. Furthermore, our framework enables explanatory analyses of crucial brain regions involved in tasks. Our code is provided at https://github.com/LzyFischer/Graph-Mamba., Comment: AAAI 2025

In recent years, large language models (LLMs) have made significant advancements in neuro-symbolic computing. However, the combination of LLM with argumentation computation remains an underexplored domain, despite its considerable potential for real-world applications requiring defeasible reasoning. In this paper, we aim to investigate the capability of LLMs in determining the extensions of various abstract argumentation semantics. To achieve this, we develop and curate a benchmark comprising diverse abstract argumentation frameworks, accompanied by detailed explanations of algorithms for computing extensions. Subsequently, we fine-tune LLMs on the proposed benchmark, focusing on two fundamental extension-solving tasks. As a comparative baseline, LLMs are evaluated using a chain-of-thought approach, where they struggle to accurately compute semantics. In the experiments, we demonstrate that the process explanation plays a crucial role in semantics computation learning. Models trained with explanations show superior generalization accuracy compared to those trained solely with question-answer pairs. Furthermore, by leveraging the self-explanation capabilities of LLMs, our approach provides detailed illustrations that mitigate the lack of transparency typically associated with neural networks. Our findings contribute to the broader understanding of LLMs' potential in argumentation computation, offering promising avenues for further research in this domain.

Using a symmetry-preserving treatment of a vector $\times$ vector contact interaction (SCI) at nonzero temperature, we compute the screening masses of flavour-SU(3) ground-state $J^P=0^\pm$, $1^\pm$ mesons, and $J^P=1/2^\pm$, $3/2^\pm$ baryons. We find that all correlation channels allowed at $T=0$ persist when the temperature increases, even above the QCD phase transition. The results for mesons qualitatively agree with those obtained from the contemporary lattice-regularised quantum chromodynamics (lQCD) simulations. One of the most remarkable features is that each parity-partner-pair degenerates when $T>T_c$, with $T_c$ being the critical temperature. For each pair, the screening mass of the negative parity meson increases monotonously with temperature. In contrast, the screening mass of the meson with positive parity is almost invariant on the domain $T\lesssim T_c/2$; when $T$ gets close to $T_c$, it decreases but soon increases again and finally degenerates with its parity partner, which signals the restoration of chiral symmetry. We also find that the $T$-dependent behaviours of baryon screening masses are quite similar to those of the mesons. For baryons, the dynamical, nonpointlike diquark correlations play a crucial role in the screening mass evolution. We further calculate the evolution of the fraction of each kind of diquark within baryons respective to temperature. We observe that, at high temperatures, only $J=0$ scalar and pseudoscalar diquark correlations can survive within $J^P=1/2^\pm$ baryons., Comment: 21 pages, 9 figures, 4 tables

Human mesh recovery (HMR) is crucial in many computer vision applications; from health to arts and entertainment. HMR from monocular images has predominantly been addressed by deterministic methods that output a single prediction for a given 2D image. However, HMR from a single image is an ill-posed problem due to depth ambiguity and occlusions. Probabilistic methods have attempted to address this by generating and fusing multiple plausible 3D reconstructions, but their performance has often lagged behind deterministic approaches. In this paper, we introduce GenHMR, a novel generative framework that reformulates monocular HMR as an image-conditioned generative task, explicitly modeling and mitigating uncertainties in the 2D-to-3D mapping process. GenHMR comprises two key components: (1) a pose tokenizer to convert 3D human poses into a sequence of discrete tokens in a latent space, and (2) an image-conditional masked transformer to learn the probabilistic distributions of the pose tokens, conditioned on the input image prompt along with randomly masked token sequence. During inference, the model samples from the learned conditional distribution to iteratively decode high-confidence pose tokens, thereby reducing 3D reconstruction uncertainties. To further refine the reconstruction, a 2D pose-guided refinement technique is proposed to directly fine-tune the decoded pose tokens in the latent space, which forces the projected 3D body mesh to align with the 2D pose clues. Experiments on benchmark datasets demonstrate that GenHMR significantly outperforms state-of-the-art methods. Project website can be found at https://m-usamasaleem.github.io/publication/GenHMR/GenHMR.html

Recent advancements in language modeling have enabled the translation of natural language into code, and the use of execution feedback to improve code generation. However, these methods often rely heavily on pre-existing test cases, which may not always be available or comprehensive. In this work, we propose a novel approach that concurrently trains a code generation model and a test generation model, utilizing execution feedback to refine and enhance the performance of both. We introduce two strategies for test and code data augmentation and a new scoring function for code and test ranking. We experiment on the APPS dataset and demonstrate that our approach can effectively generate and augment test cases, filter and synthesize correct code solutions, and rank the quality of generated code and tests. The results demonstrate that our models, when iteratively trained with an increasing number of test cases and code solutions, outperform those trained on the original dataset.

Semantic segmentation and 3D reconstruction are two fundamental tasks in remote sensing, typically treated as separate or loosely coupled tasks. Despite attempts to integrate them into a unified network, the constraints between the two heterogeneous tasks are not explicitly modeled, since the pioneering studies either utilize a loosely coupled parallel structure or engage in only implicit interactions, failing to capture the inherent connections. In this work, we explore the connections between the two tasks and propose a new network that imposes semantic constraints on the stereo matching task, both implicitly and explicitly. Implicitly, we transform the traditional parallel structure to a new cascade structure termed Semantic-Guided Cascade structure, where the deep features enriched with semantic information are utilized for the computation of initial disparity maps, enhancing semantic guidance. Explicitly, we propose a Semantic Selective Refinement (SSR) module and a Left-Right Semantic Consistency (LRSC) module. The SSR refines the initial disparity map under the guidance of the semantic map. The LRSC ensures semantic consistency between two views via reducing the semantic divergence after transforming the semantic map from one view to the other using the disparity map. Experiments on the US3D and WHU datasets demonstrate that our method achieves state-of-the-art performance for both semantic segmentation and stereo matching., Comment: 9 pages, 6 figures, AAAI 2025

Spatial-temporal graphs are widely used in a variety of real-world applications. Spatial-Temporal Graph Neural Networks (STGNNs) have emerged as a powerful tool to extract meaningful insights from this data. However, in real-world applications, most nodes may not possess any available temporal data during training. For example, the pandemic dynamics of most cities on a geographical graph may not be available due to the asynchronous nature of outbreaks. Such a phenomenon disagrees with the training requirements of most existing spatial-temporal forecasting methods, which jeopardizes their effectiveness and thus blocks broader deployment. In this paper, we propose to formulate a novel problem of inductive forecasting with limited training data. In particular, given a spatial-temporal graph, we aim to learn a spatial-temporal forecasting model that can be easily generalized onto those nodes without any available temporal training data. To handle this problem, we propose a principled framework named ST-FiT. ST-FiT consists of two key learning components: temporal data augmentation and spatial graph topology learning. With such a design, ST-FiT can be used on top of any existing STGNNs to achieve superior performance on the nodes without training data. Extensive experiments verify the effectiveness of ST-FiT in multiple key perspectives.

Editing complex visual content based on ambiguous instructions remains a challenging problem in vision-language modeling. While existing models can contextualize content, they often struggle to grasp the underlying intent within a reference image or scene, leading to misaligned edits. We introduce the Editing Vision-Language Model (EVLM), a system designed to interpret such instructions in conjunction with reference visuals, producing precise and context-aware editing prompts. Leveraging Chain-of-Thought (CoT) reasoning and KL-Divergence Target Optimization (KTO) alignment technique, EVLM captures subjective editing preferences without requiring binary labels. Fine-tuned on a dataset of 30,000 CoT examples, with rationale paths rated by human evaluators, EVLM demonstrates substantial improvements in alignment with human intentions. Experiments across image, video, 3D, and 4D editing tasks show that EVLM generates coherent, high-quality instructions, supporting a scalable framework for complex vision-language applications., Comment: Technical Report

We present the results from calibrating the data of the Commensal Radio Astronomy FAST Survey (CRAFTS) for \HI intensity mapping by the Five-hundred-meter Aperture Spherical Radio Telescope (FAST). Using 70 hours of drift-scan observation with the L-band (1.05-1.45GHz) 19-beam receiver, we obtain the data covering $270\,\rm deg^2$ sky area. We employ both the pulsar backend and the spectrum backend to calibrate the spectral time-ordered-data (TOD) before projecting them onto HEALPix maps. We produce calibrated TOD with frequency resolution of 30 kHz and time resolution of 1 s and the map data-cube with frequency resolution of 30kHz and spatial resolution of $2.95\,\rm arcmin^2$. We carefully examine the pointing errors, noise overflow, RFI contamination and their effect on the data quality. The resulting noise level is $\sim$ 5.7 mJy for the calibrated TOD and 1.6 mJy for the map, which is consistent with the theoretical predictions within 5\% at RFI-free channels. We also validate the data by Principal Components Analysis (PCA) and find most foreground components are concentrated in the first 30 modes. We identify 447 isolated bright continuum sources in our data matching the NRAO-VLA Sky Survey (NVSS) catalog, with relative flux error of 8.3\% for TOD and 11.9\% for the map-level. We also measure the \HI emission of 90 galaxies with redshift $z<0.07$ and compare with \HI-MaNGA spectra from the Green Bank Telescope (GBT), yielding an overall relative error of the \HI integral flux of 16.7\%. Our results confirm the feasibility of conducting cosmological \HI signal detection with CRAFTS., Comment: 30 pages, 30 figures, and 3 tables

The field of video generation has made remarkable advancements, yet there remains a pressing need for a clear, systematic recipe that can guide the development of robust and scalable models. In this work, we present a comprehensive study that systematically explores the interplay of model architectures, training recipes, and data curation strategies, culminating in a simple and scalable text-image-conditioned video generation method, named STIV. Our framework integrates image condition into a Diffusion Transformer (DiT) through frame replacement, while incorporating text conditioning via a joint image-text conditional classifier-free guidance. This design enables STIV to perform both text-to-video (T2V) and text-image-to-video (TI2V) tasks simultaneously. Additionally, STIV can be easily extended to various applications, such as video prediction, frame interpolation, multi-view generation, and long video generation, etc. With comprehensive ablation studies on T2I, T2V, and TI2V, STIV demonstrate strong performance, despite its simple design. An 8.7B model with 512 resolution achieves 83.1 on VBench T2V, surpassing both leading open and closed-source models like CogVideoX-5B, Pika, Kling, and Gen-3. The same-sized model also achieves a state-of-the-art result of 90.1 on VBench I2V task at 512 resolution. By providing a transparent and extensible recipe for building cutting-edge video generation models, we aim to empower future research and accelerate progress toward more versatile and reliable video generation solutions.

Recently, diffusion models have exhibited superior performance in the area of image inpainting. Inpainting methods based on diffusion models can usually generate realistic, high-quality image content for masked areas. However, due to the limitations of diffusion models, existing methods typically encounter problems in terms of semantic consistency between images and text, and the editing habits of users. To address these issues, we present PainterNet, a plugin that can be flexibly embedded into various diffusion models. To generate image content in the masked areas that highly aligns with the user input prompt, we proposed local prompt input, Attention Control Points (ACP), and Actual-Token Attention Loss (ATAL) to enhance the model's focus on local areas. Additionally, we redesigned the MASK generation algorithm in training and testing dataset to simulate the user's habit of applying MASK, and introduced a customized new training dataset, PainterData, and a benchmark dataset, PainterBench. Our extensive experimental analysis exhibits that PainterNet surpasses existing state-of-the-art models in key metrics including image quality and global/local text consistency.

Humanoid robots have significant gaps in their sensing and perception, making it hard to perform motion planning in dense environments. To address this, we introduce ARMOR, a novel egocentric perception system that integrates both hardware and software, specifically incorporating wearable-like depth sensors for humanoid robots. Our distributed perception approach enhances the robot's spatial awareness, and facilitates more agile motion planning. We also train a transformer-based imitation learning (IL) policy in simulation to perform dynamic collision avoidance, by leveraging around 86 hours worth of human realistic motions from the AMASS dataset. We show that our ARMOR perception is superior against a setup with multiple dense head-mounted, and externally mounted depth cameras, with a 63.7% reduction in collisions, and 78.7% improvement on success rate. We also compare our IL policy against a sampling-based motion planning expert cuRobo, showing 31.6% less collisions, 16.9% higher success rate, and 26x reduction in computational latency. Lastly, we deploy our ARMOR perception on our real-world GR1 humanoid from Fourier Intelligence. We are going to update the link to the source code, HW description, and 3D CAD files in the arXiv version of this text.

The ultrasound scanning robot operates in environments where frequent human-robot interactions occur. Most existing control methods for ultrasound scanning address only one specific interaction situation or implement hard switches between controllers for different situations, which compromises both safety and efficiency. In this paper, we propose a unified interaction control framework for ultrasound scanning robots capable of handling all common interactions, distinguishing both human-intended and unintended types, and adapting with appropriate compliance. Specifically, the robot suspends or modulates its ongoing main task if the interaction is intended, e.g., when the doctor grasps the robot to lead the end effector actively. Furthermore, it can identify unintended interactions and avoid potential collision in the null space beforehand. Even if that collision has happened, it can become compliant with the collision in the null space and try to reduce its impact on the main task (where the scan is ongoing) kinematically and dynamically. The multiple situations are integrated into a unified controller with a smooth transition to deal with the interactions by exhibiting human-intention-aware compliance. Experimental results validate the framework's ability to cope with all common interactions including intended intervention and unintended collision in a collaborative carotid artery ultrasound scanning task.

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where models behave normally for standard queries but generate harmful responses or unintended output when specific triggers are activated. Existing backdoor defenses often suffer from drawbacks that they either focus on detection without removal, rely on rigid assumptions about trigger properties, or prove to be ineffective against advanced attacks like multi-trigger backdoors. In this paper, we present a novel method to eliminate backdoor behaviors from LLMs through the construction of information conflicts using both internal and external mechanisms. Internally, we leverage a lightweight dataset to train a conflict model, which is then merged with the backdoored model to neutralize malicious behaviors by embedding contradictory information within the model's parametric memory. Externally, we incorporate convincing contradictory evidence into the prompt to challenge the model's internal backdoor knowledge. Experimental results on classification and conversational tasks across 4 widely used LLMs demonstrate that our method outperforms 8 state-of-the-art backdoor defense baselines. We can reduce the attack success rate of advanced backdoor attacks by up to 98% while maintaining over 90% clean data accuracy. Furthermore, our method has proven to be robust against adaptive backdoor attacks. The code will be open-sourced upon publication.

Federated Learning (FL) emerged as a paradigm for conducting machine learning across broad and decentralized datasets, promising enhanced privacy by obviating the need for direct data sharing. However, recent studies show that attackers can steal private data through model manipulation or gradient analysis. Existing attacks are constrained by low theft quantity or low-resolution data, and they are often detected through anomaly monitoring in gradients or weights. In this paper, we propose a novel data-reconstruction attack leveraging malicious code injection, supported by two key techniques, i.e., distinctive and sparse encoding design and block partitioning. Unlike conventional methods that require detectable changes to the model, our method stealthily embeds a hidden model using parameter sharing to systematically extract sensitive data. The Fibonacci-based index design ensures efficient, structured retrieval of memorized data, while the block partitioning method enhances our method's capability to handle high-resolution images by dividing them into smaller, manageable units. Extensive experiments on 4 datasets confirmed that our method is superior to the five state-of-the-art data-reconstruction attacks under the five respective detection methods. Our method can handle large-scale and high-resolution data without being detected or mitigated by state-of-the-art data reconstruction defense methods. In contrast to baselines, our method can be directly applied to both FedAVG and FedSGD scenarios, underscoring the need for developers to devise new defenses against such vulnerabilities. We will open-source our code upon acceptance.

Temporal awareness is essential for video large language models (LLMs) to understand and reason about events within long videos, enabling applications like dense video captioning and temporal video grounding in a unified system. However, the scarcity of long videos with detailed captions and precise temporal annotations limits their temporal awareness. In this paper, we propose Seq2Time, a data-oriented training paradigm that leverages sequences of images and short video clips to enhance temporal awareness in long videos. By converting sequence positions into temporal annotations, we transform large-scale image and clip captioning datasets into sequences that mimic the temporal structure of long videos, enabling self-supervised training with abundant time-sensitive data. To enable sequence-to-time knowledge transfer, we introduce a novel time representation that unifies positional information across image sequences, clip sequences, and long videos. Experiments demonstrate the effectiveness of our method, achieving a 27.6% improvement in F1 score and 44.8% in CIDEr on the YouCook2 benchmark and a 14.7% increase in recall on the Charades-STA benchmark compared to the baseline.

Quantum emitters are a key component in photonic quantum technologies. Enhancing their single-photon emission by engineering the photonic environment using cavities can significantly improve the overall efficiency in quantum information processing. However, this enhancement is often constrained by the need for precise nanoscale control over the emitter's position within micro- or nano-cavities. Inspired by the fascinating physics of moir\'e patterns, we present an approach to strongly modify the spontaneous emission rate of a quantum emitter using a finely designed multilayer moir\'e photonic crystal with a robust isolated-flatband dispersion. Theoretical analysis reveals that, due to its nearly infinite photonic density of states, the moir\'e cavity can simultaneously achieve a high Purcell factor and exhibit large tolerance over the emitter's position. We experimentally demonstrate the coupling between this moir\'e cavity and a quantum dot through the cavity-determined polarization of the dot's emission. The radiative lifetime of the quantum dot can be tuned by a factor of 40, ranging from 42 ps to 1692 ps, which is attributed to strong Purcell enhancement and Purcell inhibition effects. Our findings pave the way for moir\'e flatband cavity-enhanced quantum light sources, quantum optical switches, and quantum nodes for quantum internet applications.

Using available information from Drell-Yan data on pion and kaon structure functions, an approach is described which enables the development of pointwise profiles for all pion and kaon parton distribution functions (DFs) without reference to theories of hadron structure. The key steps are construction of structure-function-constrained probability-weighted ensembles of valence DF replicas and use of an evolution scheme for parton DFs that is all-orders exact. The DFs obtained express qualitatively sound features of light-meson structure, e.g., the effects of Higgs boson couplings into QCD and the size of heavy-quark momentum fractions in light hadrons. In order to improve the results, additional and more precise data on the $u$-quark-in-kaon, $u^K$, to $u$-quark-in-pion, $u^\pi$, DF ratio would be necessary. Of greater value would be extraction of $u^K$ alone, thereby avoiding inference from the ratio: currently, the data-based form of $u^K$ is materially influenced by results for $u^\pi$., Comment: 8 pages, 5 figures, 3 tables

Transcatheter tricuspid valve replacement (TTVR) is the latest treatment for tricuspid regurgitation and is in the early stages of clinical adoption. Intelligent robotic approaches are expected to overcome the challenges of surgical manipulation and widespread dissemination, but systems and protocols with high clinical utility have not yet been reported. In this study, we propose a complete solution that includes a passive stabilizer, robotic drive, detachable delivery catheter and valve manipulation mechanism. Working towards autonomy, a hybrid augmented intelligence approach based on reinforcement learning, Monte Carlo probabilistic maps and human-robot co-piloted control was introduced. Systematic tests in phantom and first-in-vivo animal experiments were performed to verify that the system design met the clinical requirement. Furthermore, the experimental results confirmed the advantages of co-piloted control over conventional master-slave control in terms of time efficiency, control efficiency, autonomy and stability of operation. In conclusion, this study provides a comprehensive pathway for robotic TTVR and, to our knowledge, completes the first animal study that not only successfully demonstrates the application of hybrid enhanced intelligence in interventional robotics, but also provides a solution with high application value for a cutting-edge procedure.

Documents serve as a crucial and indispensable medium for everyday workplace tasks. However, understanding, interacting and creating such documents on today's planar interfaces without any intelligent support are challenging due to our natural cognitive constraints on remembering, processing, understanding and interacting with these information. My doctorate research investigates how to bring 2D document interactions into immersive information experience using multiple of today's emergent technologies. With the examples of four specific types of documents -- medical scans, instruction document, self-report diary survey, and reference images for visual artists -- my research demonstrates how to transform such of today's 2D document interactions into an immersive information experience, by augmenting content with virtual reality, spatializing document placements with mixed reality, enriching long-term and continuous interactions with voice assistants, and simplify document creation workflow with generative AI., Comment: 6 pages, 4 figures

In this paper, we introduce Motion-Grounded Video Reasoning, a new motion understanding task that requires generating visual answers (video segmentation masks) according to the input question, and hence needs implicit spatiotemporal reasoning and grounding. This task extends existing spatiotemporal grounding work focusing on explicit action/motion grounding, to a more general format by enabling implicit reasoning via questions. To facilitate the development of the new task, we collect a large-scale dataset called GROUNDMORE, which comprises 1,715 video clips, 249K object masks that are deliberately designed with 4 question types (Causal, Sequential, Counterfactual, and Descriptive) for benchmarking deep and comprehensive motion reasoning abilities. GROUNDMORE uniquely requires models to generate visual answers, providing a more concrete and visually interpretable response than plain texts. It evaluates models on both spatiotemporal grounding and reasoning, fostering to address complex challenges in motion-related video reasoning, temporal perception, and pixel-level understanding. Furthermore, we introduce a novel baseline model named Motion-Grounded Video Reasoning Assistant (MORA). MORA incorporates the multimodal reasoning ability from the Multimodal LLM, the pixel-level perception capability from the grounding model (SAM), and the temporal perception ability from a lightweight localization head. MORA achieves respectable performance on GROUNDMORE outperforming the best existing visual grounding baseline model by an average of 21.5% relatively. We hope this novel and challenging task will pave the way for future advancements in robust and general motion understanding via video reasoning segmentation

As the application of large language models in various fields continues to expand, materials science also ushers in opportunities for AI-driven innovation. The traditional way of relying on manual search for materials science-related information is now using artificial intelligence technology as an auxiliary tool to improve the efficiency of materials science research. To accelerate researchers' knowledge acquisition and intelligent decision-making support in materials science research, this paper proposes a large language model Polymetis model for a variety of materials fields, aiming to provide highly professional knowledge answers in the field of materials, covering energy materials, functional materials, alloy materials, physical chemistry, biology, and other material directions. The model uses a dataset of about 2 million material knowledge instructions, and in the process of building the dataset, we developed the Intelligent Extraction Large Model (IELM), which is specially used to extract and form structured knowledge from scientific texts, avoiding a large number of costs that need to be manually annotated, and improving efficiency. We inject this data into the GLM4-9B model for learning to enhance its inference capabilities in a variety of material domains. In addition, we have introduced enhanced prompt strategies to ensure that the answers to the model are more organized and comprehensive, providing efficient and comprehensive intelligent support for the diverse needs of materials science exploration, and promoting the development of material science.

The discovery of new materials is very important to the field of materials science. When researchers explore new materials, they often have expected performance requirements for their crystal structure. In recent years, data-driven methods have made great progress in the direction plane of crystal structure generation, but there is still a lack of methods that can effectively map material properties to crystal structure. In this paper, we propose a Crystal DiT model to generate the crystal structure from the expected material properties by embedding the material properties and combining the symmetry information predicted by the large language model. Experimental verification shows that our proposed method has good performance.

Machine learning has become a crucial tool for predicting the properties of crystalline materials. However, existing methods primarily represent material information by constructing multi-edge graphs of crystal structures, often overlooking the chemical and physical properties of elements (such as atomic radius, electronegativity, melting point, and ionization energy), which have a significant impact on material performance. To address this limitation, we first constructed an element property knowledge graph and utilized an embedding model to encode the element attributes within the knowledge graph. Furthermore, we propose a multimodal fusion framework, ESNet, which integrates element property features with crystal structure features to generate joint multimodal representations. This provides a more comprehensive perspective for predicting the performance of crystalline materials, enabling the model to consider both microstructural composition and chemical characteristics of the materials. We conducted experiments on the Materials Project benchmark dataset, which showed leading performance in the bandgap prediction task and achieved results on a par with existing benchmarks in the formation energy prediction task.

Federated Graph Learning (FGL) is tasked with training machine learning models, such as Graph Neural Networks (GNNs), for multiple clients, each with its own graph data. Existing methods usually assume that each client has both node features and graph structure of its graph data. In real-world scenarios, however, there exist federated systems where only a part of the clients have such data while other clients (i.e. graphless clients) may only have node features. This naturally leads to a novel problem in FGL: how to jointly train a model over distributed graph data with graphless clients? In this paper, we propose a novel framework FedGLS to tackle the problem in FGL with graphless clients. In FedGLS, we devise a local graph learner on each graphless client which learns the local graph structure with the structure knowledge transferred from other clients. To enable structure knowledge transfer, we design a GNN model and a feature encoder on each client. During local training, the feature encoder retains the local graph structure knowledge together with the GNN model via knowledge distillation, and the structure knowledge is transferred among clients in global update. Our extensive experiments demonstrate the superiority of the proposed FedGLS over five baselines., Comment: Accepted by Transactions on Machine Learning Research (TMLR)

Traditional knowledge distillation focuses on aligning the student's predicted probabilities with both ground-truth labels and the teacher's predicted probabilities. However, the transition to predicted probabilities from logits would obscure certain indispensable information. To address this issue, it is intuitive to additionally introduce a logit-level loss function as a supplement to the widely used probability-level loss function, for exploiting the latent information of logits. Unfortunately, we empirically find that the amalgamation of the newly introduced logit-level loss and the previous probability-level loss will lead to performance degeneration, even trailing behind the performance of employing either loss in isolation. We attribute this phenomenon to the collapse of the classification head, which is verified by our theoretical analysis based on the neural collapse theory. Specifically, the gradients of the two loss functions exhibit contradictions in the linear classifier yet display no such conflict within the backbone. Drawing from the theoretical analysis, we propose a novel method called dual-head knowledge distillation, which partitions the linear classifier into two classification heads responsible for different losses, thereby preserving the beneficial effects of both losses on the backbone while eliminating adverse influences on the classification head. Extensive experiments validate that our method can effectively exploit the information inside the logits and achieve superior performance against state-of-the-art counterparts., Comment: Preprint

Federated Learning (FL) enables collaborative model training across decentralized edge devices while preserving data privacy. However, existing FL methods often assume clean annotated datasets, impractical for resource-constrained edge devices. In reality, noisy labels are prevalent, posing significant challenges to FL performance. Prior approaches attempt label correction and robust training techniques but exhibit limited efficacy, particularly under high noise levels. This paper introduces ClipFL (Federated Learning Client Pruning), a novel framework addressing noisy labels from a fresh perspective. ClipFL identifies and excludes noisy clients based on their performance on a clean validation dataset, tracked using a Noise Candidacy Score (NCS). The framework comprises three phases: pre-client pruning to identify potential noisy clients and calculate their NCS, client pruning to exclude a percentage of clients with the highest NCS, and post-client pruning for fine-tuning the global model with standard FL on clean clients. Empirical evaluation demonstrates ClipFL's efficacy across diverse datasets and noise levels, achieving accurate noisy client identification, superior performance, faster convergence, and reduced communication costs compared to state-of-the-art FL methods. Our code is available at https://github.com/MMorafah/ClipFL.

The k-truss model is one of the most important models in cohesive subgraph analysis. The k-truss decomposition problem is to compute the trussness of each edge in a given graph, and has been extensively studied. However, the conventional k-truss model is difficult to characterize the fine-grained hierarchical structures in networks due to the neglect of high order information. To overcome the limitation, the higher-order truss model is proposed in the literature. However, the previous solutions only consider non-parallel scenarios. To fill the gap, in this paper, we conduct the first research to study the problem of parallel higher-order truss decomposition. Specifically, a parallel framework is first proposed. Moreover, several optimizations are further developed to accelerate the processing. Finally, experiments over 6 real-world networks are conducted to verify the performance of proposed methods.

In the era of foundation models, we revisit continual learning~(CL), which aims to enable vision transformers (ViTs) to learn new tasks over time. However, as the scale of these models increases, catastrophic forgetting remains a persistent challenge, particularly in the presence of significant domain shifts across tasks. Recent studies highlight a crossover between CL techniques and parameter-efficient fine-tuning (PEFT), which focuses on fine-tuning only a small set of trainable parameters to adapt to downstream tasks, such as low-rank adaptation (LoRA). While LoRA achieves faster convergence and requires fewer trainable parameters, it has seldom been explored in the context of continual learning. To address this gap, we propose a novel PEFT-CL method called Dual Low-Rank Adaptation (DualLoRA), which introduces both an orthogonal LoRA adapter and a residual LoRA adapter parallel to pre-trained weights in each layer. These components are orchestrated by a dynamic memory mechanism to strike a balance between stability and plasticity. The orthogonal LoRA adapter's parameters are updated in an orthogonal subspace of previous tasks to mitigate catastrophic forgetting, while the residual LoRA adapter's parameters are updated in the residual subspace spanned by task-specific bases without interaction across tasks, offering complementary capabilities for fine-tuning new tasks. On ViT-based models, we demonstrate that DualLoRA offers significant advantages in accuracy, inference speed, and memory efficiency over existing CL methods across multiple benchmarks.

In the task of dense video captioning of Soccernet dataset, we propose to generate a video caption of each soccer action and locate the timestamp of the caption. Firstly, we apply Blip as our video caption framework to generate video captions. Then we locate the timestamp by using (1) multi-size sliding windows (2) temporal proposal generation and (3) proposal classification.

In the task of temporal action localization of ActivityNet-1.3 datasets, we propose to locate the temporal boundaries of each action and predict action class in untrimmed videos. We first apply VideoSwinTransformer as feature extractor to extract different features. Then we apply a unified network following Faster-TAD to simultaneously obtain proposals and semantic labels. Last, we ensemble the results of different temporal action detection models which complement each other. Faster-TAD simplifies the pipeline of TAD and gets remarkable performance, obtaining comparable results as those of multi-step approaches., Comment: arXiv admin note: substantial text overlap with arXiv:2204.02674

In order to make full use of video information, we transform the replay grounding problem into a video action location problem. We apply a unified network Faster-TAD proposed by us for temporal action detection to get the results of replay grounding. Finally, by observing the data distribution of the training data, we refine the output of the model to get the final submission.

Hardware-level memory vulnerabilities severely threaten computing systems. However, hardware patching is inefficient or difficult postfabrication. We investigate the effectiveness of hardware fuzzing in detecting hardware memory vulnerabilities and highlight challenges and potential future research directions to enhance hardware fuzzing for memory safety.

Microarchitectural attacks represent a challenging and persistent threat to modern processors, exploiting inherent design vulnerabilities in processors to leak sensitive information or compromise systems. Of particular concern is the susceptibility of Speculative Execution, a fundamental part of performance enhancement, to such attacks. We introduce Specure, a novel pre-silicon verification method composing hardware fuzzing with Information Flow Tracking (IFT) to address speculative execution leakages. Integrating IFT enables two significant and non-trivial enhancements over the existing fuzzing approaches: i) automatic detection of microarchitectural information leakages vulnerabilities without golden model and ii) a novel Leakage Path coverage metric for efficient vulnerability detection. Specure identifies previously overlooked speculative execution vulnerabilities on the RISC-V BOOM processor and explores the vulnerability search space 6.45x faster than existing fuzzing techniques. Moreover, Specure detected known vulnerabilities 20x faster.

Sim2real for robotic manipulation is difficult due to the challenges of simulating complex contacts and generating realistic task distributions. To tackle the latter problem, we introduce ManipGen, which leverages a new class of policies for sim2real transfer: local policies. Locality enables a variety of appealing properties including invariances to absolute robot and object pose, skill ordering, and global scene configuration. We combine these policies with foundation models for vision, language and motion planning and demonstrate SOTA zero-shot performance of our method to Robosuite benchmark tasks in simulation (97%). We transfer our local policies from simulation to reality and observe they can solve unseen long-horizon manipulation tasks with up to 8 stages with significant pose, object and scene configuration variation. ManipGen outperforms SOTA approaches such as SayCan, OpenVLA, LLMTrajGen and VoxPoser across 50 real-world manipulation tasks by 36%, 76%, 62% and 60% respectively. Video results at https://mihdalal.github.io/manipgen/, Comment: Main paper 7 pages, 3 tables, 3 figures. Appendix 6 pages, 2 figures, 6 tables

Diffusion models, widely used for image and video generation, face a significant limitation: the risk of memorizing and reproducing training data during inference, potentially generating unauthorized copyrighted content. While prior research has focused on image diffusion models (IDMs), video diffusion models (VDMs) remain underexplored. To address this gap, we first formally define the two types of memorization in VDMs (content memorization and motion memorization) in a practical way that focuses on privacy preservation and applies to all generation types. We then introduce new metrics specifically designed to separately assess content and motion memorization in VDMs. Additionally, we curate a dataset of text prompts that are most prone to triggering memorization when used as conditioning in VDMs. By leveraging these prompts, we generate diverse videos from various open-source VDMs, successfully extracting numerous training videos from each tested model. Through the application of our proposed metrics, we systematically analyze memorization across various pretrained VDMs, including text-conditional and unconditional models, on a variety of datasets. Our comprehensive study reveals that memorization is widespread across all tested VDMs, indicating that VDMs can also memorize image training data in addition to video datasets. Finally, we propose efficient and effective detection strategies for both content and motion memorization, offering a foundational approach for improving privacy in VDMs., Comment: Preprint

In this paper, we identify and leverage a novel `bright ending' (BE) anomaly in diffusion models prone to memorizing training images to address a new task: locating localized memorization regions within these models. BE refers to a distinct cross-attention pattern observed in text-to-image generations using diffusion models. Specifically, memorized image patches exhibit significantly greater attention to the end token during the final inference step compared to non-memorized patches. This attention map effectively highlights regions where the generated image replicates training data. Furthermore, driven by our observation that local memorization significantly underperforms in existing tasks of measuring, detecting, and mitigating memorization in diffusion models compared to global memorization, we propose a simple yet effective method to integrate BE and the results of the new localization task into these existing frameworks. This integration effectively improves their performances by narrowing the performance gap caused by local memorization. Our results not only demonstrate the successful execution of the new localization task but also establish new state-of-the-art performance across all existing tasks, underscoring the significance of the BE phenomenon., Comment: Preprint

This paper proposes a double Y-configuration multi active bridge converter (DYAB) capable of single stage bidirectional AC-DC isolated power conversion with a simple sinusoidal phase shift modulation. Compared to other dual active bridge (DAB) based AC-DC converters, the DYAB achieves power factor correction (PFC) with a simpler control method while maintaining nearly full-range zero-voltage switching (ZVS) and relatively low circulating current, resulting in high efficiency. The paper details the equivalent model and modulation method. A steady-state analysis tool based on the fast fourier transform (FFT) is developed to calculate the ZVS range, PFC performance, and loss breakdown. A 2.66kW hardware test demonstrating an efficiency of 97.14% is implemented to verify the proposed circuit and the steady state model.