Search

The salient multimodal capabilities and interactive experience of GPT-4o highlight its critical role in practical applications, yet it lacks a high-performing open-source counterpart. In this paper, we introduce Baichuan-Omni, the first open-source 7B Multimodal Large Language Model (MLLM) adept at concurrently processing and analyzing modalities of image, video, audio, and text, while delivering an advanced multimodal interactive experience and strong performance. We propose an effective multimodal training schema starting with 7B model and proceeding through two stages of multimodal alignment and multitask fine-tuning across audio, image, video, and text modal. This approach equips the language model with the ability to handle visual and audio data effectively. Demonstrating strong performance across various omni-modal and multimodal benchmarks, we aim for this contribution to serve as a competitive baseline for the open-source community in advancing multimodal understanding and real-time interaction.

The first very long baseline interferometry (VLBI) detections at 870$\mu$m wavelength (345$\,$GHz frequency) are reported, achieving the highest diffraction-limited angular resolution yet obtained from the surface of the Earth, and the highest-frequency example of the VLBI technique to date. These include strong detections for multiple sources observed on inter-continental baselines between telescopes in Chile, Hawaii, and Spain, obtained during observations in October 2018. The longest-baseline detections approach 11$\,$G$\lambda$ corresponding to an angular resolution, or fringe spacing, of 19$\mu$as. The Allan deviation of the visibility phase at 870$\mu$m is comparable to that at 1.3$\,$mm on the relevant integration time scales between 2 and 100$\,$s. The detections confirm that the sensitivity and signal chain stability of stations in the Event Horizon Telescope (EHT) array are suitable for VLBI observations at 870$\mu$m. Operation at this short wavelength, combined with anticipated enhancements of the EHT, will lead to a unique high angular resolution instrument for black hole studies, capable of resolving the event horizons of supermassive black holes in both space and time., Comment: Corresponding author: S. Doeleman

The Segment Anything Model (SAM) is a foundational model for image segmentation tasks, known for its strong generalization across diverse applications. However, its impressive performance comes with significant computational and resource demands, making it challenging to deploy in resource-limited environments such as mobile devices. To address this, a variety of SAM variants have been proposed to enhance efficiency without sacrificing accuracy. This survey provides the first comprehensive review of these efficient SAM variants. We begin by exploring the motivations driving this research. We then present core techniques used in SAM and model acceleration. This is followed by an in-depth analysis of various acceleration strategies, categorized by approach. Finally, we offer a unified and extensive evaluation of these methods, assessing their efficiency and accuracy on representative benchmarks, and providing a clear comparison of their overall performance., Comment: Report in progress

Large Language Models (LLMs) have demonstrated remarkable capabilities across various fields, from natural language understanding to text generation. Compared to non-generative LLMs like BERT and DeBERTa, generative LLMs like GPT series and Llama series are currently the main focus due to their superior algorithmic performance. The advancements in generative LLMs are closely intertwined with the development of hardware capabilities. Various hardware platforms exhibit distinct hardware characteristics, which can help improve LLM inference performance. Therefore, this paper comprehensively surveys efficient generative LLM inference on different hardware platforms. First, we provide an overview of the algorithm architecture of mainstream generative LLMs and delve into the inference process. Then, we summarize different optimization methods for different platforms such as CPU, GPU, FPGA, ASIC, and PIM/NDP, and provide inference results for generative LLMs. Furthermore, we perform a qualitative and quantitative comparison of inference performance with batch sizes 1 and 8 on different hardware platforms by considering hardware power consumption, absolute inference speed (tokens/s), and energy efficiency (tokens/J). We compare the performance of the same optimization methods across different hardware platforms, the performance across different hardware platforms, and the performance of different methods on the same hardware platform. This provides a systematic and comprehensive summary of existing inference acceleration work by integrating software optimization methods and hardware platforms, which can point to the future trends and potential developments of generative LLMs and hardware technology for edge-side scenarios., Comment: 43 pages, 15 figures

With the rapidly increasing number of satellites in space and their enhanced capabilities, the amount of earth observation images collected by satellites is exceeding the transmission limits of satellite-to-ground links. Although existing learned image compression solutions achieve remarkable performance by using a sophisticated encoder to extract fruitful features as compression and using a decoder to reconstruct, it is still hard to directly deploy those complex encoders on current satellites' embedded GPUs with limited computing capability and power supply to compress images in orbit. In this paper, we propose COSMIC, a simple yet effective learned compression solution to transmit satellite images. We first design a lightweight encoder (i.e. reducing FLOPs by $2.6\sim 5\times $) on satellite to achieve a high image compression ratio to save satellite-to-ground links. Then, for reconstructions on the ground, to deal with the feature extraction ability degradation due to simplifying encoders, we propose a diffusion-based model to compensate image details when decoding. Our insight is that satellite's earth observation photos are not just images but indeed multi-modal data with a nature of Text-to-Image pairing since they are collected with rich sensor data (e.g. coordinates, timestamp, etc.) that can be used as the condition for diffusion generation. Extensive experiments show that COSMIC outperforms state-of-the-art baselines on both perceptual and distortion metrics.

Recently, with the development of Neural Radiance Fields and Gaussian Splatting, 3D reconstruction techniques have achieved remarkably high fidelity. However, the latent representations learnt by these methods are highly entangled and lack interpretability. In this paper, we propose a novel part-aware compositional reconstruction method, called GaussianBlock, that enables semantically coherent and disentangled representations, allowing for precise and physical editing akin to building blocks, while simultaneously maintaining high fidelity. Our GaussianBlock introduces a hybrid representation that leverages the advantages of both primitives, known for their flexible actionability and editability, and 3D Gaussians, which excel in reconstruction quality. Specifically, we achieve semantically coherent primitives through a novel attention-guided centering loss derived from 2D semantic priors, complemented by a dynamic splitting and fusion strategy. Furthermore, we utilize 3D Gaussians that hybridize with primitives to refine structural details and enhance fidelity. Additionally, a binding inheritance strategy is employed to strengthen and maintain the connection between the two. Our reconstructed scenes are evidenced to be disentangled, compositional, and compact across diverse benchmarks, enabling seamless, direct and precise editing while maintaining high quality.

Control Lyapunov functions are a central tool in the design and analysis of stabilizing controllers for nonlinear systems. Constructing such functions, however, remains a significant challenge. In this paper, we investigate physics-informed learning and formal verification of neural network control Lyapunov functions. These neural networks solve a transformed Hamilton-Jacobi-Bellman equation, augmented by data generated using Pontryagin's maximum principle. Similar to how Zubov's equation characterizes the domain of attraction for autonomous systems, this equation characterizes the null-controllability set of a controlled system. This principled learning of neural network control Lyapunov functions outperforms alternative approaches, such as sum-of-squares and rational control Lyapunov functions, as demonstrated by numerical examples. As an intermediate step, we also present results on the formal verification of quadratic control Lyapunov functions, which, aided by satisfiability modulo theories solvers, can perform surprisingly well compared to more sophisticated approaches and efficiently produce global certificates of null-controllability.

In research findings, co-deletion of the 1p/19q gene is associated with clinical outcomes in low-grade gliomas. The ability to predict 1p19q status is critical for treatment planning and patient follow-up. This study aims to utilize a specially MRI-based convolutional neural network for brain cancer detection. Although public networks such as RestNet and AlexNet can effectively diagnose brain cancers using transfer learning, the model includes quite a few weights that have nothing to do with medical images. As a result, the diagnostic results are unreliable by the transfer learning model. To deal with the problem of trustworthiness, we create the model from the ground up, rather than depending on a pre-trained model. To enable flexibility, we combined convolution stacking with a dropout and full connect operation, it improved performance by reducing overfitting. During model training, we also supplement the given dataset and inject Gaussian noise. We use three--fold cross-validation to train the best selection model. Comparing InceptionV3, VGG16, and MobileNetV2 fine-tuned with pre-trained models, our model produces better results. On an validation set of 125 codeletion vs. 31 not codeletion images, the proposed network achieves 96.37\% percent F1-score, 97.46\% percent precision, and 96.34\% percent recall when classifying 1p/19q codeletion and not codeletion images., Comment: ICAI'22 - The 24th International Conference on Artificial Intelligence, The 2022 World Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE'22), Las Vegas, USA. The paper acceptance rate 17% for regular papers. The publication of the CSCE 2022 conference proceedings has been delayed due to the pandemic

Medical image analysis is crucial in modern radiological diagnostics, especially given the exponential growth in medical imaging data. The demand for automated report generation systems has become increasingly urgent. While prior research has mainly focused on using machine learning and multimodal language models for 2D medical images, the generation of reports for 3D medical images has been less explored due to data scarcity and computational complexities. This paper introduces 3D-CT-GPT, a Visual Question Answering (VQA)-based medical visual language model specifically designed for generating radiology reports from 3D CT scans, particularly chest CTs. Extensive experiments on both public and private datasets demonstrate that 3D-CT-GPT significantly outperforms existing methods in terms of report accuracy and quality. Although current methods are few, including the partially open-source CT2Rep and the open-source M3D, we ensured fair comparison through appropriate data conversion and evaluation methodologies. Experimental results indicate that 3D-CT-GPT enhances diagnostic accuracy and report coherence, establishing itself as a robust solution for clinical radiology report generation. Future work will focus on expanding the dataset and further optimizing the model to enhance its performance and applicability.

This letter aims to generate a continuous-time trajectory consisting of piecewise B\'ezier curves that satisfy signal temporal logic (STL) specifications with piecewise time-varying robustness. Our time-varying robustness is less conservative than the real-valued robustness, which enables more effective tracking in practical applications. Specifically, our continuous-time trajectories account for dynamic feasibility, leading to smaller tracking errors and ensuring that the STL specifications can be met by the tracking trajectory. Comparative experiments demonstrate the efficiency and effectiveness of the proposed approach.

We establish a correspondence between a supersymmetric mass deformation of the IKKT matrix integral at large $N$ and a background of Euclidean type IIB string theory. Both sides have sixteen supersymmetries and an $SO(3)\times SO(7)$ symmetry. In the limit of large mass the integral is dominated by a fuzzy sphere saddle point. This saddle corresponds to a Euclidean $D1$-brane in a finite, Euclidean, ellipsoidal cavity. The cavity is supported by three-form NSNS flux that polarises $N$ $D$-instantons into the $D1$-brane. We furthermore use supersymmetric localisation to show that the deformed matrix integral can be reduced to a moduli space integral, allowing exact results away from the large mass limit. At small mass the $D1$-branes can backreact on the geometry, and we discuss the possible formulation of a `timeless' holography in such regimes., Comment: 34+29 pages. 3 figures

This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, spanning multiple domains, including computer science, mathematics, natural sciences, medicine, linguistics, and social sciences. Through rigorous testing, o1-preview demonstrated remarkable capabilities, often achieving human-level or superior performance in areas ranging from coding challenges to scientific reasoning and from language processing to creative problem-solving. Key findings include: -83.3% success rate in solving complex competitive programming problems, surpassing many human experts. -Superior ability in generating coherent and accurate radiology reports, outperforming other evaluated models. -100% accuracy in high school-level mathematical reasoning tasks, providing detailed step-by-step solutions. -Advanced natural language inference capabilities across general and specialized domains like medicine. -Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis. -Remarkable proficiency in anthropology and geology, demonstrating deep understanding and reasoning in these specialized fields. -Strong capabilities in quantitative investing. O1 has comprehensive financial knowledge and statistical modeling skills. -Effective performance in social media analysis, including sentiment analysis and emotion recognition. The model excelled particularly in tasks requiring intricate reasoning and knowledge integration across various fields. While some limitations were observed, including occasional errors on simpler problems and challenges with certain highly specialized concepts, the overall results indicate significant progress towards artificial general intelligence.

This paper investigates the problem of adaptive detection of distributed targets in power heterogeneous clutter. In the considered scenario, all the data share the identical structure of clutter covariance matrix, but with varying and unknown power mismatches. To address this problem, we iteratively estimate all the unknowns, including the coordinate matrix of the target, the clutter covariance matrix, and the corresponding power mismatches, and propose three detectors based on the generalized likelihood ratio test (GLRT), Rao and the Wald tests. The results from simulated and real data both illustrate that the detectors based on GLRT and Rao test have higher probabilities of detection (PDs) than the existing competitors. Among them, the Rao test-based detector exhibits the best overall detection performance. We also analyze the impact of the target extended dimensions, the signal subspace dimensions, and the number of training samples on the detection performance. Furthermore, simulation experiments also demonstrate that the proposed detectors have a constant false alarm rate (CFAR) property for the structure of clutter covariance matrix., Comment: 9 pages, 11 figures. This manuscript is accepted in IEEE Sensors Journal

Graph Neural Networks (GNNs) are powerful deep learning models designed for graph-structured data, demonstrating effectiveness across a wide range of applications.The softmax function is the most commonly used classifier for semi-supervised node classification. However, the softmax function lacks spatial information of the graph structure. In this paper, we propose a graph similarity regularized softmax for GNNs in semi-supervised node classification. By incorporating non-local total variation (TV) regularization into the softmax activation function, we can more effectively capture the spatial information inherent in graphs. The weights in the non-local gradient and divergence operators are determined based on the graph's adjacency matrix. We apply the proposed method into the architecture of GCN and GraphSAGE, testing them on citation and webpage linking datasets, respectively. Numerical experiments demonstrate its good performance in node classification and generalization capabilities. These results indicate that the graph similarity regularized softmax is effective on both assortative and disassortative graphs.

We propose a Mamba accelerator with reconfigurable architecture, MARCA.We propose three novel approaches in this paper. (1) Reduction alternative PE array architecture for both linear and element-wise operations. For linear operations, the reduction tree connected to PE arrays is enabled and executes the reduction operation. For element-wise operations, the reduction tree is disabled and the output bypasses. (2) Reusable nonlinear function unit based on the reconfigurable PE. We decompose the exponential function into element-wise operations and a shift operation by a fast biased exponential algorithm, and the activation function (SiLU) into a range detection and element-wise operations by a piecewise approximation algorithm. Thus, the reconfigurable PEs are reused to execute nonlinear functions with negligible accuracy loss.(3) Intra-operation and inter-operation buffer management strategy. We propose intra-operation buffer management strategy to maximize input data sharing for linear operations within operations, and inter-operation strategy for element-wise operations between operations. We conduct extensive experiments on Mamba model families with different sizes.MARCA achieves up to 463.22$\times$/11.66$\times$ speedup and up to 9761.42$\times$/242.52$\times$ energy efficiency compared to Intel Xeon 8358P CPU and NVIDIA Tesla A100 GPU implementations, respectively., Comment: 9 pages, 10 figures, accepted by ICCAD 2024. arXiv admin note: text overlap with arXiv:2001.02514 by other authors

Analyzing and certifying stability and attractivity of nonlinear systems is a topic of research interest that has been extensively investigated by control theorists and engineers for many years. Despite that, accurately estimating domains of attraction for nonlinear systems remains a challenging task, where available estimation approaches are either conservative or limited to low-dimensional systems. In this work, we propose an iterative approach to accurately underapproximate safe (i.e., state-constrained) domains of attraction for general discrete-time autonomous nonlinear systems. Our approach relies on implicit representations of safe backward reachable sets of safe regions of attraction, where such regions can be be easily constructed using, e.g., quadratic Lyapunov functions. The iterations of our approach are monotonic (in the sense of set inclusion), where each iteration results in a safe region of attraction, given as a sublevel set, that underapproximates the safe domain of attraction. The sublevel set representations of the resulting regions of attraction can be efficiently utilized in verifying the inclusion of given points of interest in the safe domain of attraction. We illustrate our approach through two numerical examples, involving two- and four-dimensional nonlinear systems.

AI-based systems possess distinctive characteristics and introduce challenges in quality evaluation at the same time. Consequently, ensuring and validating AI software quality is of critical importance. In this paper, we present an effective AI software functional testing model to address this challenge. Specifically, we first present a comprehensive literature review of previous work, covering key facets of AI software testing processes. We then introduce a 3D classification model to systematically evaluate the image-based text extraction AI function, as well as test coverage criteria and complexity. To evaluate the performance of our proposed AI software quality test, we propose four evaluation metrics to cover different aspects. Finally, based on the proposed framework and defined metrics, a mobile Optical Character Recognition (OCR) case study is presented to demonstrate the framework's effectiveness and capability in assessing AI function quality.

The quality control of printed circuit boards (PCBs) is paramount in advancing electronic device technology. While numerous machine learning methodologies have been utilized to augment defect detection efficiency and accuracy, previous studies have predominantly focused on optimizing individual models for specific defect types, often overlooking the potential synergies between different approaches. This paper introduces a comprehensive inspection framework leveraging an ensemble learning strategy to address this gap. Initially, we utilize four distinct PCB defect detection models utilizing state-of-the-art methods: EfficientDet, MobileNet SSDv2, Faster RCNN, and YOLOv5. Each method is capable of identifying PCB defects independently. Subsequently, we integrate these models into an ensemble learning framework to enhance detection performance. A comparative analysis reveals that our ensemble learning framework significantly outperforms individual methods, achieving a 95% accuracy in detecting diverse PCB defects. These findings underscore the efficacy of our proposed ensemble learning framework in enhancing PCB quality control processes.

In this paper, we study the problem of Text-to-Image Person Re-identification (TIReID), which aims to find images of the same identity described by a text sentence from a pool of candidate images. Benefiting from Vision-Language Pre-training, such as CLIP (Contrastive Language-Image Pretraining), the TIReID techniques have achieved remarkable progress recently. However, most existing methods only focus on instance-level matching and ignore identity-level matching, which involves associating multiple images and texts belonging to the same person. In this paper, we propose a novel prototypical prompting framework (Propot) designed to simultaneously model instance-level and identity-level matching for TIReID. Our Propot transforms the identity-level matching problem into a prototype learning problem, aiming to learn identity-enriched prototypes. Specifically, Propot works by 'initialize, adapt, enrich, then aggregate'. We first use CLIP to generate high-quality initial prototypes. Then, we propose a domain-conditional prototypical prompting (DPP) module to adapt the prototypes to the TIReID task using task-related information. Further, we propose an instance-conditional prototypical prompting (IPP) module to update prototypes conditioned on intra-modal and inter-modal instances to ensure prototype diversity. Finally, we design an adaptive prototype aggregation module to aggregate these prototypes, generating final identity-enriched prototypes. With identity-enriched prototypes, we diffuse its rich identity information to instances through prototype-to-instance contrastive loss to facilitate identity-level matching. Extensive experiments conducted on three benchmarks demonstrate the superiority of Propot compared to existing TIReID methods., Comment: Accepted by ACM MM2024

Designing a stabilizing controller for nonlinear systems is a challenging task, especially for high-dimensional problems with unknown dynamics. Traditional reinforcement learning algorithms applied to stabilization tasks tend to drive the system close to the equilibrium point. However, these approaches often fall short of achieving true stabilization and result in persistent oscillations around the equilibrium point. In this work, we propose a reinforcement learning algorithm that stabilizes the system by learning a local linear representation ofthe dynamics. The main component of the algorithm is integrating the learned gain matrix directly into the neural policy. We demonstrate the effectiveness of our algorithm on several challenging high-dimensional dynamical systems. In these simulations, our algorithm outperforms popular reinforcement learning algorithms, such as soft actor-critic (SAC) and proximal policy optimization (PPO), and successfully stabilizes the system. To support the numerical results, we provide a theoretical analysis of the feasibility of the learned algorithm for both deterministic and stochastic reinforcement learning settings, along with a convergence analysis of the proposed learning algorithm. Furthermore, we verify that the learned control policies indeed provide asymptotic stability for the nonlinear systems.

Machine learning (ML) models have become increasingly valuable in weather forecasting, providing forecasts that not only lower computational costs but often match or exceed the accuracy of traditional numerical weather prediction (NWP) models. Despite their potential, ML models typically suffer from limitations such as coarse temporal resolution, typically 6 hours, and a limited set of meteorological variables, limiting their practical applicability. To overcome these challenges, we introduce FuXi-2.0, an advanced ML model that delivers 1-hourly global weather forecasts and includes a comprehensive set of essential meteorological variables, thereby expanding its utility across various sectors like wind and solar energy, aviation, and marine shipping. Our study conducts comparative analyses between ML-based 1-hourly forecasts and those from the high-resolution forecast (HRES) of the European Centre for Medium-Range Weather Forecasts (ECMWF) for various practical scenarios. The results demonstrate that FuXi-2.0 consistently outperforms ECMWF HRES in forecasting key meteorological variables relevant to these sectors. In particular, FuXi-2.0 shows superior performance in wind power forecasting compared to ECMWF HRES, further validating its efficacy as a reliable tool for scenarios demanding precise weather forecasts. Additionally, FuXi-2.0 also integrates both atmospheric and oceanic components, representing a significant step forward in the development of coupled atmospheric-ocean models. Further comparative analyses reveal that FuXi-2.0 provides more accurate forecasts of tropical cyclone intensity than its predecessor, FuXi-1.0, suggesting that there are benefits of an atmosphere-ocean coupled model over atmosphere-only models.

Chart Question Answering (CQA) aims at answering questions based on the visual chart content, which plays an important role in chart sumarization, business data analysis, and data report generation. CQA is a challenging multi-modal task because of the strong context dependence and complex reasoning requirement. The former refers to answering this question strictly based on the analysis of the visual content or internal data of the given chart, while the latter emphasizes the various logical and numerical reasoning involved in answer prediction process. In this paper, we pay more attention on the complex reasoning in CQA task, and propose a novel Graph-of-Thought (GoT) guided compositional reasoning model called GoT-CQA to overcome this problem. At first, we transform the chart-oriented question into a directed acyclic GoT composed of multiple operator nodes, including localization, numerical and logical operator. It intuitively reflects the human brain's solution process to this question. After that, we design an efficient auto-compositional reasoning framework guided by the GoT, to excute the multi-step reasoning operations in various types of questions. Comprehensive experiments on ChartQA and PlotQA-D datasets show that GoT-CQA achieves outstanding performance, especially in complex human-written and reasoning questions, comparing with the latest popular baselines.

Large Language Models (LLMs) may suffer from hallucinations in real-world applications due to the lack of relevant knowledge. In contrast, knowledge graphs encompass extensive, multi-relational structures that store a vast array of symbolic facts. Consequently, integrating LLMs with knowledge graphs has been extensively explored, with Knowledge Graph Question Answering (KGQA) serving as a critical touchstone for the integration. This task requires LLMs to answer natural language questions by retrieving relevant triples from knowledge graphs. However, existing methods face two significant challenges: \textit{excessively long reasoning paths distracting from the answer generation}, and \textit{false-positive relations hindering the path refinement}. In this paper, we propose an iterative interactive KGQA framework that leverages the interactive learning capabilities of LLMs to perform reasoning and Debating over Graphs (DoG). Specifically, DoG employs a subgraph-focusing mechanism, allowing LLMs to perform answer trying after each reasoning step, thereby mitigating the impact of lengthy reasoning paths. On the other hand, DoG utilizes a multi-role debate team to gradually simplify complex questions, reducing the influence of false-positive relations. This debate mechanism ensures the reliability of the reasoning process. Experimental results on five public datasets demonstrate the effectiveness and superiority of our architecture. Notably, DoG outperforms the state-of-the-art method ToG by 23.7\% and 9.1\% in accuracy on WebQuestions and GrailQA, respectively. Furthermore, the integration experiments with various LLMs on the mentioned datasets highlight the flexibility of DoG. Code is available at \url{https://github.com/reml-group/DoG}., Comment: 12 pages

Charts are widely used for data visualization across various fields, including education, research, and business. Chart Question Answering (CQA) is an emerging task focused on the automatic interpretation and reasoning of data presented in charts. However, chart images are inherently difficult to interpret, and chart-related questions often involve complex logical and numerical reasoning, which hinders the performance of existing models. This paper introduces VProChart, a novel framework designed to address these challenges in CQA by integrating a lightweight Visual Perception Alignment Agent (VPAgent) and a Programmatic Solution Reasoning approach. VPAgent aligns and models chart elements based on principles of human visual perception, enhancing the understanding of chart context. The Programmatic Solution Reasoning approach leverages large language models (LLMs) to transform natural language reasoning questions into structured solution programs, facilitating precise numerical and logical reasoning. Extensive experiments on benchmark datasets such as ChartQA and PlotQA demonstrate that VProChart significantly outperforms existing methods, highlighting its capability in understanding and reasoning with charts.

Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension. While existing Visual Language Models (VLMs) have shown progress in chart understanding, the lack of high-quality training data and comprehensive evaluation benchmarks hinders VLM chart comprehension. In this paper, we introduce EvoChart, a novel self-training method for generating synthetic chart data to enhance VLMs' capabilities in real-world chart comprehension. We also propose EvoChart-QA, a noval benchmark for measuring models' chart comprehension abilities in real-world scenarios. Specifically, EvoChart is a unique self-training data synthesis approach that simultaneously produces high-quality training corpus and a high-performance chart understanding model. EvoChart-QA consists of 650 distinct real-world charts collected from 140 different websites and 1,250 expert-curated questions that focus on chart understanding. Experimental results on various open-source and proprietary VLMs tested on EvoChart-QA demonstrate that even the best proprietary model, GPT-4o, achieves only 49.8% accuracy. Moreover, the EvoChart method significantly boosts the performance of open-source VLMs on real-world chart understanding tasks, achieving 54.2% accuracy on EvoChart-QA.

We employ the nuclear lattice effective field theory (NLEFT), an efficient tool for nuclear ab initio calculations, to solve the asymmetric multi-hadron systems. We take the $DD^*K$ three-body system as an illustration to demonstrate the capability of the method. Here the two-body chiral interactions between $D$, $D^*$ and $K$ are regulated with a soft lattice regulator and calibrated with the binding energies of the $T_{cc}^+$, $D^{*}_{s0}(2317)$ and $D_{s1}(2460)$ molecular states. We then calculate the three-body binding energy using the NLEFT and analyze the systematic uncertainties due to the finite volume effects, the sliding cutoff and the leading-order three-body forces. Even when the three-body interaction is repulsive (even as large as the infinite repulsive interaction), the three-body system has a bound state unambiguously with binding energy no larger than the $D_{s1}(2460)D$ threshold. To check the renormalization group invariance of our framework, we extract the first excited state. We find that when the ground state is fixed, the first excited states with various cutoffs coincide with each other when the cubic size goes larger. In addition, the standard angular momentum and parity projection technique is implemented for the quantum numbers of the ground and excited states. We find that both of them are S-wave states with quantum number $J^{P}=1^-$. Because the three-body state contains two charm quarks, it is easier to be detected in the Large Hadron Collider., Comment: 17 pages, 6 figures

Language based editing of 3D human avatars to precisely match user requirements is challenging due to the inherent ambiguity and limited expressiveness of natural language. To overcome this, we propose the Avatar Concept Slider (ACS), a 3D avatar editing method that allows precise manipulation of semantic concepts in human avatars towards a specified intermediate point between two extremes of concepts, akin to moving a knob along a slider track. To achieve this, our ACS has three designs. 1) A Concept Sliding Loss based on Linear Discriminant Analysis to pinpoint the concept-specific axis for precise editing. 2) An Attribute Preserving Loss based on Principal Component Analysis for improved preservation of avatar identity during editing. 3) A 3D Gaussian Splatting primitive selection mechanism based on concept-sensitivity, which updates only the primitives that are the most sensitive to our target concept, to improve efficiency. Results demonstrate that our ACS enables fine-grained 3D avatar editing with efficient feedback, without harming the avatar quality or compromising the avatar's identifying attributes.

The performance of anomaly inspection in industrial manufacturing is constrained by the scarcity of anomaly data. To overcome this challenge, researchers have started employing anomaly generation approaches to augment the anomaly dataset. However, existing anomaly generation methods suffer from limited diversity in the generated anomalies and struggle to achieve a seamless blending of this anomaly with the original image. In this paper, we overcome these challenges from a new perspective, simultaneously generating a pair of the overall image and the corresponding anomaly part. We propose DualAnoDiff, a novel diffusion-based few-shot anomaly image generation model, which can generate diverse and realistic anomaly images by using a dual-interrelated diffusion model, where one of them is employed to generate the whole image while the other one generates the anomaly part. Moreover, we extract background and shape information to mitigate the distortion and blurriness phenomenon in few-shot image generation. Extensive experiments demonstrate the superiority of our proposed model over state-of-the-art methods in terms of both realism and diversity. Overall, our approach significantly improves the performance of downstream anomaly detection tasks, including anomaly detection, anomaly localization, and anomaly classification tasks., Comment: Code: https://github.com/yinyjin/DualAnoDiff

General matrix multiplication (GEMM) operations are crucial in various computational fields. As GPU architectures evolve, optimizing GEMM performance becomes increasingly important. This paper introduces Stream-K++, an enhancement to the promising Stream-K GEMM scheduling algorithm. We expand Stream-K's scheduling policies from three to seven and implement an efficient solution selection mechanism using Bloom filters. Our approach rapidly eliminates up to 95.8% of unsuitable configurations while maintaining a 100% true-negative rate. Implemented using the AMD Composable Kernel library and evaluated on AMD Instinct MI250X GPUs, Stream-K++ demonstrates significant performance gains (up to 43%) in select scenarios. It remains competitive (within 20% of optimal) for 60-97.6% of problem sizes. Our flexible framework, implemented in the Opensieve C++ library, allows for easy adaptation to new problem sizes, scheduling policies, or additional tuning parameters, paving the way for future optimizations in GPU-based GEMM operations.

Neural-based multi-task learning (MTL) has been successfully applied to many recommendation applications. However, these MTL models (e.g., MMoE, PLE) did not consider feature interaction during the optimization, which is crucial for capturing complex high-order features and has been widely used in ranking models for real-world recommender systems. Moreover, through feature importance analysis across various tasks in MTL, we have observed an interesting divergence phenomenon that the same feature can have significantly different importance across different tasks in MTL. To address these issues, we propose Deep Multiple Task-specific Feature Interactions Network (DTN) with a novel model structure design. DTN introduces multiple diversified task-specific feature interaction methods and task-sensitive network in MTL networks, enabling the model to learn task-specific diversified feature interaction representations, which improves the efficiency of joint representation learning in a general setup. We applied DTN to our company's real-world E-commerce recommendation dataset, which consisted of over 6.3 billion samples, the results demonstrated that DTN significantly outperformed state-of-the-art MTL models. Moreover, during online evaluation of DTN in a large-scale E-commerce recommender system, we observed a 3.28% in clicks, a 3.10% increase in orders and a 2.70% increase in GMV (Gross Merchandise Value) compared to the state-of-the-art MTL models. Finally, extensive offline experiments conducted on public benchmark datasets demonstrate that DTN can be applied to various scenarios beyond recommendations, enhancing the performance of ranking models.

Skeleton Action Recognition (SAR) has attracted significant interest for its efficient representation of the human skeletal structure. Despite its advancements, recent studies have raised security concerns in SAR models, particularly their vulnerability to adversarial attacks. However, such strategies are limited to digital scenarios and ineffective in physical attacks, limiting their real-world applicability. To investigate the vulnerabilities of SAR in the physical world, we introduce the Physical Skeleton Backdoor Attacks (PSBA), the first exploration of physical backdoor attacks against SAR. Considering the practicalities of physical execution, we introduce a novel trigger implantation method that integrates infrequent and imperceivable actions as triggers into the original skeleton data. By incorporating a minimal amount of this manipulated data into the training set, PSBA enables the system misclassify any skeleton sequences into the target class when the trigger action is present. We examine the resilience of PSBA in both poisoned and clean-label scenarios, demonstrating its efficacy across a range of datasets, poisoning ratios, and model architectures. Additionally, we introduce a trigger-enhancing strategy to strengthen attack performance in the clean label setting. The robustness of PSBA is tested against three distinct backdoor defenses, and the stealthiness of PSBA is evaluated using two quantitative metrics. Furthermore, by employing a Kinect V2 camera, we compile a dataset of human actions from the real world to mimic physical attack situations, with our findings confirming the effectiveness of our proposed attacks. Our project website can be found at https://qichenzheng.github.io/psba-website., Comment: Accepted by ECCV 2024

Deep neural networks are proven to be vulnerable to data poisoning attacks. Recently, a specific type of data poisoning attack known as availability attacks has led to the failure of data utilization for model learning by adding imperceptible perturbations to images. Consequently, it is quite beneficial and challenging to detect poisoned samples, also known as Unlearnable Examples (UEs), from a mixed dataset. In response, we propose an Iterative Filtering approach for UEs identification. This method leverages the distinction between the inherent semantic mapping rules and shortcuts, without the need for any additional information. We verify that when training a classifier on a mixed dataset containing both UEs and clean data, the model tends to quickly adapt to the UEs compared to the clean data. Due to the accuracy gaps between training with clean/poisoned samples, we employ a model to misclassify clean samples while correctly identifying the poisoned ones. The incorporation of additional classes and iterative refinement enhances the model's ability to differentiate between clean and poisoned samples. Extensive experiments demonstrate the superiority of our method over state-of-the-art detection approaches across various attacks, datasets, and poison ratios, significantly reducing the Half Total Error Rate (HTER) compared to existing methods., Comment: Accepted by ICANN 2024

The stacked intelligent metasurface (SIM) emerges as an innovative technology with the ability to directly manipulate electromagnetic (EM) wave signals, drawing parallels to the operational principles of artificial neural networks (ANN). Leveraging its structure for direct EM signal processing alongside its low-power consumption, SIM holds promise for enhancing system performance within wireless communication systems. In this paper, we focus on SIM-assisted multi-user multi-input and single-output (MU-MISO) system downlink scenarios in the transmitter. We proposed a joint optimization method for SIM phase shift configuration and antenna power allocation based on the twin delayed deep deterministic policy gradient (TD3) algorithm to efficiently improve the sum rate. The results show that the proposed algorithm outperforms both deep deterministic policy gradient (DDPG) and alternating optimization (AO) algorithms. Furthermore, increasing the number of meta-atoms per layer of the SIM is always beneficial. However, continuously increasing the number of layers of SIM does not lead to sustained performance improvement., Comment: accepted by IEEE GLOBECOM 2024

In real-world scenarios, where knowledge distributions exhibit long-tail. Humans manage to master knowledge uniformly across imbalanced distributions, a feat attributed to their diligent practices of reviewing, summarizing, and correcting errors. Motivated by this learning process, we propose a novel learning paradigm, called reflecting learning, in handling long-tail recognition. Our method integrates three processes for reviewing past predictions during training, summarizing and leveraging the feature relation across classes, and correcting gradient conflict for loss functions. These designs are lightweight enough to plug and play with existing long-tail learning methods, achieving state-of-the-art performance in popular long-tail visual benchmarks. The experimental results highlight the great potential of reflecting learning in dealing with long-tail recognition., Comment: ECCV2024, Oral

We are witnessing a surge in the use of commercial off-the-shelf (COTS) hardware for cost-effective in-orbit computing, such as deep neural network (DNN) based on-satellite sensor data processing, Earth object detection, and task decision.However, once exposed to harsh space environments, COTS hardware is vulnerable to cosmic radiation and suffers from exhaustive single-event upsets (SEUs) and multi-unit upsets (MCUs), both threatening the functionality and correctness of in-orbit computing.Existing hardware and system software protections against radiation are expensive for resource-constrained COTS nanosatellites and overwhelming for upper-layer applications due to their requirement for heavy resource redundancy and frequent reboots. Instead, we make a case for cost-effective space radiation tolerance using application domain knowledge. Our solution for the on-satellite DNN tasks, \name, exploits the uneven SEU/MCU sensitivity across DNN layers and MCUs' spatial correlation for lightweight radiation-tolerant in-orbit AI computing. Our extensive experiments using Chaohu-1 SAR satellite payloads and a hardware-in-the-loop, real data-driven space radiation emulator validate that RedNet can suppress the influence of radiation errors to $\approx$ 0 and accelerate the on-satellite DNN inference speed by 8.4%-33.0% at negligible extra costs.

We present REMM, a rotation-equivariant framework for end-to-end multimodal image matching, which fully encodes rotational differences of descriptors in the whole matching pipeline. Previous learning-based methods mainly focus on extracting modal-invariant descriptors, while consistently ignoring the rotational invariance. In this paper, we demonstrate that our REMM is very useful for multimodal image matching, including multimodal feature learning module and cyclic shift module. We first learn modal-invariant features through the multimodal feature learning module. Then, we design the cyclic shift module to rotationally encode the descriptors, greatly improving the performance of rotation-equivariant matching, which makes them robust to any angle. To validate our method, we establish a comprehensive rotation and scale-matching benchmark for evaluating the anti-rotation performance of multimodal images, which contains a combination of multi-angle and multi-scale transformations from four publicly available datasets. Extensive experiments show that our method outperforms existing methods in benchmarking and generalizes well to independent datasets. Additionally, we conducted an in-depth analysis of the key components of the REMM to validate the improvements brought about by the cyclic shift module. Code and dataset at https://github.com/HanNieWHU/REMM., Comment: 13 pages, 13 figures

Machine unlearning (MU) seeks to remove knowledge of specific data samples from trained models without the necessity for complete retraining, a task made challenging by the dual objectives of effective erasure of data and maintaining the overall performance of the model. Despite recent advances in this field, balancing between the dual objectives of unlearning remains challenging. From a fresh perspective of generalization, we introduce a novel Learning-to-Unlearn (LTU) framework, which adopts a meta-learning approach to optimize the unlearning process to improve forgetting and remembering in a unified manner. LTU includes a meta-optimization scheme that facilitates models to effectively preserve generalizable knowledge with only a small subset of the remaining set, while thoroughly forgetting the specific data samples. We also introduce a Gradient Harmonization strategy to align the optimization trajectories for remembering and forgetting via mitigating gradient conflicts, thus ensuring efficient and effective model updates. Our approach demonstrates improved efficiency and efficacy for MU, offering a promising solution to the challenges of data rights and model reusability., Comment: Accepted by ECCV 2024

We introduce Diff-Tracker, a novel approach for the challenging unsupervised visual tracking task leveraging the pre-trained text-to-image diffusion model. Our main idea is to leverage the rich knowledge encapsulated within the pre-trained diffusion model, such as the understanding of image semantics and structural information, to address unsupervised visual tracking. To this end, we design an initial prompt learner to enable the diffusion model to recognize the tracking target by learning a prompt representing the target. Furthermore, to facilitate dynamic adaptation of the prompt to the target's movements, we propose an online prompt updater. Extensive experiments on five benchmark datasets demonstrate the effectiveness of our proposed method, which also achieves state-of-the-art performance., Comment: ECCV 2024

Early detection and accurate diagnosis can predict the risk of malignant disease transformation, thereby increasing the probability of effective treatment. Identifying mild syndrome with small pathological regions serves as an ominous warning and is fundamental in the early diagnosis of diseases. While deep learning algorithms, particularly convolutional neural networks (CNNs), have shown promise in segmenting medical objects, analyzing small areas in medical images remains challenging. This difficulty arises due to information losses and compression defects from convolution and pooling operations in CNNs, which become more pronounced as the network deepens, especially for small medical objects. To address these challenges, we propose a novel scale-variant attention-based network (SvANet) for accurately segmenting small-scale objects in medical images. The SvANet consists of scale-variant attention, cross-scale guidance, Monte Carlo attention, and vision transformer, which incorporates cross-scale features and alleviates compression artifacts for enhancing the discrimination of small medical objects. Quantitative experimental results demonstrate the superior performance of SvANet, achieving 96.12%, 96.11%, 89.79%, 84.15%, 80.25%, 73.05%, and 72.58% in mean Dice coefficient for segmenting kidney tumors, skin lesions, hepatic tumors, polyps, surgical excision cells, retinal vasculatures, and sperms, which occupy less than 1% of the image areas in KiTS23, ISIC 2018, ATLAS, PolypGen, TissueNet, FIVES, and SpermHealth datasets, respectively., Comment: 14 pages, 9 figures, under review

Magnetic skyrmions emerge as promising quasi-particles for encoding information in nextgeneration spintronic devices. Their innate flexibility in shape is essential for the applications although they were often ideally treated as rigid particles. In this work, we investigated the voltagecontrolled uniform strain mediated dynamics of deformed skyrmions in heterostructures with a flower-shaped magnetic nanostructure, using micromagnetic simulations. The simulated results revealed the possible states of isolated skyrmion nucleated in the nanostructure, which can be mutually switched by applying suitable in-plane strain pulses. In addition, it was found that the skyrmion motions are driven by the emerging internal forces and strain force, which originate from the asymmetric deformation of skyrmion structures. Furthermore, an analytical model of deformed skyrmions was proposed to interpret the dependences of internal forces and strain force on the asymmetric deformation of skyrmion, with some formulae derived for these forces in a semi-analytical approach. Further calculations based on these formulae verified the forces appearing in the skyrmion motion, with the resulting forces showing consistence with the simulated data. This suggested that our semi-analytical model successfully captures the main physics responsible for the motion of deformed skyrmion in the nanostructure. Our work extends the understanding of the mechanics emerging in deformed skyrmion, and provides an effective approach for deterministic manipulation of deformed skyrmion motion via strain forces and internal forces, which may be instructive to design of skyrmion-based spintronic devices.

We conduct a reverberation mapping (RM) campaign to spectroscopically monitor a sample of selected bright active galactic nuclei with large anticipated broad-line region (BLR) sizes adequate for spectroastrometric observations by the GRAVITY instrument on the Very Large Telescope Interferometer. We report the first results for five objects, IC 4329A, Mrk 335, Mrk 509, Mrk 1239, and PDS 456, among which Mrk 1239 and PDS 456 are for the first time spectroscopically monitored. We obtain multi-year monitoring data and perform multi-component spectral decomposition to extract the broad H$\beta$ profiles. We detect significant time lags between the H$\beta$ and continuum variations, generally obeying the previously established BLR size-luminosity relation. Velocity-resolved H$\beta$ time lags illustrate diverse, possibly evolving BLR kinematics. We further measure the H$\beta$ line widths from mean and rms spectra and the resulting virial products show good consistency among different seasons. Adopting a unity virial factor and the full width at half maximum of the broad H$\beta$ line from the mean spectrum as the measure of velocity, the obtained black hole mass averaged over seasons is $\log M_\bullet/M_\odot=8.02_{-0.14}^{+0.09}$, $6.92_{-0.12}^{+0.12}$, $8.01_{-0.25}^{+0.16}$, $7.44_{-0.14}^{+0.13}$, and $8.59_{-0.11}^{+0.07}$ for the five objects, respectively. The black hole mass estimations using other line width measures are also reported (up to the virial factors). For objects with previous RM campaigns, our mass estimates are in agreement with earlier results. In a companion paper, we will employ BLR dynamical modeling to directly infer the black hole mass and thereby determine the virial factors., Comment: 32 pages, 6 tables, 20 figures. To appear in ApJ

Emerging integrated space and terrestrial networks (ISTN) built upon low earth orbit (LEO) satellite constellations aim at providing planet-wide Internet services, not only for residential users, but also for mobile users (e.g., in airplane and cruise scenarios). Efficiently managing global mobility and keeping connections active for mobile users is critical for ISTN operators. However, our quantitative analysis identifies that existing mobility management (MM) schemes suffer from frequent connection interruptions and long latency in ISTN scenarios. The fundamental challenge stems from a unique characteristic of ISTNs: not only users are mobile, but also core network infrastructures (i.e., LEO satellites) are frequently changing their locations in the network. To facilitate seamless and low-latency satellite Internet services, this paper presents SKYCASTLE, a novel network-based global mobility management mechanism. SKYCASTLE incorporates two key techniques to address frequent connection interruptions in ISTNs. First, to reduce the interruption time, SKYCASTLE adopts distributed satellite anchors to track the location changes of mobile nodes, manage handovers and avoid routing convergence. Second, SKYCASTLE leverages an anchor manager to schedule MM functionalities at satellites to reduce deployment costs while guaranteeing low latency. Extensive evaluations combining real constellation information and mobile user trajectories show that: SKYCASTLE can improve up to 55.8% uninterrupted time and reduce 47.8% latency as compared to other existing MM solutions., Comment: 10 pages, 10 figures, accepted by IEEE INFOCOM 2024

With the rapid evolution of space-borne capabilities, space edge computing (SEC) is becoming a new computation paradigm for future integrated space and terrestrial networks. Satellite edges adopt advanced on-board hardware, which not only enables new opportunities to perform complex intelligent tasks in orbit, but also involves new challenges due to the additional energy consumption in power-constrained space environment. In this paper, we present PHOENIX, an energy-efficient task scheduling framework for emerging SEC networks. PHOENIX exploits a key insight that in the SEC network, there always exist a number of sunlit edges which are illuminated during the entire orbital period and have sufficient energy supplement from the sun. PHOENIX accomplishes energy-efficient in-orbit computing by judiciously offloading space tasks to "sunlight-sufficient" edges or to the ground. Specifically, PHOENIX first formulates the SEC battery energy optimizing (SBEO) problem which aims at minimizing the average battery energy consumption while satisfying various task completion constraints. Then PHOENIX incorporates a sunlight-aware scheduling mechanism to solve the SBEO problem and schedule SEC tasks efficiently. Finally, we implement a PHOENIX prototype and build an SEC testbed. Extensive data-driven evaluations demonstrate that as compared to other state-of-the-art solutions, PHOENIX can effectively reduce up to 54.8% SEC battery energy consumption and prolong battery lifetime to 2.9$\times$ while still completing tasks on time., Comment: Accepted by IEEE INFOCOM 2024

Non-Hermitian dynamics in quantum systems have unveiled novel phenomena, yet the implementation of valid non-Hermitian quantum measurement remains a challenge, because a universal quantum projective mechanism on the complete but skewed non-Hermitian eigenstates is not explicit in experiment. This limitation hinders the direct acquisition of non-Hermitian observable statistics (e.g., non-Hermitian population dynamics), also constrains investigations of non-Hermitian quantum measurement properties such as uncertainty relation. Here, we address these challenges by presenting a non-Hermitian projective protocol and investigating the non-Hermitian uncertainty relation. We derive the uncertainty relation for pseudo-Hermitian (PH) observables that is generalized beyond the Hermitian ones. We then investigate the projective properties of general quantum states onto complete non-Hermitian eigenvectors, and present a quantum simulating method to apply the valid non-Hermitian projective measurement on a direct-sum dilated space. Subsequently, we experimentally construct a quantum simulator in the quantum optical circuit and realize the 3-dimensional non-Hermitian quantum measurement on the single-photon qutrit. Employing this platform, we explore the uncertainty relation experimentally with different PH metrics. Our non-Hermitian quantum measurement method is state-independent and outputs directly the non-Hermitian quantum projective statistics, paving the way for studies of extensive non-Hermitian observable in quantum domain., Comment: 6 pages, 4 figures

In this paper, we investigate an important research problem facing the upcoming satellite Internet: from a network perspective, how many satellites exactly do we need to construct a survivable and performant LSN? To answer this question, we first formulate the survivable and performant LSN design (SPLD) problem, which aims to find the minimum number of needed satellites to construct an LSN that can provide sufficient amount of redundant paths, required link capacity and acceptable latency for traffic carried by the LSN. Second, to efficiently solve the tricky SPLD problem, we propose MEGAREDUCE, a requirement-driven constellation optimization mechanism, which can calculate feasible solutions for SPLD in polynomial time. Finally, we conduct extensive trace-driven simulations to verify MEGAREDUCE's cost-effectiveness in constructing survivable and performant LSNs on demand, and showcase how MEGAREDUCE can help optimize the incremental deployment and long-term maintenance of future satellite Internet.

During software evolution, it is advocated that test code should co-evolve with production code. In real development scenarios, test updating may lag behind production code changing, which may cause the project to fail to compile or bring other troubles. Existing techniques based on pre-trained language models can be adopted to repair obsolete tests caused by such unsynchronized code changes, especially syntactic-related ones. However, the lack of target-oriented contextual information affects repair accuracy on large-scale projects. Starting from an obsoleted test, the key challenging task is precisely identifying and constructing Test-Repair-Oriented Contexts (TROCtx) from the whole repository within a limited token size. In this paper, we propose SynBCIATR (Syntactic-Breaking-Change-Induced Automated Test Repair), a novel approach to automatically repair obsolete test cases via precise and concise TROCtx construction. Inspired by developers' programming practices of the task, we design three types of TROCtx: class contexts, usage contexts, and environment contexts. For every type of TROCtx, SynBCIATR automatically collects the changed-token-related code information through static analysis techniques. Then it generates reranking queries to identify the most relevant TROCtxs, which will be taken as the repair-required key context and be input to the Large Language Model for the final test repair. To evaluate the effectiveness of SynBCIATR, we construct a benchmark dataset that contains diverse syntactic breaking changes. The experimental results show that SynBCIATR outperforms baseline approaches both on textual- and intent-matching metrics. With the augmentation of TROCtx constructed by SynBCIATR, hallucinations are reduced by 57.1%.

Anomaly detection, the technique of identifying abnormal samples using only normal samples, has attracted widespread interest in industry. Existing one-model-per-category methods often struggle with limited generalization capabilities due to their focus on a single category, and can fail when encountering variations in product. Recent feature reconstruction methods, as representatives in one-model-all-categories schemes, face challenges including reconstructing anomalous samples and blurry reconstructions. In this paper, we creatively combine a diffusion model and a transformer for multi-class anomaly detection. This approach leverages diffusion to obtain high-frequency information for refinement, greatly alleviating the blurry reconstruction problem while maintaining the sampling efficiency of the reverse diffusion process. The task is transformed into image inpainting to disconnect the input-output correlation, thereby mitigating the "identical shortcuts" problem and avoiding the model from reconstructing anomalous samples. Besides, we introduce category-awareness using dual conditioning to ensure the accuracy of prediction and reconstruction in the reverse diffusion process, preventing excessive deviation from the target category, thus effectively enabling multi-class anomaly detection. Futhermore, Spatio-temporal fusion is also employed to fuse heatmaps predicted at different timesteps and scales, enhancing the performance of multi-class anomaly detection. Extensive experiments on benchmark datasets demonstrate the superior performance and exceptional multi-class anomaly detection capabilities of our proposed method compared to others.