Search

Precise camera tracking, high-fidelity 3D tissue reconstruction, and real-time online visualization are critical for intrabody medical imaging devices such as endoscopes and capsule robots. However, existing SLAM (Simultaneous Localization and Mapping) methods often struggle to achieve both complete high-quality surgical field reconstruction and efficient computation, restricting their intraoperative applications among endoscopic surgeries. In this paper, we introduce EndoGSLAM, an efficient SLAM approach for endoscopic surgeries, which integrates streamlined Gaussian representation and differentiable rasterization to facilitate over 100 fps rendering speed during online camera tracking and tissue reconstructing. Extensive experiments show that EndoGSLAM achieves a better trade-off between intraoperative availability and reconstruction quality than traditional or neural SLAM approaches, showing tremendous potential for endoscopic surgeries. The project page is at https://EndoGSLAM.loping151.com

The conformational landscape of proteins is crucial to understanding their functionality in complex biological processes. Traditional physics-based computational methods, such as molecular dynamics (MD) simulations, suffer from rare event sampling and long equilibration time problems, hindering their applications in general protein systems. Recently, deep generative modeling techniques, especially diffusion models, have been employed to generate novel protein conformations. However, existing score-based diffusion methods cannot properly incorporate important physical prior knowledge to guide the generation process, causing large deviations in the sampled protein conformations from the equilibrium distribution. In this paper, to overcome these limitations, we propose a force-guided SE(3) diffusion model, ConfDiff, for protein conformation generation. By incorporating a force-guided network with a mixture of data-based score models, ConfDiff can generate protein conformations with rich diversity while preserving high fidelity. Experiments on a variety of protein conformation prediction tasks, including 12 fast-folding proteins and the Bovine Pancreatic Trypsin Inhibitor (BPTI), demonstrate that our method surpasses the state-of-the-art method., Comment: ICML 2024

Learned Image Compression (LIC) has achieved dramatic progress regarding objective and subjective metrics. MSE-based models aim to improve objective metrics while generative models are leveraged to improve visual quality measured by subjective metrics. However, they all suffer from blurring or deformation at low bit rates, especially at below $0.2bpp$. Besides, deformation on human faces and text is unacceptable for visual quality assessment, and the problem becomes more prominent on small faces and text. To solve this problem, we combine the advantage of MSE-based models and generative models by utilizing region of interest (ROI). We propose Hierarchical-ROI (H-ROI), to split images into several foreground regions and one background region to improve the reconstruction of regions containing faces, text, and complex textures. Further, we propose adaptive quantization by non-linear mapping within the channel dimension to constrain the bit rate while maintaining the visual quality. Exhaustive experiments demonstrate that our methods achieve better visual quality on small faces and text with lower bit rates, e.g., $0.7X$ bits of HiFiC and $0.5X$ bits of BPG.

The pleasure that often comes with eating can be further enhanced with intelligent technology, as the field of human-food interaction suggests. However, knowledge on how to design such pleasure-supporting eating systems is limited. To begin filling this knowledge gap, we designed "GustosonicSense", a novel gustosonic eating system that utilizes wireless earbuds for sensing different eating and drinking actions with a machine learning algorithm and trigger playful sounds as a way to facilitate pleasurable eating experiences. We present the findings from our design and a study that revealed how we can support the "stimulation", "hedonism", and "reflexivity" for playful human-food interactions. Ultimately, with our work, we aim to support interaction designers in facilitating playful experiences with food., Comment: To appear at CHI'24: The ACM Conference on Human Factors in Computing Systems (CHI), Honolulu, Hawaii, 2024

Generative adversial network (GAN) is a type of generative model that maps a high-dimensional noise to samples in target distribution. However, the dimension of noise required in GAN is not well understood. Previous approaches view GAN as a mapping from a continuous distribution to another continous distribution. In this paper, we propose to view GAN as a discrete sampler instead. From this perspective, we build a connection between the minimum noise required and the bits to losslessly compress the images. Furthermore, to understand the behaviour of GAN when noise dimension is limited, we propose divergence-entropy trade-off. This trade-off depicts the best divergence we can achieve when noise is limited. And as rate distortion trade-off, it can be numerically solved when source distribution is known. Finally, we verifies our theory with experiments on image generation., Comment: ICME24

Implicit neural representations (INRs) recently achieved great success in image representation and compression, offering high visual quality and fast rendering speeds with 10-1000 FPS, assuming sufficient GPU resources are available. However, this requirement often hinders their use on low-end devices with limited memory. In response, we propose a groundbreaking paradigm of image representation and compression by 2D Gaussian Splatting, named GaussianImage. We first introduce 2D Gaussian to represent the image, where each Gaussian has 8 parameters including position, covariance and color. Subsequently, we unveil a novel rendering algorithm based on accumulated summation. Remarkably, our method with a minimum of 3$\times$ lower GPU memory usage and 5$\times$ faster fitting time not only rivals INRs (e.g., WIRE, I-NGP) in representation performance, but also delivers a faster rendering speed of 1500-2000 FPS regardless of parameter size. Furthermore, we integrate existing vector quantization technique to build an image codec. Experimental results demonstrate that our codec attains rate-distortion performance comparable to compression-based INRs such as COIN and COIN++, while facilitating decoding speeds of approximately 2000 FPS. Additionally, preliminary proof of concept shows that our codec surpasses COIN and COIN++ in performance when using partial bits-back coding. Code is available at https://github.com/Xinjie-Q/GaussianImage., Comment: Accepted by ECCV 2024. Project Page:https://xingtongge.github.io/GaussianImage-page/ Code: https://github.com/Xinjie-Q/GaussianImage

Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the spatial-disparity characteristics inherent in stereo images, which leads to suboptimal rate-distortion results. In this paper, we propose a stereo image compression framework, named CAMSIC. CAMSIC independently transforms each image to latent representation and employs a powerful decoder-free Transformer entropy model to capture both spatial and disparity dependencies, by introducing a novel content-aware masked image modeling (MIM) technique. Our content-aware MIM facilitates efficient bidirectional interaction between prior information and estimated tokens, which naturally obviates the need for an extra Transformer decoder. Experiments show that our stereo image codec achieves state-of-the-art rate-distortion performance on two stereo image datasets Cityscapes and InStereo2K with fast encoding and decoding speed.

Few-shot learning on heterogeneous graphs (FLHG) is attracting more attention from both academia and industry because prevailing studies on heterogeneous graphs often suffer from label sparsity. FLHG aims to tackle the performance degradation in the face of limited annotated data and there have been numerous recent studies proposing various methods and applications. In this paper, we provide a comprehensive review of existing FLHG methods, covering challenges, research progress, and future prospects. Specifically, we first formalize FLHG and categorize its methods into three types: single-heterogeneity FLHG, dual-heterogeneity FLHG, and multi-heterogeneity FLHG. Then, we analyze the research progress within each category, highlighting the most recent and representative developments. Finally, we identify and discuss promising directions for future research in FLHG. To the best of our knowledge, this paper is the first systematic and comprehensive review of FLHG.

BaTiS3, a quasi-1D complex chalcogenide, has gathered considerable scientific and technological interest due to its giant optical anisotropy and electronic phase transitions. However, the synthesis of high-quality BaTiS3 crystals, particularly those featuring crystal sizes of millimeters or larger, remains a challenge. Here, we investigate the growth of BaTiS3 crystals utilizing a molten salt flux of either potassium iodide, or a mixture of barium chloride and barium iodide. The crystals obtained through this method exhibit a substantial increase in volume compared to those synthesized via the chemical vapor transport method, while preserving their intrinsic optical and electronic properties. Our flux growth method provides a promising route towards the production of high-quality, large-scale single crystals of BaTiS3, which will greatly facilitate advanced characterizations of BaTiS3 and its practical applications that require large crystal dimensions. Additionally, our approach offers an alternative synthetic route for other emerging complex chalcogenides.

Pre-trained diffusion models utilized for image generation encapsulate a substantial reservoir of a priori knowledge pertaining to intricate textures. Harnessing the potential of leveraging this a priori knowledge in the context of image super-resolution presents a compelling avenue. Nonetheless, prevailing diffusion-based methodologies presently overlook the constraints imposed by degradation information on the diffusion process. Furthermore, these methods fail to consider the spatial variability inherent in the estimated blur kernel, stemming from factors such as motion jitter and out-of-focus elements in open-environment scenarios. This oversight results in a notable deviation of the image super-resolution effect from fundamental realities. To address these concerns, we introduce a framework known as Adaptive Multi-modal Fusion of \textbf{S}patially Variant Kernel Refinement with Diffusion Model for Blind Image \textbf{S}uper-\textbf{R}esolution (SSR). Within the SSR framework, we propose a Spatially Variant Kernel Refinement (SVKR) module. SVKR estimates a Depth-Informed Kernel, which takes the depth information into account and is spatially variant. Additionally, SVKR enhance the accuracy of depth information acquired from LR images, allowing for mutual enhancement between the depth map and blur kernel estimates. Finally, we introduce the Adaptive Multi-Modal Fusion (AMF) module to align the information from three modalities: low-resolution images, depth maps, and blur kernels. This alignment can constrain the diffusion model to generate more authentic SR results.

Discovering pragmatic and efficient approaches to synthesize $\varepsilon$-approximations to quantum operators such as real (imaginary) time-evolution propagators in terms of the basic quantum operations (gates) is challenging. These invaluable $\varepsilon$-approximations enable the compilation of classical and quantum algorithms modeling, e.g., dynamical properties. In parallel, symmetries are powerful tools concisely describing the fundamental laws of nature; the symmetrical underpinnings of physical laws having consistently provided profound insights and substantially increased predictive power. In this work, we consider the interplay between $\varepsilon$-approximations processes and symmetries in a semi-coherent context--where measurements occur at each logical clock cycle. We draw inspiration from Pascual Jordan's groundbreaking formulation of non-associative, but commutative, algebraic forms. Our symmetrized formalism is applied in various domains such as quantum random walks, real-time-evolutions, variational algorithms ansatzes, and efficient entanglement verification. Our work paves the way for a deeper understanding and greater appreciation of how symmetries can be used to control quantum dynamics in the near-term., Comment: 15 pages, 3 figures, comments welcome

The performance of CLIP in dynamic facial expression recognition (DFER) task doesn't yield exceptional results as observed in other CLIP-based classification tasks. While CLIP's primary objective is to achieve alignment between images and text in the feature space, DFER poses challenges due to the abstract nature of text and the dynamic nature of video, making label representation limited and perfect alignment difficult. To address this issue, we have designed A$^{3}$lign-DFER, which introduces a new DFER labeling paradigm to comprehensively achieve alignment, thus enhancing CLIP's suitability for the DFER task. Specifically, our A$^{3}$lign-DFER method is designed with multiple modules that work together to obtain the most suitable expanded-dimensional embeddings for classification and to achieve alignment in three key aspects: affective, dynamic, and bidirectional. We replace the input label text with a learnable Multi-Dimensional Alignment Token (MAT), enabling alignment of text to facial expression video samples in both affective and dynamic dimensions. After CLIP feature extraction, we introduce the Joint Dynamic Alignment Synchronizer (JAS), further facilitating synchronization and alignment in the temporal dimension. Additionally, we implement a Bidirectional Alignment Training Paradigm (BAP) to ensure gradual and steady training of parameters for both modalities. Our insightful and concise A$^{3}$lign-DFER method achieves state-of-the-art results on multiple DFER datasets, including DFEW, FERV39k, and MAFW. Extensive ablation experiments and visualization studies demonstrate the effectiveness of A$^{3}$lign-DFER. The code will be available in the future.

Semi-supervised learning is a sound measure to relieve the strict demand of abundant annotated datasets, especially for challenging multi-organ segmentation . However, most existing SSL methods predict pixels in a single image independently, ignoring the relations among images and categories. In this paper, we propose a two-stage Dual Contrastive Learning Network for semi-supervised MoS, which utilizes global and local contrastive learning to strengthen the relations among images and classes. Concretely, in Stage 1, we develop a similarity-guided global contrastive learning to explore the implicit continuity and similarity among images and learn global context. Then, in Stage 2, we present an organ-aware local contrastive learning to further attract the class representations. To ease the computation burden, we introduce a mask center computation algorithm to compress the category representations for local contrastive learning. Experiments conducted on the public 2017 ACDC dataset and an in-house RC-OARs dataset has demonstrated the superior performance of our method., Comment: Published at ICASSP 2024

In this study, we employ the atomistic wave-packet method to directly simulate coherent phonon transport and scattering dynamics in an aperiodic superlattice structure with aperiodically arranged interfaces. Our investigation reveals that interference dynamics, contingent upon the relative magnitudes of phonon wavelength, spatial coherence length, and average interface spacing, profoundly influence transmission spectra and mode-conversion behavior. Particularly, longer-wavelength phonons possessing larger coherence lengths exhibit more pronounced destructive interference and mode-conversion, leading to generally lower transmission. The insights gained into coherent phonon wave physics from this study can significantly augment the analysis and design of phononic devices.

To satisfy the rapidly increasing demands on the large image (2K-8K) super-resolution (SR), prevailing methods follow two independent tracks: 1) accelerate existing networks by content-aware routing, and 2) design better super-resolution networks via token mixer refining. Despite directness, they encounter unavoidable defects (e.g., inflexible route or non-discriminative processing) limiting further improvements of quality-complexity trade-off. To erase the drawbacks, we integrate these schemes by proposing a content-aware mixer (CAMixer), which assigns convolution for simple contexts and additional deformable window-attention for sparse textures. Specifically, the CAMixer uses a learnable predictor to generate multiple bootstraps, including offsets for windows warping, a mask for classifying windows, and convolutional attentions for endowing convolution with the dynamic property, which modulates attention to include more useful textures self-adaptively and improves the representation capability of convolution. We further introduce a global classification loss to improve the accuracy of predictors. By simply stacking CAMixers, we obtain CAMixerSR which achieves superior performance on large-image SR, lightweight SR, and omnidirectional-image SR., Comment: Accepted by CVPR 2024

Deep learning has facilitated the automation of radiotherapy by predicting accurate dose distribution maps. However, existing methods fail to derive the desirable radiotherapy parameters that can be directly input into the treatment planning system (TPS), impeding the full automation of radiotherapy. To enable more thorough automatic radiotherapy, in this paper, we propose a novel two-stage framework to directly regress the radiotherapy parameters, including a dose map prediction stage and a radiotherapy parameters regression stage. In stage one, we combine transformer and convolutional neural network (CNN) to predict realistic dose maps with rich global and local information, providing accurate dosimetric knowledge for the subsequent parameters regression. In stage two, two elaborate modules, i.e., an intra-relation modeling (Intra-RM) module and an inter-relation modeling (Inter-RM) module, are designed to exploit the organ-specific and organ-shared features for precise parameters regression. Experimental results on a rectal cancer dataset demonstrate the effectiveness of our method., Comment: Accepted by ISBI 2024

The recently emerged molecular communication (MC) paradigm intends to leverage communication engineering tools for the design of synthetic chemical communication systems. These systems are envisioned to operate at nanoscale and in biological environments, such as the human body, and catalyze the emergence of revolutionary applications in the context of early disease monitoring and drug targeting. Despite the abundance of theoretical (and recently also experimental) MC system designs proposed over the past years, some fundamental questions remain unresolved, hindering the breakthrough of MC in real-world applications. One of these questions is: What can be a useful measure of information in the context of MC applications? While most existing works on MC build upon the concept of syntactic information as introduced by Shannon, in this paper, we explore the framework of semantic information as introduced by Kolchinsky and Wolpert for the information-theoretic analysis of a natural MC system, namely bacterial chemotaxis. Exploiting computational agent-based modeling (ABM), we are able to quantify, for the first time, the amount of information that the considered chemotactic bacterium (CB) utilizes to adapt to and survive in a dynamic environment. In other words, we show how the flow of information between the environment and the CB is related to the effectiveness of communication. Effectiveness here refers to the adaptation of the CB to the dynamic environment in order to ensure survival. Our analysis reveals that it highly depends on the environmental conditions how much information the CB can effectively utilize for improving their survival chances. Encouraged by our results, we envision that the proposed semantic information framework can open new avenues for the development of theoretical and experimental MC system designs for future nanoscale applications., Comment: 7 pages, 5 figures, This work has been submitted in part for possible publication to the IEEE Global Communications Conference (GLOBECOM) 2024

Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their representation capabilities, primarily due to inadequate alignment of intermediate features during target frame decoding. This paper introduces a universal boosting framework for current implicit video representation approaches. Specifically, we utilize a conditional decoder with a temporal-aware affine transform module, which uses the frame index as a prior condition to effectively align intermediate features with target frames. Besides, we introduce a sinusoidal NeRV-like block to generate diverse intermediate features and achieve a more balanced parameter distribution, thereby enhancing the model's capacity. With a high-frequency information-preserving reconstruction loss, our approach successfully boosts multiple baseline INRs in the reconstruction quality and convergence speed for video regression, and exhibits superior inpainting and interpolation results. Further, we integrate a consistent entropy minimization technique and develop video codecs based on these boosted INRs. Experiments on the UVG dataset confirm that our enhanced codecs significantly outperform baseline INRs and offer competitive rate-distortion performance compared to traditional and learning-based codecs. Code is available at https://github.com/Xinjie-Q/Boosting-NeRV., Comment: Accept by CVPR 2024

In autonomous driving, cooperative perception makes use of multi-view cameras from both vehicles and infrastructure, providing a global vantage point with rich semantic context of road conditions beyond a single vehicle viewpoint. Currently, two major challenges persist in vehicle-infrastructure cooperative 3D (VIC3D) object detection: $1)$ inherent pose errors when fusing multi-view images, caused by time asynchrony across cameras; $2)$ information loss in transmission process resulted from limited communication bandwidth. To address these issues, we propose a novel camera-based 3D detection framework for VIC3D task, Enhanced Multi-scale Image Feature Fusion (EMIFF). To fully exploit holistic perspectives from both vehicles and infrastructure, we propose Multi-scale Cross Attention (MCA) and Camera-aware Channel Masking (CCM) modules to enhance infrastructure and vehicle features at scale, spatial, and channel levels to correct the pose error introduced by camera asynchrony. We also introduce a Feature Compression (FC) module with channel and spatial compression blocks for transmission efficiency. Experiments show that EMIFF achieves SOTA on DAIR-V2X-C datasets, significantly outperforming previous early-fusion and late-fusion methods with comparable transmission costs., Comment: 7 pages, 8 figures. Accepted by ICRA 2024. arXiv admin note: text overlap with arXiv:arXiv:2303.10975

Well-designed prompts have demonstrated the potential to guide text-to-image models in generating amazing images. Although existing prompt engineering methods can provide high-level guidance, it is challenging for novice users to achieve the desired results by manually entering prompts due to a discrepancy between novice-user-input prompts and the model-preferred prompts. To bridge the distribution gap between user input behavior and model training datasets, we first construct a novel Coarse-Fine Granularity Prompts dataset (CFP) and propose a novel User-Friendly Fine-Grained Text Generation framework (UF-FGTG) for automated prompt optimization. For CFP, we construct a novel dataset for text-to-image tasks that combines coarse and fine-grained prompts to facilitate the development of automated prompt generation methods. For UF-FGTG, we propose a novel framework that automatically translates user-input prompts into model-preferred prompts. Specifically, we propose a prompt refiner that continually rewrites prompts to empower users to select results that align with their unique needs. Meanwhile, we integrate image-related loss functions from the text-to-image model into the training process of text generation to generate model-preferred prompts. Additionally, we propose an adaptive feature extraction module to ensure diversity in the generated results. Experiments demonstrate that our approach is capable of generating more visually appealing and diverse images than previous state-of-the-art methods, achieving an average improvement of 5% across six quality and aesthetic metrics., Comment: Accepted by The 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)

Logs are widely used in the development and maintenance of software systems. Logs can help engineers understand the runtime behavior of systems and diagnose system failures. For anomaly diagnosis, existing methods generally use log event data extracted from historical logs to build diagnostic models. However, we find that existing methods do not make full use of two types of features, (1) statistical features: some inherent statistical features in log data, such as word frequency and abnormal label distribution, are not well exploited. Compared with log raw data, statistical features are deterministic and naturally compatible with corresponding tasks. (2) semantic features: Logs contain the execution logic behind software systems, thus log statements share deep semantic relationships. How to effectively combine statistical features and semantic features in log data to improve the performance of log anomaly diagnosis is the key point of this paper. In this paper, we propose an adaptive semantic gate networks (ASGNet) that combines statistical features and semantic features to selectively use statistical features to consolidate log text semantic representation. Specifically, ASGNet encodes statistical features via a variational encoding module and fuses useful information through a well-designed adaptive semantic threshold mechanism. The threshold mechanism introduces the information flow into the classifier based on the confidence of the semantic features in the decision, which is conducive to training a robust classifier and can solve the overfitting problem caused by the use of statistical features. The experimental results on the real data set show that our method proposed is superior to all baseline methods in terms of various performance indicators.

Spinal metastasis is the most common disease in bone metastasis and may cause pain, instability and neurological injuries. Early detection of spinal metastasis is critical for accurate staging and optimal treatment. The diagnosis is usually facilitated with Computed Tomography (CT) scans, which requires considerable efforts from well-trained radiologists. In this paper, we explore a learning-based automatic bone quality classification method for spinal metastasis based on CT images. We simultaneously take the posterolateral spine involvement classification task into account, and employ multi-task learning (MTL) technique to improve the performance. MTL acts as a form of inductive bias which helps the model generalize better on each task by sharing representations between related tasks. Based on the prior knowledge that the mixed type can be viewed as both blastic and lytic, we model the task of bone quality classification as two binary classification sub-tasks, i.e., whether blastic and whether lytic, and leverage a multiple layer perceptron to combine their predictions. In order to make the model more robust and generalize better, self-paced learning is adopted to gradually involve from easy to more complex samples into the training process. The proposed learning-based method is evaluated on a proprietary spinal metastasis CT dataset. At slice level, our method significantly outperforms an 121-layer DenseNet classifier in sensitivities by $+12.54\%$, $+7.23\%$ and $+29.06\%$ for blastic, mixed and lytic lesions, respectively, meanwhile $+12.33\%$, $+23.21\%$ and $+34.25\%$ at vertebrae level.

Vertebral body (VB) segmentation is an important preliminary step towards medical visual diagnosis for spinal diseases. However, most previous works require pixel/voxel-wise strong supervisions, which is expensive, tedious and time-consuming for experts to annotate. In this paper, we propose a Weakly supervised Iterative Spinal Segmentation (WISS) method leveraging only four corner landmark weak labels on a single sagittal slice to achieve automatic volumetric segmentation from CT images for VBs. WISS first segments VBs on an annotated sagittal slice in an iterative self-training manner. This self-training method alternates between training and refining labels in the training set. Then WISS proceeds to segment the whole VBs slice by slice with a slice-propagation method to obtain volumetric segmentations. We evaluate the performance of WISS on a private spinal metastases CT dataset and the public lumbar CT dataset. On the first dataset, WISS achieves distinct improvements with regard to two different backbones. For the second dataset, WISS achieves dice coefficients of $91.7\%$ and $83.7\%$ for mid-sagittal slices and 3D CT volumes, respectively, saving a lot of labeling costs and only sacrificing a little segmentation performance., Comment: arXiv admin note: text overlap with arXiv:1412.7062 by other authors

Diffusion Inverse Solvers (DIS) are designed to sample from the conditional distribution $p_{\theta}(X_0|y)$, with a predefined diffusion model $p_{\theta}(X_0)$, an operator $f(\cdot)$, and a measurement $y=f(x'_0)$ derived from an unknown image $x'_0$. Existing DIS estimate the conditional score function by evaluating $f(\cdot)$ with an approximated posterior sample drawn from $p_{\theta}(X_0|X_t)$. However, most prior approximations rely on the posterior means, which may not lie in the support of the image distribution, thereby potentially diverge from the appearance of genuine images. Such out-of-support samples may significantly degrade the performance of the operator $f(\cdot)$, particularly when it is a neural network. In this paper, we introduces a novel approach for posterior approximation that guarantees to generate valid samples within the support of the image distribution, and also enhances the compatibility with neural network-based operators $f(\cdot)$. We first demonstrate that the solution of the Probability Flow Ordinary Differential Equation (PF-ODE) with an initial value $x_t$ yields an effective posterior sample $p_{\theta}(X_0|X_t=x_t)$. Based on this observation, we adopt the Consistency Model (CM), which is distilled from PF-ODE, for posterior sampling. Furthermore, we design a novel family of DIS using only CM. Through extensive experiments, we show that our proposed method for posterior sample approximation substantially enhance the effectiveness of DIS for neural network operators $f(\cdot)$ (e.g., in semantic segmentation). Additionally, our experiments demonstrate the effectiveness of the new CM-based inversion techniques. The source code is provided in the supplementary material.

As the modern CPU, GPU, and NPU chip design complexity and transistor counts keep increasing, and with the relentless shrinking of semiconductor technology nodes to nearly 1 nanometer, the placement and routing have gradually become the two most pivotal processes in modern very-large-scale-integrated (VLSI) circuit back-end design. How to evaluate routability efficiently and accurately in advance (at the placement and global routing stages) has grown into a crucial research area in the field of artificial intelligence (AI) assisted electronic design automation (EDA). In this paper, we propose a novel U-Net variant model boosted by an Inception embedded module to predict Routing Congestion (RC) and Design Rule Checking (DRC) hotspots. Experimental results on the recently published CircuitNet dataset benchmark show that our proposed method achieves up to 5% (RC) and 20% (DRC) rate reduction in terms of Avg-NRMSE (Average Normalized Root Mean Square Error) compared to the classic architecture. Furthermore, our approach consistently outperforms the prior model on the SSIM (Structural Similarity Index Measure) metric., Comment: The paper is submitted to the International Symposium of EDA (2024, XiAn, China)

Trust plays an essential role in an individual's decision-making. Traditional trust prediction models rely on pairwise correlations to infer potential relationships between users. However, in the real world, interactions between users are usually complicated rather than pairwise only. Hypergraphs offer a flexible approach to modeling these complex high-order correlations (not just pairwise connections), since hypergraphs can leverage hyperedeges to link more than two nodes. However, most hypergraph-based methods are generic and cannot be well applied to the trust prediction task. In this paper, we propose an Adaptive Hypergraph Network for Trust Prediction (AHNTP), a novel approach that improves trust prediction accuracy by using higher-order correlations. AHNTP utilizes Motif-based PageRank to capture high-order social influence information. In addition, it constructs hypergroups from both node-level and structure-level attributes to incorporate complex correlation information. Furthermore, AHNTP leverages adaptive hypergraph Graph Convolutional Network (GCN) layers and multilayer perceptrons (MLPs) to generate comprehensive user embeddings, facilitating trust relationship prediction. To enhance model generalization and robustness, we introduce a novel supervised contrastive learning loss for optimization. Extensive experiments demonstrate the superiority of our model over the state-of-the-art approaches in terms of trust prediction accuracy. The source code of this work can be accessed via https://github.com/Sherry-XU1995/AHNTP.

Radiotherapy is a primary treatment for cancers with the aim of applying sufficient radiation dose to the planning target volume (PTV) while minimizing dose hazards to the organs at risk (OARs). Convolutional neural networks (CNNs) have automated the radiotherapy plan-making by predicting the dose maps. However, current CNN-based methods ignore the remarkable dose difference in the dose map, i.e., high dose value in the interior PTV while low value in the exterior PTV, leading to a suboptimal prediction. In this paper, we propose a triplet-constraint transformer (TCtrans) with multi-scale refinement to predict the high-quality dose distribution. Concretely, a novel PTV-guided triplet constraint is designed to refine dose feature representations in the interior and exterior PTV by utilizing the explicit geometry of PTV. Furthermore, we introduce a multi-scale refinement (MSR) module to effectively fulfill the triplet constraint in different decoding layers with multiple scales. Besides, a transformer encoder is devised to learn the important global dosimetric knowledge. Experiments on a clinical cervical cancer dataset demonstrate the superiority of our method., Comment: accepted by 2024 IEEE ISBI

In the exciting generative AI era, the diffusion model has emerged as a very powerful and widely adopted content generation and editing tool for various data modalities, making the study of their potential security risks very necessary and critical. Very recently, some pioneering works have shown the vulnerability of the diffusion model against backdoor attacks, calling for in-depth analysis and investigation of the security challenges of this popular and fundamental AI technique. In this paper, for the first time, we systematically explore the detectability of the poisoned noise input for the backdoored diffusion models, an important performance metric yet little explored in the existing works. Starting from the perspective of a defender, we first analyze the properties of the trigger pattern in the existing diffusion backdoor attacks, discovering the important role of distribution discrepancy in Trojan detection. Based on this finding, we propose a low-cost trigger detection mechanism that can effectively identify the poisoned input noise. We then take a further step to study the same problem from the attack side, proposing a backdoor attack strategy that can learn the unnoticeable trigger to evade our proposed detection scheme. Empirical evaluations across various diffusion models and datasets demonstrate the effectiveness of the proposed trigger detection and detection-evading attack strategy. For trigger detection, our distribution discrepancy-based solution can achieve a 100\% detection rate for the Trojan triggers used in the existing works. For evading trigger detection, our proposed stealthy trigger design approach performs end-to-end learning to make the distribution of poisoned noise input approach that of benign noise, enabling nearly 100\% detection pass rate with very high attack and benign performance for the backdoored diffusion models.

The advent of large language models (LLMs) such as ChatGPT, PaLM, and GPT-4 has catalyzed remarkable advances in natural language processing, demonstrating human-like language fluency and reasoning capacities. This position paper introduces the concept of Professional Agents (PAgents), an application framework harnessing LLM capabilities to create autonomous agents with controllable, specialized, interactive, and professional-level competencies. We posit that PAgents can reshape professional services through continuously developed expertise. Our proposed PAgents framework entails a tri-layered architecture for genesis, evolution, and synergy: a base tool layer, a middle agent layer, and a top synergy layer. This paper aims to spur discourse on promising real-world applications of LLMs. We argue the increasing sophistication and integration of PAgents could lead to AI systems exhibiting professional mastery over complex domains, serving critical needs, and potentially achieving artificial general intelligence., Comment: 14 pages, 1 figure

To obtain high-quality Positron emission tomography (PET) images while minimizing radiation exposure, numerous methods have been proposed to reconstruct standard-dose PET (SPET) images from the corresponding low-dose PET (LPET) images. However, these methods heavily rely on voxel-based representations, which fall short of adequately accounting for the precise structure and fine-grained context, leading to compromised reconstruction. In this paper, we propose a 3D point-based context clusters GAN, namely PCC-GAN, to reconstruct high-quality SPET images from LPET. Specifically, inspired by the geometric representation power of points, we resort to a point-based representation to enhance the explicit expression of the image structure, thus facilitating the reconstruction with finer details. Moreover, a context clustering strategy is applied to explore the contextual relationships among points, which mitigates the ambiguities of small structures in the reconstructed images. Experiments on both clinical and phantom datasets demonstrate that our PCC-GAN outperforms the state-of-the-art reconstruction methods qualitatively and quantitatively. Code is available at https://github.com/gluucose/PCCGAN., Comment: Accepted by ICASSP 2024

This paper offers a comprehensive overview of recent technological advancements concerning the critical point of chiral phase transition, with a particular focus on Effective Field. Theories in Quantum Chromodynamics (QCD). It delves into the intricacies of these pivotal points, utilizing theoretical tools to explore associated phenomena.

This paper is devoted to the existence, uniqueness and comparison theorem on unbounded solutions of one-dimensional backward stochastic differential equations (BSDEs) with sub-quadratic generators, where the terminal time is allowed to be finite or infinite. We first establish existence of the unbounded solutions for this kind of BSDEs with generator $g$ satisfying a time-varying one-sided linear growth in the first unknown variable $y$ and a time-varying sub-quadratic growth in the second unknown variable $z$. Then, the uniqueness and comparison theorem of the unbounded solutions for this kind of BSDEs are proved under a time-varying extended convexity assumption. These results generalized those obtained in \cite{12} to the general time interval BSDEs. Finally, several sufficient conditions ensuring that the uniqueness holds are put forward and verified via some innovative ideas, which are explored at the first time even though for the case of finite time interval BSDEs., Comment: 28 pages

With the terminal value $\xi^-$ admitting a certain exponential moment and $\xi^+$ admitting every exponential moments or being bounded, we establish several existence and uniqueness results for unbounded solutions of backward stochastic differential equations (BSDEs) whose generator $g$ satisfies a monotonicity condition with general growth in the first unknown variable $y$ and a convexity condition with quadratic growth in the second unknown variable $z$. In particular, the generator $g$ may be not locally-Lipschitz continuous in $y$. This generalizes some results reported in \cite{Delbaen 2011} by relaxing the continuity and growth of $g$ in $y$. We also give an explicit expression of the first process in the unique unbounded solution of a BSDE when the generator $g$ is jointly convex in $(y,z)$ and has a linear growth in $y$ and a quadratic growth in $z$. Finally, we put forward the corresponding comparison theorems for unbounded solutions of the preceding BSDEs. These results are proved by those existing ideas and some innovative ones., Comment: 23 pages

Long-term fetal heart rate (FHR) monitoring during the antepartum period, increasingly popularized by electronic FHR monitoring, represents a growing approach in FHR monitoring. This kind of continuous monitoring, in contrast to the short-term one, collects an extended period of fetal heart data. This offers a more comprehensive understanding of fetus's conditions. However, the interpretation of long-term antenatal fetal heart monitoring is still in its early stages, lacking corresponding clinical standards. Furthermore, the substantial amount of data generated by continuous monitoring imposes a significant burden on clinical work when analyzed manually. To address above challenges, this study develops an automatic analysis system named LARA (Long-term Antepartum Risk Analysis system) for continuous FHR monitoring, combining deep learning and information fusion methods. LARA's core is a well-established convolutional neural network (CNN) model. It processes long-term FHR data as input and generates a Risk Distribution Map (RDM) and Risk Index (RI) as the analysis results. We evaluate LARA on inner test dataset, the performance metrics are as follows: AUC 0.872, accuracy 0.816, specificity 0.811, sensitivity 0.806, precision 0.271, and F1 score 0.415. In our study, we observe that long-term FHR monitoring data with higher RI is more likely to result in adverse outcomes (p=0.0021). In conclusion, this study introduces LARA, the first automated analysis system for long-term FHR monitoring, initiating the further explorations into its clinical value in the future.

Neutron star (NS) binaries can be potentially intriguing gravitational wave (GW) sources, with both high- and low-frequency radiations from the possibly aspherical individual stars and the binary orbit, respectively. The successful detection of such a dual-line source could provide fresh insights into binary geometry and NS physics. In the absence of electromagnetic observations, we develop a strategy for inferring the spin-orbit misalignment angle using the tight dual-line double NS system under the spin-orbit coupling. Based on the four-year joint detection of a typical dual-line system with LISA and Cosmic Explorer, we find that the misalignment angle and the NS moment of inertia can be measured with sub-percentage and 5% accuracy, respectively., Comment: 8 pages, 3 figures. Accepted by PRD

Due to the subjective nature of image quality assessment (IQA), assessing which image has better quality among a sequence of images is more reliable than assigning an absolute mean opinion score for an image. Thus, IQA models are evaluated by global correlation consistency (GCC) metrics like PLCC and SROCC, rather than mean opinion consistency (MOC) metrics like MAE and MSE. However, most existing methods adopt MOC metrics to define their loss functions, due to the infeasible computation of GCC metrics during training. In this work, we construct a novel loss function and network to exploit Global-correlation and Mean-opinion Consistency, forming a GMC-IQA framework. Specifically, we propose a novel GCC loss by defining a pairwise preference-based rank estimation to solve the non-differentiable problem of SROCC and introducing a queue mechanism to reserve previous data to approximate the global results of the whole data. Moreover, we propose a mean-opinion network, which integrates diverse opinion features to alleviate the randomness of weight learning and enhance the model robustness. Experiments indicate that our method outperforms SOTA methods on multiple authentic datasets with higher accuracy and generalization. We also adapt the proposed loss to various networks, which brings better performance and more stable training.

3D vision-language grounding, which focuses on aligning language with the 3D physical environment, stands as a cornerstone in the development of embodied agents. In comparison to recent advancements in the 2D domain, grounding language in 3D scenes faces several significant challenges: (i) the inherent complexity of 3D scenes due to the diverse object configurations, their rich attributes, and intricate relationships; (ii) the scarcity of paired 3D vision-language data to support grounded learning; and (iii) the absence of a unified learning framework to distill knowledge from grounded 3D data. In this work, we aim to address these three major challenges in 3D vision-language by examining the potential of systematically upscaling 3D vision-language learning in indoor environments. We introduce the first million-scale 3D vision-language dataset, SceneVerse, encompassing about 68K 3D indoor scenes and comprising 2.5M vision-language pairs derived from both human annotations and our scalable scene-graph-based generation approach. We demonstrate that this scaling allows for a unified pre-training framework, Grounded Pre-training for Scenes (GPS), for 3D vision-language learning. Through extensive experiments, we showcase the effectiveness of GPS by achieving state-of-the-art performance on all existing 3D visual grounding benchmarks. The vast potential of SceneVerse and GPS is unveiled through zero-shot transfer experiments in the challenging 3D vision-language tasks. Project website: https://scene-verse.github.io., Comment: ECCV 2024

As personalized recommendation systems become vital in the age of information overload, traditional methods relying solely on historical user interactions often fail to fully capture the multifaceted nature of human interests. To enable more human-centric modeling of user preferences, this work proposes a novel explainable recommendation framework, i.e., LLMHG, synergizing the reasoning capabilities of large language models (LLMs) and the structural advantages of hypergraph neural networks. By effectively profiling and interpreting the nuances of individual user interests, our framework pioneers enhancements to recommendation systems with increased explainability. We validate that explicitly accounting for the intricacies of human preferences allows our human-centric and explainable LLMHG approach to consistently outperform conventional models across diverse real-world datasets. The proposed plug-and-play enhancement framework delivers immediate gains in recommendation performance while offering a pathway to apply advanced LLMs for better capturing the complexity of human interests across machine learning applications., Comment: 14 pages, 5 figures

In this paper, we propose a cooperative long-term task execution (LTTE) algorithm for protecting a moving target into the interior of an ordering-flexible convex hull by a team of robots resiliently in the changing environments. Particularly, by designing target-approaching and sensing-neighbor collision-free subtasks, and incorporating these subtasks into the constraints rather than the traditional cost function in an online constraint-based optimization framework, the proposed LTTE can systematically guarantee long-term target convoying under changing environments in the n-dimensional Euclidean space. Then, the introduction of slack variables allow for the constraint violation of different subtasks; i.e., the attraction from target-approaching constraints and the repulsion from time-varying collision-avoidance constraints, which results in the desired formation with arbitrary spatial ordering sequences. Rigorous analysis is provided to guarantee asymptotical convergence with challenging nonlinear couplings induced by time-varying collision-free constraints. Finally, 2D experiments using three autonomous mobile robots (AMRs) are conducted to validate the effectiveness of the proposed algorithm, and 3D simulations tackling changing environmental elements, such as different initial positions, some robots suddenly breakdown and static obstacles are presented to demonstrate the multi-dimensional adaptability, robustness and the ability of obstacle avoidance of the proposed method.

Existing Spatial Interaction Models (SIMs) are limited in capturing the complex and context-aware interactions between business clusters and trade areas. To address the limitation, we propose a SIM-GAT model to predict spatiotemporal visitation flows between community business clusters and their trade areas. The model innovatively represents the integrated system of business clusters, trade areas, and transportation infrastructure within an urban region using a connected graph. Then, a graph-based deep learning model, i.e., Graph AttenTion network (GAT), is used to capture the complexity and interdependencies of business clusters. We developed this model with data collected from the Miami metropolitan area in Florida. We then demonstrated its effectiveness in capturing varying attractiveness of business clusters to different residential neighborhoods and across scenarios with an eXplainable AI approach. We contribute a novel method supplementing conventional SIMs to predict and analyze the dynamics of inter-connected community business clusters. The analysis results can inform data-evidenced and place-specific planning strategies helping community business clusters better accommodate their customers across scenarios, and hence improve the resilience of community businesses.

In this technical report, we present TeleChat, a collection of large language models (LLMs) with parameters of 3 billion, 7 billion and 12 billion. It includes pretrained language models as well as fine-tuned chat models that is aligned with human preferences. TeleChat is initially pretrained on an extensive corpus containing a diverse collection of texts from both English and Chinese languages, including trillions of tokens. Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe. We evaluate the performance of TeleChat on various tasks, including language understanding, mathematics, reasoning, code generation, and knowledge-based question answering. Our findings indicate that TeleChat achieves comparable performance to other open-source models of similar size across a wide range of public benchmarks. To support future research and applications utilizing LLMs, we release the fine-tuned model checkpoints of TeleChat's 7B and 12B variant, along with code and a portion of our pretraining data, to the public community., Comment: 28 pages, 2 figures

Let $n \equiv 0\, (\, \text{mod } 3\,)$ and $H_{n, n/3}^2$ be the 3-graph of order $n$, whose vertex set is partitioned into two sets $S$ and $T$ of size $\frac{1}{3}n+1$ and $\frac{2}{3}n -1$, respectively, and whose edge set consists of all triples with at least $2$ vertices in $T$. Suppose that $n$ is sufficiently large and $H$ is a 3-uniform hypergraph of order $n$ with no isolated vertex. Zhang and Lu [Discrete Math. 341 (2018), 748--758] conjectured that if $deg(u)+deg(v) > 2(\binom{n-1}{2}-\binom{2n/3}{2})$ for any two vertices $u$ and $v$ that are contained in some edge of $H$, then $H$ contains a perfect matching or $H$ is a subgraph of $H_{n,n/3}^2$. We construct a counter-example to the conjecture. Furthermore, for all $\gamma>0$ and let $n \in 3 \mathbb{Z}$ be sufficiently large, we prove that if $deg(u)+deg(v) > (3/5+\gamma)n^2$ for any two vertices $u$ and $v$ that are contained in some edge of $H$, then $H$ contains a perfect matching or $H$ is a subgraph of $H_{n,n/3}^2$. This implies a result of Zhang, Zhao and Lu [Electron. J. Combin. 25 (3), 2018]., Comment: arXiv admin note: text overlap with arXiv:1901.07674

Heterogeneous graph few-shot learning (HGFL) has been developed to address the label sparsity issue in heterogeneous graphs (HGs), which consist of various types of nodes and edges. The core concept of HGFL is to extract knowledge from rich-labeled classes in a source HG, transfer this knowledge to a target HG to facilitate learning new classes with few-labeled training data, and finally make predictions on unlabeled testing data. Existing methods typically assume that the source HG, training data, and testing data all share the same distribution. However, in practice, distribution shifts among these three types of data are inevitable due to two reasons: (1) the limited availability of the source HG that matches the target HG distribution, and (2) the unpredictable data generation mechanism of the target HG. Such distribution shifts result in ineffective knowledge transfer and poor learning performance in existing methods, thereby leading to a novel problem of out-of-distribution (OOD) generalization in HGFL. To address this challenging problem, we propose a novel Causal OOD Heterogeneous graph Few-shot learning model, namely COHF. In COHF, we first characterize distribution shifts in HGs with a structural causal model, establishing an invariance principle for OOD generalization in HGFL. Then, following this invariance principle, we propose a new variational autoencoder-based heterogeneous graph neural network to mitigate the impact of distribution shifts. Finally, by integrating this network with a novel meta-learning framework, COHF effectively transfers knowledge to the target HG to predict new classes with few-labeled data. Extensive experiments on seven real-world datasets have demonstrated the superior performance of COHF over the state-of-the-art methods.

Sampling from Boltzmann distributions, particularly those tied to high-dimensional and complex energy functions, poses a significant challenge in many fields. In this work, we present the Energy-Based Diffusion Generator (EDG), a novel approach that integrates ideas from variational autoencoders and diffusion models. EDG leverages a decoder to transform latent variables from a simple distribution into samples approximating the target Boltzmann distribution, while the diffusion-based encoder provides an accurate estimate of the Kullback-Leibler divergence during training. Notably, EDG is simulation-free, eliminating the need to solve ordinary or stochastic differential equations during training. Furthermore, by removing constraints such as bijectivity in the decoder, EDG allows for flexible network design. Through empirical evaluation, we demonstrate the superior performance of EDG across a variety of complex distribution tasks, outperforming existing methods.

A network can contain numerous spanning trees. If two spanning trees $T_i,T_j$ do not share any common edges, $T_i$ and $T_j$ are said to be pairwisely edge-disjoint. For spanning trees $T_1, T_2, ..., T_m$, if every two of them are pairwisely edge-disjoint, they are called completely edge-independent spanning trees (CEISTs for short). CEISTs can facilitate many network functionalities, and constructing CEISTs as maximally allowed as possible in a given network is a worthy undertaking. In this paper, we establish the maximal number of CEISTs in the locally twisted cube network, and propose an algorithm to construct $\lfloor \frac{n}{2} \rfloor$ CEISTs in $LTQ_n$, the $n$-dimensional locally twisted cube. The proposed algorithm has been actually implemented, and we present the outputs. Network broadcasting in the $LTQ_n$ was simulated using $\lfloor\frac{n}{2}\rfloor$ CEISTs, and the performance compared with broadcasting using a single tree.