Search

Deep Neural Networks (DNNs) are well-known to act as over-parameterized deep image priors (DIP) that regularize various image inverse problems. Meanwhile, researchers also proposed extremely compact, under-parameterized image priors (e.g., deep decoder) that are strikingly competent for image restoration too, despite a loss of accuracy. These two extremes push us to think whether there exists a better solution in the middle: between over- and under-parameterized image priors, can one identify "intermediate" parameterized image priors that achieve better trade-offs between performance, efficiency, and even preserving strong transferability? Drawing inspirations from the lottery ticket hypothesis (LTH), we conjecture and study a novel "lottery image prior" (LIP) by exploiting DNN inherent sparsity, stated as: given an over-parameterized DNN-based image prior, it will contain a sparse subnetwork that can be trained in isolation, to match the original DNN's performance when being applied as a prior to various image inverse problems. Our results validate the superiority of LIPs: we can successfully locate the LIP subnetworks from over-parameterized DIPs at substantial sparsity ranges. Those LIP subnetworks significantly outperform deep decoders under comparably compact model sizes (by often fully preserving the effectiveness of their over-parameterized counterparts), and they also possess high transferability across different images as well as restoration task types. Besides, we also extend LIP to compressive sensing image reconstruction, where a pre-trained GAN generator is used as the prior (in contrast to untrained DIP or deep decoder), and confirm its validity in this setting too. To our best knowledge, this is the first time that LTH is demonstrated to be relevant in the context of inverse problems or image priors., Comment: Codes are available at https://github.com/VITA-Group/Chasing-Better-DIPs

GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's trained end-to-end across text, vision, and audio, meaning all inputs and outputs are processed by the same neural network. GPT-4o can respond to audio inputs in as little as 232 milliseconds, with an average of 320 milliseconds, which is similar to human response time in conversation. It matches GPT-4 Turbo performance on text in English and code, with significant improvement on text in non-English languages, while also being much faster and 50\% cheaper in the API. GPT-4o is especially better at vision and audio understanding compared to existing models. In line with our commitment to building AI safely and consistent with our voluntary commitments to the White House, we are sharing the GPT-4o System Card, which includes our Preparedness Framework evaluations. In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure the model is safe and aligned. We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.

Mental health issues significantly impact individuals' daily lives, yet many do not receive the help they need even with available online resources. This study aims to provide diverse, accessible, stigma-free, personalized, and real-time mental health support through cutting-edge AI technologies. It makes the following contributions: (1) Conducting an extensive survey of recent mental health support methods to identify prevalent functionalities and unmet needs. (2) Introducing SouLLMate, an adaptive LLM-driven system that integrates LLM technologies, Chain, Retrieval-Augmented Generation (RAG), prompt engineering, and domain knowledge. This system offers advanced features such as Risk Detection and Proactive Guidance Dialogue, and utilizes RAG for personalized profile uploads and Conversational Information Extraction. (3) Developing novel evaluation approaches for preliminary assessments and risk detection via professionally annotated interview data and real-life suicide tendency data. (4) Proposing the Key Indicator Summarization (KIS), Proactive Questioning Strategy (PQS), and Stacked Multi-Model Reasoning (SMMR) methods to enhance model performance and usability through context-sensitive response adjustments, semantic coherence evaluations, and enhanced accuracy of long-context reasoning in language models. This study contributes to advancing mental health support technologies, potentially improving the accessibility and effectiveness of mental health care globally., Comment: 26 pages, 19 figures, 8 tables

Medical image segmentation poses challenges due to domain gaps, data modality variations, and dependency on domain knowledge or experts, especially for low- and middle-income countries (LMICs). Whereas for humans, given a few exemplars (with corresponding labels), we are able to segment different medical images even without exten-sive domain-specific clinical training. In addition, current SAM-based medical segmentation models use fine-grained visual prompts, such as the bounding rectangle generated from manually annotated target segmentation mask, as the bounding box (bbox) prompt during the testing phase. However, in actual clinical scenarios, no such precise prior knowledge is available. Our experimental results also reveal that previous models nearly fail to predict when given coarser bbox prompts. Considering these issues, in this paper, we introduce a domain-aware selective adaptation approach to adapt the general knowledge learned from a large model trained with natural images to the corresponding medical domains/modalities, with access to only a few (e.g. less than 5) exemplars. Our method mitigates the aforementioned limitations, providing an efficient and LMICs-friendly solution. Extensive experimental analysis showcases the effectiveness of our approach, offering potential advancements in healthcare diagnostics and clinical applications in LMICs., Comment: Accepcted in ACCV 2024

Recent deep-learning-based approaches to single-image reflection removal have shown promising advances, primarily for two reasons: 1) the utilization of recognition-pretrained features as inputs, and 2) the design of dual-stream interaction networks. However, according to the Information Bottleneck principle, high-level semantic clues tend to be compressed or discarded during layer-by-layer propagation. Additionally, interactions in dual-stream networks follow a fixed pattern across different layers, limiting overall performance. To address these limitations, we propose a novel architecture called Reversible Decoupling Network (RDNet), which employs a reversible encoder to secure valuable information while flexibly decoupling transmission- and reflection-relevant features during the forward pass. Furthermore, we customize a transmission-rate-aware prompt generator to dynamically calibrate features, further boosting performance. Extensive experiments demonstrate the superiority of RDNet over existing SOTA methods on five widely-adopted benchmark datasets. Our code will be made publicly available.

The Korteweg-de Vries (KdV) equation is a fundamental partial differential equation that models wave propagation in shallow water and other dispersive media. Accurately solving the KdV equation is essential for understanding wave dynamics in physics and engineering applications. This project focuses on implementing the Crank-Nicolson scheme, a finite difference method known for its stability and accuracy, to solve the KdV equation. The Crank-Nicolson scheme's implicit nature allows for a more stable numerical solution, especially in handling the dispersive and nonlinear terms of the KdV equation. We investigate the performance of the scheme through various test cases, analyzing its convergence and error behavior. The results demonstrate that the Crank-Nicolson method provides a robust approach for solving the KdV equation, with improved accuracy over traditional explicit methods. Code is available at the end of the paper.

Objective: Mitigating algorithmic disparities is a critical challenge in healthcare research, where ensuring equity and fairness is paramount. While large-scale healthcare data exist across multiple institutions, cross-institutional collaborations often face privacy constraints, highlighting the need for privacy-preserving solutions that also promote fairness. Materials and Methods: In this study, we present Fair Federated Machine Learning (FairFML), a model-agnostic solution designed to reduce algorithmic bias in cross-institutional healthcare collaborations while preserving patient privacy. As a proof of concept, we validated FairFML using a real-world clinical case study focused on reducing gender disparities in cardiac arrest outcome prediction. Results: We demonstrate that the proposed FairFML framework enhances fairness in federated learning (FL) models without compromising predictive performance. Our findings show that FairFML improves model fairness by up to 65% compared to the centralized model, while maintaining performance comparable to both local and centralized models, as measured by receiver operating characteristic analysis. Discussion and Conclusion: FairFML offers a promising and flexible solution for FL collaborations, with its adaptability allowing seamless integration with various FL frameworks and models, from traditional statistical methods to deep learning techniques. This makes FairFML a robust approach for developing fairer FL models across diverse clinical and biomedical applications.

Mental health issues significantly impact individuals' daily lives, yet many do not receive the help they need even with available online resources. This study aims to provide accessible, stigma-free, personalized, and real-time mental health support through cutting-edge AI technologies. It makes the following contributions: (1) Conducting an extensive survey of recent mental health support methods to identify prevalent functionalities and unmet needs. (2) Introducing SouLLMate, an adaptive LLM-driven system that integrates LLM technologies, Chain, Retrieval-Augmented Generation (RAG), prompt engineering, and domain knowledge. This system offers advanced features such as Suicide Risk Detection and Proactive Guidance Dialogue, and utilizes RAG for personalized profile uploads and Conversational Information Extraction. (3) Developing novel evaluation approaches to assess preliminary assessments and suicide risk detection, utilizing annotated real-life interview data and professionally labeled datasets indicating suicide tendencies. (4) Proposing Key Indicator Summarization (KIS) and Proactive Questioning Strategy (PQS) methods to enhance model performance and usability through context-sensitive response adjustments and semantic coherence evaluations. This study contributes to advancing mental health support technologies, potentially improving the accessibility and effectiveness of mental health care globally.

Crowd Counting is a fundamental topic, aiming to estimate the number of individuals in the crowded images or videos fed from surveillance cameras. Recent works focus on improving counting accuracy, while ignoring the certified robustness of counting models. In this paper, we propose a novel Bound Tightening Network (BTN) for Robust Crowd Counting. It consists of three parts: base model, smooth regularization module and certify bound module. The core idea is to propagate the interval bound through the base model (certify bound module) and utilize the layer weights (smooth regularization module) to guide the network learning. Experiments on different benchmark datasets for counting demonstrate the effectiveness and efficiency of BTN., Comment: This work was done 2 years ago

We investigate microwave interference from a spin ensemble and its mirror image in a one-dimensional waveguide. Away from the mirror, the resonance frequencies of the Kittel mode (KM) inside a ferrimagnetic spin ensemble have sinusoidal shifts as the normalized distance between the spin ensemble and the mirror increases compared to the setup without the mirror. These shifts are a consequence of the KM's interaction with its own image. Furthermore, the variation of the magnon radiative decay into the waveguide shows a cosine squared oscillation and is enhanced twofold when the KM sits at the magnetic antinode of the corresponding eigenmode. We can finely tune the KM to achieve the maximum adsorption of the input photons at the critical coupling point. Moreover, by placing the KM in proximity to the node of the resonance field, its lifetime is extended to more than eight times compared to its positioning near the antinode.

Intelligent Transportation Systems (ITS) are vital in modern traffic management and optimization, significantly enhancing traffic efficiency and safety. Recently, diffusion models have emerged as transformative tools for addressing complex challenges within ITS. In this paper, we present a comprehensive survey of diffusion models for ITS, covering both theoretical and practical aspects. First, we introduce the theoretical foundations of diffusion models and their key variants, including conditional diffusion models and latent diffusion models, highlighting their suitability for modeling complex, multi-modal traffic data and enabling controllable generation. Second, we outline the primary challenges in ITS and the corresponding advantages of diffusion models, providing readers with a deeper understanding of the intersection between ITS and diffusion models. Third, we offer a multi-perspective investigation of current applications of diffusion models in ITS domains, including autonomous driving, traffic simulation, trajectory prediction, and traffic safety. Finally, we discuss state-of-the-art diffusion model techniques and highlight key ITS research directions that warrant further investigation. Through this structured overview, we aim to provide researchers with a comprehensive understanding of diffusion models for ITS, thereby advancing their future applications in the transportation domain., Comment: 7 figures

Recent advancements in deep learning have greatly advanced the field of infrared small object detection (IRSTD). Despite their remarkable success, a notable gap persists between these IRSTD methods and generic segmentation approaches in natural image domains. This gap primarily arises from the significant modality differences and the limited availability of infrared data. In this study, we aim to bridge this divergence by investigating the adaptation of generic segmentation models, such as the Segment Anything Model (SAM), to IRSTD tasks. Our investigation reveals that many generic segmentation models can achieve comparable performance to state-of-the-art IRSTD methods. However, their full potential in IRSTD remains untapped. To address this, we propose a simple, lightweight, yet effective baseline model for segmenting small infrared objects. Through appropriate distillation strategies, we empower smaller student models to outperform state-of-the-art methods, even surpassing fine-tuned teacher results. Furthermore, we enhance the model's performance by introducing a novel query design comprising dense and sparse queries to effectively encode multi-scale features. Through extensive experimentation across four popular IRSTD datasets, our model demonstrates significantly improved performance in both accuracy and throughput compared to existing approaches, surpassing SAM and Semantic-SAM by over 14 IoU on NUDT and 4 IoU on IRSTD1k. The source code and models will be released at https://github.com/O937-blip/SimIR., Comment: ACM MM'24

In fine-tuning large language models (LLMs), conserving computational resources while maintaining effectiveness and improving outcomes within the same computational constraints is crucial. The Low-Rank Adaptation (LoRA) strategy balances efficiency and performance in fine-tuning large models by reducing the number of trainable parameters and computational costs. However, current advancements in LoRA might be focused on its fine-tuning methodologies, with not as much exploration as might be expected into further compression of LoRA. Since most of LoRA's parameters might still be superfluous, this may lead to unnecessary wastage of computational resources. In this paper, we propose \textbf{CoRA}: leveraging shared knowledge to optimize LoRA training by substituting its matrix $B$ with a common subspace from large models. Our two-fold method includes (1) Freezing the substitute matrix $B$ to halve parameters while training matrix $A$ for specific tasks and (2) Using the substitute matrix $B$ as an enhanced initial state for the original matrix $B$, achieving improved results with the same parameters. Our experiments show that the first approach achieves the same efficacy as the original LoRA fine-tuning while being more efficient than halving parameters. At the same time, the second approach has some improvements compared to LoRA's original fine-tuning performance. They generally attest to the effectiveness of our work.

With the continuous development of deep learning, the field of repetitive action counting is gradually gaining notice from many researchers. Extraction of pose keypoints using human pose estimation networks is proven to be an effective pose-level method. However, existing pose-level methods suffer from the shortcomings that the single coordinate is not stable enough to handle action distortions due to changes in camera viewpoints, thus failing to accurately identify salient poses, and is vulnerable to misdetection during the transition from the exception to the actual action. To overcome these problems, we propose a simple but efficient Global Multi-geometric Feature Learning Network (GMFL-Net). Specifically, we design a MIA-Module that aims to improve information representation by fusing multi-geometric features, and learning the semantic similarity among the input multi-geometric features. Then, to improve the feature representation from a global perspective, we also design a GBFL-Module that enhances the inter-dependencies between point-wise and channel-wise elements and combines them with the rich local information generated by the MIA-Module to synthesise a comprehensive and most representative global feature representation. In addition, considering the insufficient existing dataset, we collect a new dataset called Countix-Fitness-pose (https://github.com/Wantong66/Countix-Fitness) which contains different cycle lengths and exceptions, a test set with longer duration, and annotate it with fine-grained annotations at the pose-level. We also add two new action classes, namely lunge and rope push-down. Finally, extensive experiments on the challenging RepCount-pose, UCFRep-pose, and Countix-Fitness-pose benchmarks show that our proposed GMFL-Net achieves state-of-the-art performance.

Reinforcement Learning from Human Feedback (RLHF) has proven effective in aligning large language models with human intentions, yet it often relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and present challenges in sample efficiency and stability. In this paper, we introduce Inverse-Q*, an innovative framework that transcends traditional RL methods by optimizing token-level reinforcement learning without the need for additional reward or value models. Inverse-Q* leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model's responses, facilitating more granular and flexible policy shaping. Our approach reduces reliance on human annotation and external supervision, making it especially suitable for low-resource settings. We present extensive experimental results demonstrating that Inverse-Q* not only matches but potentially exceeds the effectiveness of PPO in terms of convergence speed and the alignment of model responses with human preferences. Our findings suggest that Inverse-Q* offers a practical and robust alternative to conventional RLHF approaches, paving the way for more efficient and adaptable model training approaches.

Code benchmarks such as HumanEval are widely adopted to evaluate the capabilities of Large Language Models (LLMs), providing insights into their strengths and weaknesses. However, current benchmarks primarily exercise LLMs' capability on common coding tasks (e.g., bubble sort, greatest common divisor), leaving domain-specific coding tasks (e.g., computation, system, cryptography) unexplored. To fill this gap, we propose a multi-domain code benchmark, DOMAINEVAL, designed to evaluate LLMs' coding capabilities thoroughly. Our pipeline works in a fully automated manner, enabling a push-bottom construction from code repositories into formatted subjects under study. Interesting findings are observed by evaluating 12 representative LLMs against DOMAINEVAL. We notice that LLMs are generally good at computation tasks while falling short on cryptography and system coding tasks. The performance gap can be as much as 68.94% (80.94% - 12.0%) in some LLMs. We also observe that generating more samples can increase the overall performance of LLMs, while the domain bias may even increase. The contributions of this study include a code generation benchmark dataset DOMAINEVAL, encompassing six popular domains, a fully automated pipeline for constructing code benchmarks, and an identification of the limitations of LLMs in code generation tasks based on their performance on DOMAINEVAL, providing directions for future research improvements. The leaderboard is available at https://domaineval.github.io/.

In recent years, although U-Net network has made significant progress in the field of image segmentation, it still faces performance bottlenecks in remote sensing image segmentation. In this paper, we innovatively propose to introduce SimAM and CBAM attention mechanism in U-Net, and the experimental results show that after adding SimAM and CBAM modules alone, the model improves 17.41% and 12.23% in MIoU, and the Mpa and Accuracy are also significantly improved. And after fusing the two,the model performance jumps up to 19.11% in MIoU, and the Mpa and Accuracy are also improved by 16.38% and 14.8% respectively, showing excellent segmentation accuracy and visual effect with strong generalization ability and robustness. This study opens up a new path for remote sensing image segmentation technology and has important reference value for algorithm selection and improvement.

Reading comprehension models answer questions posed in natural language when provided with a short passage of text. They present an opportunity to address a long-standing challenge in data management: the extraction of structured data from unstructured text. Consequently, several approaches are using these models to perform information extraction. However, these modern approaches leave an opportunity behind because they do not exploit the relational structure of the target extraction table. In this paper, we introduce a new model, Relation Coherence, that exploits knowledge of the relational structure to improve the extraction quality. We incorporate the Relation Coherence model as part of FabricQA-Extractor, an end-to-end system we built from scratch to conduct large scale extraction tasks over millions of documents. We demonstrate on two datasets with millions of passages that Relation Coherence boosts extraction performance and evaluate FabricQA-Extractor on large scale datasets.

LiDAR-based outdoor 3D object detection has received widespread attention. However, training 3D detectors from the LiDAR point cloud typically relies on expensive bounding box annotations. This paper presents OC3D, an innovative weakly supervised method requiring only coarse clicks on the bird's eye view of the 3D point cloud. A key challenge here is the absence of complete geometric descriptions of the target objects from such simple click annotations. To address this problem, our proposed OC3D adopts a two-stage strategy. In the first stage, we initially design a novel dynamic and static classification strategy and then propose the Click2Box and Click2Mask modules to generate box-level and mask-level pseudo-labels for static and dynamic instances, respectively. In the second stage, we design a Mask2Box module, leveraging the learning capabilities of neural networks to update mask-level pseudo-labels, which contain less information, to box-level pseudo-labels. Experimental results on the widely used KITTI and nuScenes datasets demonstrate that our OC3D with only coarse clicks achieves state-of-the-art performance compared to weakly-supervised 3D detection methods. Combining OC3D with a missing click mining strategy, we propose an OC3D++ pipeline, which requires only 0.2% annotation cost in the KITTI dataset to achieve performance comparable to fully supervised methods. The code will be made publicly available.

We propose progressive radiance distillation, an inverse rendering method that combines physically-based rendering with Gaussian-based radiance field rendering using a distillation progress map. Taking multi-view images as input, our method starts from a pre-trained radiance field guidance, and distills physically-based light and material parameters from the radiance field using an image-fitting process. The distillation progress map is initialized to a small value, which favors radiance field rendering. During early iterations when fitted light and material parameters are far from convergence, the radiance field fallback ensures the sanity of image loss gradients and avoids local minima that attracts under-fit states. As fitted parameters converge, the physical model gradually takes over and the distillation progress increases correspondingly. In presence of light paths unmodeled by the physical model, the distillation progress never finishes on affected pixels and the learned radiance field stays in the final rendering. With this designed tolerance for physical model limitations, we prevent unmodeled color components from leaking into light and material parameters, alleviating relighting artifacts. Meanwhile, the remaining radiance field compensates for the limitations of the physical model, guaranteeing high-quality novel views synthesis. Experimental results demonstrate that our method significantly outperforms state-of-the-art techniques quality-wise in both novel view synthesis and relighting. The idea of progressive radiance distillation is not limited to Gaussian splatting. We show that it also has positive effects for prominently specular scenes when adapted to a mesh-based inverse rendering method.

LiDAR-based vision systems are integral for 3D object detection, which is crucial for autonomous navigation. However, they suffer from performance degradation in adverse weather conditions due to the quality deterioration of LiDAR point clouds. Fusing LiDAR with the weather-robust 4D radar sensor is expected to solve this problem. However, the fusion of LiDAR and 4D radar is challenging because they differ significantly in terms of data quality and the degree of degradation in adverse weather. To address these issues, we introduce L4DR, a weather-robust 3D object detection method that effectively achieves LiDAR and 4D Radar fusion. Our L4DR includes Multi-Modal Encoding (MME) and Foreground-Aware Denoising (FAD) technique to reconcile sensor gaps, which is the first exploration of the complementarity of early fusion between LiDAR and 4D radar. Additionally, we design an Inter-Modal and Intra-Modal ({IM}2 ) parallel feature extraction backbone coupled with a Multi-Scale Gated Fusion (MSGF) module to counteract the varying degrees of sensor degradation under adverse weather conditions. Experimental evaluation on a VoD dataset with simulated fog proves that L4DR is more adaptable to changing weather conditions. It delivers a significant performance increase under different fog levels, improving the 3D mAP by up to 20.0% over the traditional LiDAR-only approach. Moreover, the results on the K-Radar dataset validate the consistent performance improvement of L4DR in real-world adverse weather conditions.

In the 1970s, Wiesner introduced the concept of quantum money, where quantum states generated according to specific rules function as currency. These states circulate among users with quantum resources through quantum channels or face-to-face interactions. Quantum mechanics grants quantum money physical-level unforgeability but also makes minting, storing, and circulating it significantly challenging. Currently, quantum computers capable of minting and preserving quantum money have not yet emerged, and existing quantum channels are not stable enough to support the efficient transmission of quantum states for quantum money, limiting its practicality. Semi-quantum money schemes support fully classical transactions and complete classical banks, reducing dependence on quantum resources and enhancing feasibility. To further minimize the system's reliance on quantum resources, we propose a cloud-based semi-quantum money (CSQM) scheme. This scheme relies only on semi-honest third-party quantum clouds, while the rest of the system remains entirely classical. We also discuss estimating the computational power required by the quantum cloud for the scheme and conduct a security analysis.

Large language models (LLMs) such as ChatGPT and GPT-4 have demonstrated impressive capabilities in various generative tasks. However, their performance is often hampered by limitations in accessing and leveraging long-term memory, leading to specific vulnerabilities and biases, especially during long interactions. This paper introduces ChatLogic, an innovative framework specifically targeted at LLM reasoning tasks that can enhance the performance of LLMs in multi-step deductive reasoning tasks by integrating logic programming. In ChatLogic, the language model plays a central role, acting as a controller and participating in every system operation stage. We propose a novel method of converting logic problems into symbolic integration with an inference engine. This approach leverages large language models' situational understanding and imitation skills and uses symbolic memory to enhance multi-step deductive reasoning capabilities. Our results show that the ChatLogic framework significantly improves the multi-step reasoning capabilities of LLMs. The source code and data are available at \url{https://github.com/Strong-AI-Lab/ChatLogic}, Comment: 8 pages, 3 figures. This paper has been accepted by WCCI IJCNN 2024

We introduce the first version of GPU4PySCF, a module that provides GPU acceleration of methods in PySCF. As a core functionality, this provides a GPU implementation of two-electron repulsion integrals (ERIs) for contracted basis sets comprising up to g functions using Rys quadrature. As an illustration of how this can accelerate a quantum chemistry workflow, we describe how to use the ERIs efficiently in the integral-direct Hartree-Fock Fock build and nuclear gradient construction. Benchmark calculations show a significant speedup of two orders of magnitude with respect to the multi-threaded CPU Hartree-Fock code of PySCF, and performance comparable to other GPU-accelerated quantum chemical packages including GAMESS and QUICK on a single NVIDIA A100 GPU.

Optical tweezer arrays of laser-cooled and individual controlled particles have revolutionized the atomic, molecular and optical physics, and they afford exquisite capabilities for applications in quantum simulation of many-body physics, quantum computation and quantum sensing. Underlying this development is the technical maturity of generating scalable optical beams, enabled by active components and high numerical aperture objective. However, such a complex combination of bulk optics outside the vacuum chamber is very sensitive to any vibration and drift. Here we demonstrate the generation of 3*3 static tweezer array with a single chip-scale multifunctional metasurface element in vacuum, replacing the meter-long free space optics. Fluorescence counts on the camera validates the successfully trapping of the atomic ensemble array. Further, we discuss the strategy to achieve low scattering and crosstalk, where a metasurface design featuring dual-wavelength independent control is included. Our results, together with other recent development in integrated photonics for cold atoms, could pave the way for compact and portable quantum sensors and simulators in platforms of neutral atom arrays.

Clinical and biomedical research in low-resource settings often faces significant challenges due to the need for high-quality data with sufficient sample sizes to construct effective models. These constraints hinder robust model training and prompt researchers to seek methods for leveraging existing knowledge from related studies to support new research efforts. Transfer learning (TL), a machine learning technique, emerges as a powerful solution by utilizing knowledge from pre-trained models to enhance the performance of new models, offering promise across various healthcare domains. Despite its conceptual origins in the 1990s, the application of TL in medical research has remained limited, especially beyond image analysis. In our review of TL applications in structured clinical and biomedical data, we screened 3,515 papers, with 55 meeting the inclusion criteria. Among these, only 2% (one out of 55) utilized external studies, and 7% (four out of 55) addressed scenarios involving multi-site collaborations with privacy constraints. To achieve actionable TL with structured medical data while addressing regional disparities, inequality, and privacy constraints in healthcare research, we advocate for the careful identification of appropriate source data and models, the selection of suitable TL frameworks, and the validation of TL models with proper baselines.

Frequency conversion is a widely realized physical process in nonlinear systems of optics and electronics. As an emerging nonlinear platform, spintronic devices have the potential to achieve stronger frequency conversion. Here, we demonstrated a microwave frequency conversion method in a hybrid quantum system, integrating nitrogen-vacancy centers in diamond with magnetic thin film CoFeB. We achieve a conversion bandwidth ranging from 0.1 to 12GHz, presenting an up to $\mathrm{25^{th}}$ order frequency conversion and further display the application of this method for frequency detection and qubits coherent control. Distinct from traditional frequency conversion techniques based on nonlinear electric response, our approach employs nonlinear magnetic response in spintronic devices. The nonlinearity, originating from the symmetry breaking such as domain walls in magnetic films, presents that our method can be adapted to hybrid systems of other spintronic devices and spin qubits, expanding the application scope of spintronic devices and providing a promising on-chip platform for coupling quantum systems., Comment: 11 pages, 5 figures

Though advanced in understanding visual information with human languages, Large Vision-Language Models (LVLMs) still suffer from multimodal hallucinations. A natural concern is that during multimodal interaction, the generated hallucinations could influence the LVLMs' subsequent generation. Thus, we raise a question: When presented with a query relevant to the previously generated hallucination, will LVLMs be misled and respond incorrectly, even though the ground visual information exists? To answer this, we propose a framework called MMHalSnowball to evaluate LVLMs' behaviors when encountering generated hallucinations, where LVLMs are required to answer specific visual questions within a curated hallucinatory conversation. Crucially, our experiment shows that the performance of open-source LVLMs drops by at least $31\%$, indicating that LVLMs are prone to accept the generated hallucinations and make false claims that they would not have supported without distractions. We term this phenomenon Multimodal Hallucination Snowballing. To mitigate this, we further propose a training-free method called Residual Visual Decoding, where we revise the output distribution of LVLMs with the one derived from the residual visual input, providing models with direct access to the visual information. Experiments show that our method can mitigate more than $24\%$ of the snowballed multimodal hallucination while maintaining capabilities., Comment: Accepted to ACL 2024 Main Conference. 21 pages, 20 figures

Large language models (LLMs) have achieved remarkable success in natural language processing (NLP), demonstrating significant capabilities in processing and understanding text data. However, recent studies have identified limitations in LLMs' ability to reason about graph-structured data. To address this gap, we introduce GraphEval2000, the first comprehensive graph dataset, comprising 40 graph data structure problems along with 2000 test cases. Additionally, we introduce an evaluation framework based on GraphEval2000, designed to assess the graph reasoning abilities of LLMs through coding challenges. Our dataset categorizes test cases into four primary and four sub-categories, ensuring a comprehensive evaluation. We evaluate eight popular LLMs on GraphEval2000, revealing that LLMs exhibit a better understanding of directed graphs compared to undirected ones. While private LLMs consistently outperform open-source models, the performance gap is narrowing. Furthermore, to improve the usability of our evaluation framework, we propose Structured Symbolic Decomposition (SSD), an instruction-based method designed to enhance LLM performance on GraphEval2000. Results show that SSD improves the performance of GPT-3.5, GPT-4, and GPT-4o on complex graph problems, with an increase of 11.11\%, 33.37\%, and 33.37\%, respectively., Comment: Submitted to NeurIPs 2024 Dataset and Benchmark track, under review

Online Large Language Model (LLM) services such as ChatGPT and Claude 3 have transformed business operations and academic research by effortlessly enabling new opportunities. However, due to data-sharing restrictions, sectors such as healthcare and finance prefer to deploy local LLM applications using costly hardware resources. This scenario requires a balance between the effectiveness advantages of LLMs and significant financial burdens. Additionally, the rapid evolution of models increases the frequency and redundancy of benchmarking efforts. Existing benchmarking toolkits, which typically focus on effectiveness, often overlook economic considerations, making their findings less applicable to practical scenarios. To address these challenges, we introduce CEBench, an open-source toolkit specifically designed for multi-objective benchmarking that focuses on the critical trade-offs between expenditure and effectiveness required for LLM deployments. CEBench allows for easy modifications through configuration files, enabling stakeholders to effectively assess and optimize these trade-offs. This strategic capability supports crucial decision-making processes aimed at maximizing effectiveness while minimizing cost impacts. By streamlining the evaluation process and emphasizing cost-effectiveness, CEBench seeks to facilitate the development of economically viable AI solutions across various industries and research fields. The code and demonstration are available in \url{https://github.com/amademicnoboday12/CEBench}.

LiDAR-based sparse 3D object detection plays a crucial role in autonomous driving applications due to its computational efficiency advantages. Existing methods either use the features of a single central voxel as an object proxy, or treat an aggregated cluster of foreground points as an object proxy. However, the former lacks the ability to aggregate contextual information, resulting in insufficient information expression in object proxies. The latter relies on multi-stage pipelines and auxiliary tasks, which reduce the inference speed. To maintain the efficiency of the sparse framework while fully aggregating contextual information, in this work, we propose SparseDet which designs sparse queries as object proxies. It introduces two key modules, the Local Multi-scale Feature Aggregation (LMFA) module and the Global Feature Aggregation (GFA) module, aiming to fully capture the contextual information, thereby enhancing the ability of the proxies to represent objects. Where LMFA sub-module achieves feature fusion across different scales for sparse key voxels %which does this through via coordinate transformations and using nearest neighbor relationships to capture object-level details and local contextual information, GFA sub-module uses self-attention mechanisms to selectively aggregate the features of the key voxels across the entire scene for capturing scene-level contextual information. Experiments on nuScenes and KITTI demonstrate the effectiveness of our method. Specifically, on nuScene, SparseDet surpasses the previous best sparse detector VoxelNeXt by 2.2\% mAP with 13.5 FPS, and on KITTI, it surpasses VoxelNeXt by 1.12\% $\mathbf{AP_{3D}}$ on hard level tasks with 17.9 FPS., Comment: arXiv admin note: text overlap with arXiv:2401.02702

Combinatorial optimization problems are pivotal across many fields. Among these, Quadratic Unconstrained Binary Optimization (QUBO) problems, central to fields like portfolio optimization, network design, and computational biology, are NP-hard and require exponential computational resources. To address these challenges, we develop a novel Quantum-Inspired Mean Field (QIMF) probabilistic model that approximates solutions to QUBO problems with enhanced accuracy and efficiency. The QIMF model draws inspiration from quantum measurement principles and leverages the mean field probabilistic model. We incorporate a measurement grouping technique and an amplitude-based shot allocation strategy, both critical for optimizing cost functions with a polynomial speedup over traditional methods. Our extensive empirical studies demonstrate significant improvements in solution evaluation for large-scale problems of portfolio selection, the weighted maxcut problem, and the Ising model. Specifically, using S&P 500 data from 2022 and 2023, QIMF improves cost values by 152.8% and 12.5%, respectively, compared to the state-of-the-art baselines. Furthermore, when evaluated on increasingly larger datasets for QUBO problems, QIMF's scalability demonstrates its potential for large-scale QUBO challenges., Comment: 13 pages, 10 figures

High-rate remote entanglement between photon and matter-based qubits is essential for distributed quantum information processing. A key technique to increase the modest entangling rates of existing long-distance quantum networking approaches is multiplexing. Here, we demonstrate a temporally multiplexed ion-photon interface via rapid transport of a chain of nine calcium ions across 74 $\mathrm{\mu m}$ within 86 $\mathrm{\mu s}$. The non-classical nature of the multiplexed photons is verified by measuring the second-order correlation function with an average value of $g^{(2)}(0)$ = 0.060(13), indicating negligible crosstalk between the multiplexed modes. In addition, we characterize the motional degree-of-freedom of the ion crystal after transport and find that it is coherently excited to as much as $\bar{n}_\alpha\approx 110$ for the center-of-mass mode. Our proof-of-principle implementation paves the way for large-scale quantum networking with trapped ions, but highlights some challenges that must be overcome., Comment: 6 pages, 4 figures

This paper explores an automatic news generation and fact-checking system based on language processing, aimed at enhancing the efficiency and quality of news production while ensuring the authenticity and reliability of the news content. With the rapid development of Natural Language Processing (NLP) and deep learning technologies, automatic news generation systems are capable of extracting key information from massive data and generating well-structured, fluent news articles. Meanwhile, by integrating fact-checking technology, the system can effectively prevent the spread of false news and improve the accuracy and credibility of news. This study details the key technologies involved in automatic news generation and factchecking, including text generation, information extraction, and the application of knowledge graphs, and validates the effectiveness of these technologies through experiments. Additionally, the paper discusses the future development directions of automatic news generation and fact-checking systems, emphasizing the importance of further integration and innovation of technologies. The results show that with continuous technological optimization and practical application, these systems will play an increasingly important role in the future news industry, providing more efficient and reliable news services.

Due to spatial redundancy in remote sensing images, sparse tokens containing rich information are usually involved in self-attention (SA) to reduce the overall token numbers within the calculation, avoiding the high computational cost issue in Vision Transformers. However, such methods usually obtain sparse tokens by hand-crafted or parallel-unfriendly designs, posing a challenge to reach a better balance between efficiency and performance. Different from them, this paper proposes to use learnable meta tokens to formulate sparse tokens, which effectively learn key information meanwhile improving the inference speed. Technically, the meta tokens are first initialized from image tokens via cross-attention. Then, we propose Dual Cross-Attention (DCA) to promote information exchange between image tokens and meta tokens, where they serve as query and key (value) tokens alternatively in a dual-branch structure, significantly reducing the computational complexity compared to self-attention. By employing DCA in the early stages with dense visual tokens, we obtain the hierarchical architecture LeMeViT with various sizes. Experimental results in classification and dense prediction tasks show that LeMeViT has a significant $1.7 \times$ speedup, fewer parameters, and competitive performance compared to the baseline models, and achieves a better trade-off between efficiency and performance., Comment: Accepted by IJCAI'2024. The code is available at https://github.com/ViTAE-Transformer/LeMeViT

The emerging all-van der Waals (vdW) magnetic heterostructure provides a new platform to control the magnetization by the electric field beyond the traditional spintronics devices. One promising strategy is using unconventional spin-orbit torque (SOT) exerted by the out-of-plane polarized spin current to enable deterministic magnetization switching and enhance the switching efficiency. However, in all-vdW heterostructures, large unconventional SOT remains elusive and the robustness of the field-free switching against external magnetic field hasn't been examined, which hinder further applications. Here we demonstrate the field-free switching in an all-vdW heterostructure combining a type-II Weyl semimetal TaIrTe4 and above-room-temperature ferromagnet Fe3GaTe2. The fully field-free switching can be achieved at 2.56 x 10^10 A per m2 at 300K and a large SOT effective field efficiency of the out-of-plane polarized spin current generated by TaIrTe4 is determined to be 0.37. Moreover, we find that the switching polarity cannot be changed until the external in-plane magnetic field reaches 252mT, indicating a robust switching against the magnetic field. The numerical simulation suggests the large unconventional SOT reduces the switching current density and enhances the robustness of the switching. Our work shows that all-vdW heterostructures are promising candidates for future highly efficient and stable SOT-based devices., Comment: 15 pages, 4 figures, accepted by Advanced Materials

A non-linear complex system governed by multi-spatial and multi-temporal physics scales cannot be fully understood with a single diagnostic, as each provides only a partial view and much information is lost during data extraction. Combining multiple diagnostics also results in imperfect projections of the system's physics. By identifying hidden inter-correlations between diagnostics, we can leverage mutual support to fill in these gaps, but uncovering these inter-correlations analytically is too complex. We introduce a groundbreaking machine learning methodology to address this issue. Our multimodal approach generates super resolution data encompassing multiple physics phenomena, capturing detailed structural evolution and responses to perturbations previously unobservable. This methodology addresses a critical problem in fusion plasmas: the Edge Localized Mode (ELM), a plasma instability that can severely damage reactor walls. One method to stabilize ELM is using resonant magnetic perturbation to trigger magnetic islands. However, low spatial and temporal resolution of measurements limits the analysis of these magnetic islands due to their small size, rapid dynamics, and complex interactions within the plasma. With super-resolution diagnostics, we can experimentally verify theoretical models of magnetic islands for the first time, providing unprecedented insights into their role in ELM stabilization. This advancement aids in developing effective ELM suppression strategies for future fusion reactors like ITER and has broader applications, potentially revolutionizing diagnostics in fields such as astronomy, astrophysics, and medical imaging.

The path of tokamak fusion and ITER is maintaining high-performance plasma to produce sufficient fusion power. This effort is hindered by the transient energy burst arising from the instabilities at the boundary of high-confinement plasmas. The application of 3D magnetic perturbations is the method in ITER and possibly in future fusion power plants to suppress this instability and avoid energy busts damaging the device. Unfortunately, the conventional use of the 3D field in tokamaks typically leads to degraded fusion performance and an increased risk of other plasma instabilities, two severe issues for reactor implementation. In this work, we present an innovative 3D field optimization, exploiting machine learning, real-time adaptability, and multi-device capabilities to overcome these limitations. This integrated scheme is successfully deployed on DIII-D and KSTAR tokamaks, consistently achieving reactor-relevant core confinement and the highest fusion performance without triggering damaging instabilities or bursts while demonstrating ITER-relevant automated 3D optimization for the first time. This is enabled both by advances in the physics understanding of self-organized transport in the plasma edge and by advances in machine-learning technology, which is used to optimize the 3D field spectrum for automated management of a volatile and complex system. These findings establish real-time adaptive 3D field optimization as a crucial tool for ITER and future reactors to maximize fusion performance while simultaneously minimizing damage to machine components.

The advent of neural and Gaussian-based radiance field methods have achieved great success in the field of novel view synthesis. However, specular reflection remains non-trivial, as the high frequency radiance field is notoriously difficult to fit stably and accurately. We present a deferred shading method to effectively render specular reflection with Gaussian splatting. The key challenge comes from the environment map reflection model, which requires accurate surface normal while simultaneously bottlenecks normal estimation with discontinuous gradients. We leverage the per-pixel reflection gradients generated by deferred shading to bridge the optimization process of neighboring Gaussians, allowing nearly correct normal estimations to gradually propagate and eventually spread over all reflective objects. Our method significantly outperforms state-of-the-art techniques and concurrent work in synthesizing high-quality specular reflection effects, demonstrating a consistent improvement of peak signal-to-noise ratio (PSNR) for both synthetic and real-world scenes, while running at a frame rate almost identical to vanilla Gaussian splatting.

An analytic calculation is given for binary star evaporation under the tidal perturbation from randomly distributed, spatially extended dark objects. In particular, the Milky Way's wide binary star population are susceptible to such disruption from dark matter solitons of comparable and larger sizes. We identify high-probability `halo-like' wide binaries in GAIA EDR3 with separations larger than 0.1 parsec. Survival of the farthest-separated candidates will provide a novel gravitational probe to dark matter in the form of solitons. In case of dilute axion-like solitons, the observational sensitivity is shown to extend into the axion mass range $m_a \sim 10^{-17}-10^{-15}$ eV., Comment: 15 pages, 4 figures, 3 tables

We describe our contribution as industrial stakeholders to the existing open-source GPU4PySCF project (https: //github.com/pyscf/gpu4pyscf), a GPU-accelerated Python quantum chemistry package. We have integrated GPU acceleration into other PySCF functionality including Density Functional Theory (DFT), geometry optimization, frequency analysis, solvent models, and density fitting technique. Through these contributions, GPU4PySCF v1.0 can now be regarded as a fully functional and industrially relevant platform which we demonstrate in this work through a range of tests. When performing DFT calculations on modern GPU platforms, GPU4PySCF delivers 30 times speedup over a 32-core CPU node, resulting in approximately 90% cost savings for most DFT tasks. The performance advantages and productivity improvements have been found in multiple industrial applications, such as generating potential energy surfaces, analyzing molecular properties, calculating solvation free energy, identifying chemical reactions in lithium-ion batteries, and accelerating neural-network methods. With the improved design that makes it easy to integrate with the Python and PySCF ecosystem, GPU4PySCF is natural choice that we can now recommend for many industrial quantum chemistry applications., Comment: 40 pages, 14 figures

Quadratic unconstrained binary optimization (QUBO) tasks are very important in chemistry, finance, job scheduling, and so on, which can be represented using graph structures, with the variables as nodes and the interaction between them as edges. Variational quantum algorithms, especially the Quantum Approximate Optimization Algorithm (QAOA) and its variants, present a promising way, potentially exceeding the capabilities of classical algorithms, for addressing QUBO tasks. However, the possibility of using message-passing machines, inspired by classical graph neural networks, to enhance the power and performance of these quantum algorithms for QUBO tasks was not investigated. This study introduces a novel variational quantum graph optimization algorithm that integrates the message-passing mechanism, which demonstrates significant improvements in performance for solving QUBO problems in terms of resource efficiency and solution precision, compared to QAOA, its variants, and other quantum graph neural networks. Furthermore, in terms of scalability on QUBO tasks, our algorithm shows superior performance compared to QAOA, presenting a substantial advancement in the field of quantum approximate optimization., Comment: 11pages,5figures

Traffic forecasting is crucial for intelligent transportation systems. It has experienced significant advancements thanks to the power of deep learning in capturing latent patterns of traffic data. However, recent deep-learning architectures require intricate model designs and lack an intuitive understanding of the mapping from input data to predicted results. Achieving both accuracy and explainability in traffic prediction models remains a challenge due to the complexity of traffic data and the inherent opacity of deep learning models. To tackle these challenges, we propose a Traffic flow Prediction model based on Large Language Models (LLMs) to generate explainable traffic predictions, named xTP-LLM. By transferring multi-modal traffic data into natural language descriptions, xTP-LLM captures complex time-series patterns and external factors from comprehensive traffic data. The LLM framework is fine-tuned using language-based instructions to align with spatial-temporal traffic flow data. Empirically, xTP-LLM shows competitive accuracy compared with deep learning baselines, while providing an intuitive and reliable explanation for predictions. This paper contributes to advancing explainable traffic prediction models and lays a foundation for future exploration of LLM applications in transportation. To the best of our knowledge, this is the first study to use LLM for explainable prediction of traffic flows., Comment: 31pages, 16 figures

RGB-T tracking, a vital downstream task of object tracking, has made remarkable progress in recent years. Yet, it remains hindered by two major challenges: 1) the trade-off between performance and efficiency; 2) the scarcity of training data. To address the latter challenge, some recent methods employ prompts to fine-tune pre-trained RGB tracking models and leverage upstream knowledge in a parameter-efficient manner. However, these methods inadequately explore modality-independent patterns and disregard the dynamic reliability of different modalities in open scenarios. We propose M3PT, a novel RGB-T prompt tracking method that leverages middle fusion and multi-modal and multi-stage visual prompts to overcome these challenges. We pioneer the use of the adjustable middle fusion meta-framework for RGB-T tracking, which could help the tracker balance the performance with efficiency, to meet various demands of application. Furthermore, based on the meta-framework, we utilize multiple flexible prompt strategies to adapt the pre-trained model to comprehensive exploration of uni-modal patterns and improved modeling of fusion-modal features in diverse modality-priority scenarios, harnessing the potential of prompt learning in RGB-T tracking. Evaluating on 6 existing challenging benchmarks, our method surpasses previous state-of-the-art prompt fine-tuning methods while maintaining great competitiveness against excellent full-parameter fine-tuning methods, with only 0.34M fine-tuned parameters.

Supervised deep learning techniques can be used to generate synthetic 7T MRIs from 3T MRI inputs. This image enhancement process leverages the advantages of ultra-high-field MRI to improve the signal-to-noise and contrast-to-noise ratios of 3T acquisitions. In this paper, we introduce multiple novel 7T synthesization algorithms based on custom-designed variants of the V-Net convolutional neural network. We demonstrate that the V-Net based model has superior performance in enhancing both single-site and multi-site MRI datasets compared to the existing benchmark model. When trained on 3T-7T MRI pairs from 8 subjects with mild Traumatic Brain Injury (TBI), our model achieves state-of-the-art 7T synthesization performance. Compared to previous works, synthetic 7T images generated from our pipeline also display superior enhancement of pathological tissue. Additionally, we implement and test a data augmentation scheme for training models that are robust to variations in the input distribution. This allows synthetic 7T models to accommodate intra-scanner and inter-scanner variability in multisite datasets. On a harmonized dataset consisting of 18 3T-7T MRI pairs from two institutions, including both healthy subjects and those with mild TBI, our model maintains its performance and can generalize to 3T MRI inputs with lower resolution. Our findings demonstrate the promise of V-Net based models for MRI enhancement and offer a preliminary probe into improving the generalizability of synthetic 7T models with data augmentation., Comment: 13 pages including supplemental materials, accepted for presentation at MICCAI 2024

Survival analysis serves as a fundamental component in numerous healthcare applications, where the determination of the time to specific events (such as the onset of a certain disease or death) for patients is crucial for clinical decision-making. Scoring systems are widely used for swift and efficient risk prediction. However, existing methods for constructing survival scores presume that data originates from a single source, posing privacy challenges in collaborations with multiple data owners. We propose a novel framework for building federated scoring systems for multi-site survival outcomes, ensuring both privacy and communication efficiency. We applied our approach to sites with heterogeneous survival data originating from emergency departments in Singapore and the United States. Additionally, we independently developed local scores at each site. In testing datasets from each participant site, our proposed federated scoring system consistently outperformed all local models, evidenced by higher integrated area under the receiver operating characteristic curve (iAUC) values, with a maximum improvement of 11.6%. Additionally, the federated score's time-dependent AUC(t) values showed advantages over local scores, exhibiting narrower confidence intervals (CIs) across most time points. The model developed through our proposed method exhibits effective performance on each local site, signifying noteworthy implications for healthcare research. Sites participating in our proposed federated scoring model training gained benefits by acquiring survival models with enhanced prediction accuracy and efficiency. This study demonstrates the effectiveness of our privacy-preserving federated survival score generation framework and its applicability to real-world heterogeneous survival data.

The interactions between power, transportation, and information networks (PTIN), are becoming more profound with the advent of smart city technologies. Existing mobile energy storage resource (MESR)-based power distribution network (PDN) restoration schemes often neglect the interdependencies among PTIN, thus, efficient PDN restoration cannot be achieved. This paper outlines the interacting factors of power supply demand, traffic operation efficiency, communication coverage, electric vehicle (EV) deployment capability, and PDN controllability among PTIN and further develops a PTIN-interacting model to reflect the chained recovery effect of the MESR-based restoration process. On this basis, a two-stage PDN restoration scheme is proposed that utilizes three emergency resources, including EVs, mobile energy storage systems (MESSs), and unmanned aerial vehicles (UAVs), to restore the power supply and communication of PDNs. This scheme first improves the distribution automation function, EV deployment capability, and traffic operation efficiency by prioritizing the recovery of communication network (CN) and urban traffic network (UTN) loads. Then, EVs and MESSs are further scheduled to achieve a better PDN restoration effect with the support of the restored CNs and UTNs. Case studies on a PDN, CN, and UTN integrated test system are conducted to verify the effectiveness of the proposed scheme. The results show that the prioritized load recovery operation for CN and UTN facilities in this scheme greatly improves the PDN restoration effect.