Search

Combining the complementary benefits of frames and events has been widely used for object detection in challenging scenarios. However, most object detection methods use two independent Artificial Neural Network (ANN) branches, limiting cross-modality information interaction across the two visual streams and encountering challenges in extracting temporal cues from event streams with low power consumption. To address these challenges, we propose HDI-Former, a Hybrid Dynamic Interaction ANN-SNN Transformer, marking the first trial to design a directly trained hybrid ANN-SNN architecture for high-accuracy and energy-efficient object detection using frames and events. Technically, we first present a novel semantic-enhanced self-attention mechanism that strengthens the correlation between image encoding tokens within the ANN Transformer branch for better performance. Then, we design a Spiking Swin Transformer branch to model temporal cues from event streams with low power consumption. Finally, we propose a bio-inspired dynamic interaction mechanism between ANN and SNN sub-networks for cross-modality information interaction. The results demonstrate that our HDI-Former outperforms eleven state-of-the-art methods and our four baselines by a large margin. Our SNN branch also shows comparable performance to the ANN with the same architecture while consuming 10.57$\times$ less energy on the DSEC-Detection dataset. Our open-source code is available in the supplementary material., Comment: 17 pages, 11 figures

Graph neural architecture search (GNAS) can customize high-performance graph neural network architectures for specific graph tasks or datasets. However, existing GNAS methods begin searching for architectures from a zero-knowledge state, ignoring the prior knowledge that may improve the search efficiency. The available knowledge base (e.g. NAS-Bench-Graph) contains many rich architectures and their multiple performance metrics, such as the accuracy (#Acc) and number of parameters (#Params). This study proposes exploiting such prior knowledge to accelerate the multi-objective evolutionary search on a new graph dataset, named knowledge-aware evolutionary GNAS (KEGNAS). KEGNAS employs the knowledge base to train a knowledge model and a deep multi-output Gaussian process (DMOGP) in one go, which generates and evaluates transfer architectures in only a few GPU seconds. The knowledge model first establishes a dataset-to-architecture mapping, which can quickly generate candidate transfer architectures for a new dataset. Subsequently, the DMOGP with architecture and dataset encodings is designed to predict multiple performance metrics for candidate transfer architectures on the new dataset. According to the predicted metrics, non-dominated candidate transfer architectures are selected to warm-start the multi-objective evolutionary algorithm for optimizing the #Acc and #Params on a new dataset. Empirical studies on NAS-Bench-Graph and five real-world datasets show that KEGNAS swiftly generates top-performance architectures, achieving 4.27% higher accuracy than advanced evolutionary baselines and 11.54% higher accuracy than advanced differentiable baselines. In addition, ablation studies demonstrate that the use of prior knowledge significantly improves the search performance., Comment: This work has been accepted by Knowledge-Based Systems

Effective performance profiling and analysis are essential for optimizing training and inference of deep learning models, especially given the growing complexity of heterogeneous computing environments. However, existing tools often lack the capability to provide comprehensive program context information and performance optimization insights for sophisticated interactions between CPUs and GPUs. This paper introduces DeepContext, a novel profiler that links program contexts across high-level Python code, deep learning frameworks, underlying libraries written in C/C++, as well as device code executed on GPUs. DeepContext incorporates measurements of both coarse- and fine-grained performance metrics for major deep learning frameworks, such as PyTorch and JAX, and is compatible with GPUs from both Nvidia and AMD, as well as various CPU architectures, including x86 and ARM. In addition, DeepContext integrates a novel GUI that allows users to quickly identify hotpots and an innovative automated performance analyzer that suggests users with potential optimizations based on performance metrics and program context. Through detailed use cases, we demonstrate how DeepContext can help users identify and analyze performance issues to enable quick and effective optimization of deep learning workloads. We believe Deep Context is a valuable tool for users seeking to optimize complex deep learning workflows across multiple compute environments.

Time series foundation models have demonstrated impressive performance as zero-shot forecasters. However, achieving effectively unified training on time series remains an open challenge. Existing approaches introduce some level of model specialization to account for the highly heterogeneous nature of time series data. For instance, Moirai pursues unified training by employing multiple input/output projection layers, each tailored to handle time series at a specific frequency. Similarly, TimesFM maintains a frequency embedding dictionary for this purpose. We identify two major drawbacks to this human-imposed frequency-level model specialization: (1) Frequency is not a reliable indicator of the underlying patterns in time series. For example, time series with different frequencies can display similar patterns, while those with the same frequency may exhibit varied patterns. (2) Non-stationarity is an inherent property of real-world time series, leading to varied distributions even within a short context window of a single time series. Frequency-level specialization is too coarse-grained to capture this level of diversity. To address these limitations, this paper introduces Moirai-MoE, using a single input/output projection layer while delegating the modeling of diverse time series patterns to the sparse mixture of experts (MoE) within Transformers. With these designs, Moirai-MoE reduces reliance on human-defined heuristics and enables automatic token-level specialization. Extensive experiments on 39 datasets demonstrate the superiority of Moirai-MoE over existing foundation models in both in-distribution and zero-shot scenarios. Furthermore, this study conducts comprehensive model analyses to explore the inner workings of time series MoE foundation models and provides valuable insights for future research.

Time series foundation models excel in zero-shot forecasting, handling diverse tasks without explicit training. However, the advancement of these models has been hindered by the lack of comprehensive benchmarks. To address this gap, we introduce the General Time Series Forecasting Model Evaluation, GIFT-Eval, a pioneering benchmark aimed at promoting evaluation across diverse datasets. GIFT-Eval encompasses 23 datasets over 144,000 time series and 177 million data points, spanning seven domains, 10 frequencies, multivariate inputs, and prediction lengths ranging from short to long-term forecasts. To facilitate the effective pretraining and evaluation of foundation models, we also provide a non-leaking pretraining dataset containing approximately 230 billion data points. Additionally, we provide a comprehensive analysis of 17 baselines, which includes statistical models, deep learning models, and foundation models. We discuss each model in the context of various benchmark characteristics and offer a qualitative analysis that spans both deep learning and foundation models. We believe the insights from this analysis, along with access to this new standard zero-shot time series forecasting benchmark, will guide future developments in time series foundation models. Code, data, and the leaderboard can be found at https://github.com/SalesforceAIResearch/gift-eval .

This paper is devoted to studying a multi-objective control problem for a class of multi-dimensional quasi-linear parabolic equations. The considered system is driven by a leader control and two follower controls. For each leader control, a pair of follower controls is searched for as a Nash quasi-equilibrium (or Nash equilibrium) of cost functionals, while the aim for a leader control is to solve a controllability problem. This hierarchic control problem may be transformed into controllability of a strongly coupled system of quasi-linear parabolic equations through one control. Regarding controllability for quasi-linear parabolic equations of second order, the existing results usually require coefficients in principal parts to be independent of gradient of solutions, or spacial dimension to be limited. In this paper, the coefficients in principal parts for the controlled quasi-linear system contain not only the state itself but also its gradient with general spacial dimension.

Automated persistent and fine-grained monitoring of orchards at the individual tree or fruit level helps maximize crop yield and optimize resources such as water, fertilizers, and pesticides while preventing agricultural waste. Towards this goal, we present a 4D spatio-temporal metric-semantic mapping method that fuses data from multiple sensors, including LiDAR, RGB camera, and IMU, to monitor the fruits in an orchard across their growth season. A LiDAR-RGB fusion module is designed for 3D fruit tracking and localization, which first segments fruits using a deep neural network and then tracks them using the Hungarian Assignment algorithm. Additionally, the 4D data association module aligns data from different growth stages into a common reference frame and tracks fruits spatio-temporally, providing information such as fruit counts, sizes, and positions. We demonstrate our method's accuracy in 4D metric-semantic mapping using data collected from a real orchard under natural, uncontrolled conditions with seasonal variations. We achieve a 3.1 percent error in total fruit count estimation for over 1790 fruits across 60 apple trees, along with accurate size estimation results with a mean error of 1.1 cm. The datasets, consisting of LiDAR, RGB, and IMU data of five fruit species captured across their growth seasons, along with corresponding ground truth data, will be made publicly available at: https://4d-metric-semantic-mapping.org/

Holography is an essential technique of generating three-dimensional images. Recently, quantum holography with undetected photons (QHUP) has emerged as a groundbreaking method capable of capturing complex amplitude images. Despite its potential, the practical application of QHUP has been limited by susceptibility to phase disturbances, low interference visibility, and limited spatial resolution. Deep learning, recognized for its ability in processing complex data, holds significant promise in addressing these challenges. In this report, we present an ample advancement in QHUP achieved by harnessing the power of deep learning to extract images from single-shot holograms, resulting in vastly reduced noise and distortion, alongside a notable enhancement in spatial resolution. The proposed and demonstrated deep learning QHUP (DL-QHUP) methodology offers a transformative solution by delivering high-speed imaging, improved spatial resolution, and superior noise resilience, making it suitable for diverse applications across an array of research fields stretching from biomedical imaging to remote sensing. DL-QHUP signifies a crucial leap forward in the realm of holography, demonstrating its immense potential to revolutionize imaging capabilities and pave the way for advancements in various scientific disciplines. The integration of DL-QHUP promises to unlock new possibilities in imaging applications, transcending existing limitations and offering unparalleled performance in challenging environments.

Perceiving the global field from sparse sensors has been a grand challenge in the monitoring, analysis, and design of physical systems. In this context, sensor placement optimization is a crucial issue. Most existing works require large and sufficient data to construct data-based criteria, which are intractable in data-free scenarios without numerical and experimental data. To this end, we propose a novel physics-driven sensor placement optimization (PSPO) method for temperature field reconstruction using a physics-based criterion to optimize sensor locations. In our methodological framework, we firstly derive the theoretical upper and lower bounds of the reconstruction error under noise scenarios by analyzing the optimal solution, proving that error bounds correlate with the condition number determined by sensor locations. Furthermore, the condition number, as the physics-based criterion, is used to optimize sensor locations by the genetic algorithm. Finally, the best sensors are validated by reconstruction models, including non-invasive end-to-end models, non-invasive reduced-order models, and physics-informed models. Experimental results, both on a numerical and an application case, demonstrate that the PSPO method significantly outperforms random and uniform selection methods, improving the reconstruction accuracy by nearly an order of magnitude. Moreover, the PSPO method can achieve comparable reconstruction accuracy to the existing data-driven placement optimization methods.

This paper reviews the challenge on Sparse Neural Rendering that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2024. This manuscript focuses on the competition set-up, the proposed methods and their respective results. The challenge aims at producing novel camera view synthesis of diverse scenes from sparse image observations. It is composed of two tracks, with differing levels of sparsity; 3 views in Track 1 (very sparse) and 9 views in Track 2 (sparse). Participants are asked to optimise objective fidelity to the ground-truth images as measured via the Peak Signal-to-Noise Ratio (PSNR) metric. For both tracks, we use the newly introduced Sparse Rendering (SpaRe) dataset and the popular DTU MVS dataset. In this challenge, 5 teams submitted final results to Track 1 and 4 teams submitted final results to Track 2. The submitted models are varied and push the boundaries of the current state-of-the-art in sparse neural rendering. A detailed description of all models developed in the challenge is provided in this paper., Comment: Part of Advances in Image Manipulation workshop at ECCV 2024

Despite the promising performance of current video segmentation models on existing benchmarks, these models still struggle with complex scenes. In this paper, we introduce the 6th Large-scale Video Object Segmentation (LSVOS) challenge in conjunction with ECCV 2024 workshop. This year's challenge includes two tasks: Video Object Segmentation (VOS) and Referring Video Object Segmentation (RVOS). In this year, we replace the classic YouTube-VOS and YouTube-RVOS benchmark with latest datasets MOSE, LVOS, and MeViS to assess VOS under more challenging complex environments. This year's challenge attracted 129 registered teams from more than 20 institutes across over 8 countries. This report include the challenge and dataset introduction, and the methods used by top 7 teams in two tracks. More details can be found in our homepage https://lsvos.github.io/., Comment: ECCV 2024 LSVOS Challenge Report: https://lsvos.github.io/

Satellite imagery, due to its long-range imaging, brings with it a variety of scale-preferred tasks, such as the detection of tiny/small objects, making the precise localization and detection of small objects of interest a challenging task. In this article, we design a Knowledge Discovery Network (KDN) to implement the renormalization group theory in terms of efficient feature extraction. Renormalized connection (RC) on the KDN enables ``synergistic focusing'' of multi-scale features. Based on our observations of KDN, we abstract a class of RCs with different connection strengths, called n21C, and generalize it to FPN-based multi-branch detectors. In a series of FPN experiments on the scale-preferred tasks, we found that the ``divide-and-conquer'' idea of FPN severely hampers the detector's learning in the right direction due to the large number of large-scale negative samples and interference from background noise. Moreover, these negative samples cannot be eliminated by the focal loss function. The RCs extends the multi-level feature's ``divide-and-conquer'' mechanism of the FPN-based detectors to a wide range of scale-preferred tasks, and enables synergistic effects of multi-level features on the specific learning goal. In addition, interference activations in two aspects are greatly reduced and the detector learns in a more correct direction. Extensive experiments of 17 well-designed detection architectures embedded with n21s on five different levels of scale-preferred tasks validate the effectiveness and efficiency of the RCs. Especially the simplest linear form of RC, E421C performs well in all tasks and it satisfies the scaling property of RGT. We hope that our approach will transfer a large number of well-designed detectors from the computer vision community to the remote sensing community., Comment: 24 pages, 14 figures Journal

Predictive learning for spatio-temporal processes (PL-STP) on complex spatial domains plays a critical role in various scientific and engineering fields, with its essence being the construction of operators between infinite-dimensional function spaces. This paper focuses on the unequal-domain mappings in PL-STP and categorising them into increase-domain and decrease-domain mapping. Recent advances in deep learning have revealed the great potential of neural operators (NOs) to learn operators directly from observational data. However, existing NOs require input space and output space to be the same domain, which pose challenges in ensuring predictive accuracy and stability for unequal-domain mappings. To this end, this study presents a general reduced-order neural operator named Reduced-Order Neural Operator on Riemannian Manifolds (RO-NORM), which consists of two parts: the unequal-domain encoder/decoder and the same-domain approximator. Motivated by the variable separation in classical modal decomposition, the unequal-domain encoder/decoder uses the pre-computed bases to reformulate the spatio-temporal function as a sum of products between spatial (or temporal) bases and corresponding temporally (or spatially) distributed weight functions, thus the original unequal-domain mapping can be converted into a same-domain mapping. Consequently, the same-domain approximator NORM is applied to model the transformed mapping. The performance of our proposed method has been evaluated on six benchmark cases, including parametric PDEs, engineering and biomedical applications, and compared with four baseline algorithms: DeepONet, POD-DeepONet, PCA-Net, and vanilla NORM. The experimental results demonstrate the superiority of RO-NORM in prediction accuracy and training efficiency for PL-STP.

Tightly focused optical fields are essential in nano-optics, but their applications have been limited by the challenges of accurate yet efficient characterization. In this article, we develop an in situ method for reconstructing the fully vectorial information of tightly focused fields in three-dimensional (3D) space, while simultaneously retrieving the pupil functions. Our approach encodes these fields using phase-modulated focusing and polarization-split detection, followed by decoding through an algorithm based on least-sampling matrix-based Fourier transform and analytically derived gradient. We further employ a focus scanning strategy. When combined with our decoding algorithm, this strategy mitigates the imperfections in the detection path. This approach requires only 10 frames of 2D measurements to realize approximate 90% accuracy in tomography and pupil function retrieval within 10s. Thus, it serves as a robust and convenient tool for the precise characterization and optimization of light at the nanoscale. We apply this technique to fully vectorial field manipulation, adaptive-optics-assisted nanoscopy, and addressing mixed-state problems., Comment: 10 pages, 5 figures

Considered here are robust subgroup-classifier learning and testing in change-plane regressions with heavy-tailed errors, which can identify subgroups as a basis for making optimal recommendations for individualized treatment. A new subgroup classifier is proposed by smoothing the indicator function, which is learned by minimizing the smoothed Huber loss. Nonasymptotic properties and the Bahadur representation of estimators are established, in which the proposed estimators of the grouping difference parameter and baseline parameter achieve sub-Gaussian tails. The hypothesis test considered here belongs to the class of test problems for which some parameters are not identifiable under the null hypothesis. The classic supremum of the squared score test statistic may lose power in practice when the dimension of the grouping parameter is large, so to overcome this drawback and make full use of the data's heavy-tailed error distribution, a robust weighted average of the squared score test statistic is proposed, which achieves a closed form when an appropriate weight is chosen. Asymptotic distributions of the proposed robust test statistic are derived under the null and alternative hypotheses. The proposed robust subgroup classifier and test statistic perform well on finite samples, and their performances are shown further by applying them to a medical dataset. The proposed procedure leads to the immediate application of recommending optimal individualized treatments.

Video Object Segmentation (VOS) presents several challenges, including object occlusion and fragmentation, the dis-appearance and re-appearance of objects, and tracking specific objects within crowded scenes. In this work, we combine the strengths of the state-of-the-art (SOTA) models SAM2 and Cutie to address these challenges. Additionally, we explore the impact of various hyperparameters on video instance segmentation performance. Our approach achieves a J\&F score of 0.7952 in the testing phase of LSVOS challenge VOS track, ranking third overall., Comment: arXiv admin note: text overlap with arXiv:2406.03668

Considered here is a hypothesis test for the coefficients in the change-plane regression models to detect the existence of a change plane. The test that is considered is from the class of test problems in which some parameters are not identifiable under the null hypothesis. The classic exponential average tests do not work well in practice. To overcome this drawback, a novel test statistic is proposed by taking the weighted average of the squared score test statistic (WAST) over the grouping parameter's space, which has a closed form from the perspective of the conjugate priors when an appropriate weight is chosen. The WAST significantly improves the power in practice, particularly in cases where the number of the grouping variables is large. The asymptotic distributions of the WAST are derived under the null and alternative hypotheses. The approximation of critical value by the bootstrap method is investigated, which is theoretically guaranteed. Furthermore, the proposed test method is naturally extended to the generalized estimating equation (GEE) framework, as well as multiple change planes that can test if there are three or more subgroups. The WAST performs well in simulation studies, and its performance is further validated by applying it to real datasets.

Convolution is the core component within deep neural networks and it is computationally intensive and time consuming. Tensor data layouts significantly impact convolution operations in terms of memory access and computational efficiency. Yet, there is still a lack of comprehensive performance characterization on data layouts on SIMD architectures concerning convolution methods. This paper proposes three novel data layouts for im2win convolution: NHWC, CHWN, and CHWN8, and introduces a set of general optimization techniques for both direct and im2win convolutions. We compare the optimized im2win convolution with the direct convolution and PyTorch's im2col-based convolution across the aforementioned layouts on SIMD machines. The experiments demonstrated that the im2win convolution with the new NHWC layout achieved up to 355% performance speedup over NCHW layout. Our optimizations also significantly improve the performance of both im2win and direct convolutions. Our optimized im2win and direct convolutions achieved up to 95% and 94% of machine's theoretical peak performance, respectively.

Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, \textbf{E}nergy-guided \textbf{DI}ffusion \textbf{S}ampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions to distill this knowledge for enhanced data generation in the online phase. The theoretical analysis demonstrates that EDIS exhibits reduced suboptimality compared to solely utilizing online data or directly reusing offline data. EDIS is a plug-in approach and can be combined with existing methods in offline-to-online RL setting. By implementing EDIS to off-the-shelf methods Cal-QL and IQL, we observe a notable 20% average improvement in empirical performance on MuJoCo, AntMaze, and Adroit environments. Code is available at \url{https://github.com/liuxhym/EDIS}.

Understanding 3D scenes is a crucial challenge in computer vision research with applications spanning multiple domains. Recent advancements in distilling 2D vision-language foundation models into neural fields, like NeRF and 3DGS, enable open-vocabulary segmentation of 3D scenes from 2D multi-view images without the need for precise 3D annotations. However, while effective, these methods typically rely on the per-pixel distillation of high-dimensional CLIP features, introducing ambiguity and necessitating complex regularization strategies, which adds inefficiency during training. This paper presents MaskField, which enables efficient 3D open-vocabulary segmentation with neural fields from a novel perspective. Unlike previous methods, MaskField decomposes the distillation of mask and semantic features from foundation models by formulating a mask feature field and queries. MaskField overcomes ambiguous object boundaries by naturally introducing SAM segmented object shapes without extra regularization during training. By circumventing the direct handling of dense high-dimensional CLIP features during training, MaskField is particularly compatible with explicit scene representations like 3DGS. Our extensive experiments show that MaskField not only surpasses prior state-of-the-art methods but also achieves remarkably fast convergence. We hope that MaskField will inspire further exploration into how neural fields can be trained to comprehend 3D scenes from 2D models., Comment: 15 pages, 9 figures

The utilization of Large Language Models (LLMs) in financial trading has primarily been concentrated within the stock market, aiding in economic and financial decisions. Yet, the unique opportunities presented by the cryptocurrency market, noted for its on-chain data's transparency and the critical influence of off-chain signals like news, remain largely untapped by LLMs. This work aims to bridge the gap by developing an LLM-based trading agent, CryptoTrade, which uniquely combines the analysis of on-chain and off-chain data. This approach leverages the transparency and immutability of on-chain data, as well as the timeliness and influence of off-chain signals, providing a comprehensive overview of the cryptocurrency market. CryptoTrade incorporates a reflective mechanism specifically engineered to refine its daily trading decisions by analyzing the outcomes of prior trading decisions. This research makes two significant contributions. Firstly, it broadens the applicability of LLMs to the domain of cryptocurrency trading. Secondly, it establishes a benchmark for cryptocurrency trading strategies. Through extensive experiments, CryptoTrade has demonstrated superior performance in maximizing returns compared to traditional trading strategies and time-series baselines across various cryptocurrencies and market conditions. Our code and data are available at \url{https://anonymous.4open.science/r/CryptoTrade-Public-92FC/}.

This paper develops a real-time decentralized metric-semantic Simultaneous Localization and Mapping (SLAM) algorithm framework that enables a heterogeneous robot team to collaboratively construct object-based metric-semantic maps of 3D environments featuring indoor, urban, and forests without relying on GPS. The framework integrates a data-driven front-end for instance segmentation from either RGBD cameras or LiDARs and a custom back-end for optimizing robot trajectories and object landmarks in the map. To allow multiple robots to merge their information, we design semantics-driven place recognition algorithms that leverage the informativeness and viewpoint invariance of the object-level metric-semantic map for inter-robot loop closure detection. A communication module is designed to track each robot's observations and those of other robots whenever communication links are available. Our framework enables real-time decentralized operations onboard robots, allowing them to opportunistically leverage communication. We integrate the proposed framework with the autonomous navigation and exploration systems of three types of aerial and ground robots, conducting extensive experiments in a variety of indoor and outdoor environments. These experiments demonstrate accuracy in inter-robot localization and object mapping, along with its moderate demands on computation, storage, and communication resources. The framework is open-sourced and available as a modular stack for object-level metric-semantic SLAM, suitable for both single-agent and multi-robot scenarios. The project website and code can be found at https://xurobotics.github.io/slideslam/ and https://github.com/XuRobotics/SLIDE_SLAM, respectively., Comment: Xu Liu, Jiuzhou Lei, and Ankit Prabhu contributed equally to this work. This is a preliminary release and is subject to improvement

The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches., Comment: CVPR 2024 PBDL Challenges: https://pbdl-ws.github.io/pbdl2024/challenge/index.html

The meta-material sensor has been regarded as a next-generation sensing technology for the battery-free Internet of Things (IoT) due to its battery-free characteristic and improved sensing performance. The meta-material sensors function as backscatter tags that change their reflection coefficients with the conditions of sensing targets such as temperature and gas concentration, allowing transceivers to perform sensing by analyzing the reflected signals from the sensors. Simultaneously, the sensors also function as environmental scatterers, creating additional signal paths to enhance communication performance. Therefore, the meta-material sensor potentially provides a new paradigm of Integrated Sensing and Communication (ISAC) for the battery-free IoT system. In this article, we first propose a Meta-Backscatter system that utilizes meta-material sensors to achieve diverse sensing functionalities and improved communication performance. We begin with the introduction of the metamaterial sensor and further elaborate on the Meta-Backscatter system. Subsequently, we present optimization strategies for meta-material sensors, transmitters, and receivers to strike a balance between sensing and communication. Furthermore, this article provides a case study of the system and examines the feasibility and trade-off through the simulation results. Finally, potential extensions of the system and their related research challenges are addressed.

Neural Radiance Fields (NeRF) have been successfully applied in various aerial scenes, yet they face challenges with sparse views due to limited supervision. The acquisition of dense aerial views is often prohibitive, as unmanned aerial vehicles (UAVs) may encounter constraints in perspective range and energy constraints. In this work, we introduce Multiplane Prior guided NeRF (MPNeRF), a novel approach tailored for few-shot aerial scene rendering-marking a pioneering effort in this domain. Our key insight is that the intrinsic geometric regularities specific to aerial imagery could be leveraged to enhance NeRF in sparse aerial scenes. By investigating NeRF's and Multiplane Image (MPI)'s behavior, we propose to guide the training process of NeRF with a Multiplane Prior. The proposed Multiplane Prior draws upon MPI's benefits and incorporates advanced image comprehension through a SwinV2 Transformer, pre-trained via SimMIM. Our extensive experiments demonstrate that MPNeRF outperforms existing state-of-the-art methods applied in non-aerial contexts, by tripling the performance in SSIM and LPIPS even with three views available. We hope our work offers insights into the development of NeRF-based applications in aerial scenes with limited data., Comment: 17 pages, 8 figures, accepted at CVPR 2024

In rotating black hole background surrounded by dark matter, we investigated the super-radiant phenomenon of massive scalar field and its associated instability.Using the method of asymptotic matching, we computed the amplification factor of scalar wave scattering to assess the strength of super-radiance. We discussed the influence of dark matter density on amplification factor in this black hole background. Our result indicates that the presence of dark matter has suppressive influence on black hole super-radiance. We also computed the net extracted energy to further support this result. Finally, we analyzed the super-radiant instability caused by massive scalar field using the black hole bomb mechanism and found that the presence of dark matter has no influence on the super-radiant instability condition., Comment: v1:14 pages, 5 figures,1 table. v2:16 pages, 4 figures, 1 tale, figures updated, discussions expanded, reference added, version to appear in Physics of the Dark Universe

Unlike natural language processing and computer vision, the development of Foundation Models (FMs) for time series forecasting is blocked due to data scarcity. While recent efforts are focused on building such FMs by unlocking the potential of language models (LMs) for time series analysis, dedicated parameters for various downstream forecasting tasks need training, which hinders the common knowledge sharing across domains. Moreover, data owners may hesitate to share the access to local data due to privacy concerns and copyright protection, which makes it impossible to simply construct a FM on cross-domain training instances. To address these issues, we propose Time-FFM, a Federated Foundation Model for Time series forecasting by leveraging pretrained LMs. Specifically, we begin by transforming time series into the modality of text tokens. To bootstrap LMs for time series reasoning, we propose a prompt adaption module to determine domain-customized prompts dynamically instead of artificially. Given the data heterogeneity across domains, we design a personalized federated training strategy by learning global encoders and local prediction heads. Our comprehensive experiments indicate that Time-FFM outperforms state-of-the-arts and promises effective few-shot and zero-shot forecaster.

Spatio-temporal graph neural networks have proven efficacy in capturing complex dependencies for urban computing tasks such as forecasting and kriging. Yet, their performance is constrained by the reliance on extensive data for training on a specific task, thereby limiting their adaptability to new urban domains with varied task demands. Although transfer learning has been proposed to remedy this problem by leveraging knowledge across domains, the cross-task generalization still remains under-explored in spatio-temporal graph transfer learning due to the lack of a unified framework. To bridge the gap, we propose Spatio-Temporal Graph Prompting (STGP), a prompt-based framework capable of adapting to multi-diverse tasks in a data-scarce domain. Specifically, we first unify different tasks into a single template and introduce a task-agnostic network architecture that aligns with this template. This approach enables capturing dependencies shared across tasks. Furthermore, we employ learnable prompts to achieve domain and task transfer in a two-stage prompting pipeline, facilitating the prompts to effectively capture domain knowledge and task-specific properties. Our extensive experiments demonstrate that STGP outperforms state-of-the-art baselines in three tasks-forecasting, kriging, and extrapolation-achieving an improvement of up to 10.7%.

Existing diffusion-based methods have achieved impressive results in human motion editing. However, these methods often exhibit significant ghosting and body distortion in unseen in-the-wild cases. In this paper, we introduce Edit-Your-Motion, a video motion editing method that tackles these challenges through one-shot fine-tuning on unseen cases. Specifically, firstly, we utilized DDIM inversion to initialize the noise, preserving the appearance of the source video and designed a lightweight motion attention adapter module to enhance motion fidelity. DDIM inversion aims to obtain the implicit representations by estimating the prediction noise from the source video, which serves as a starting point for the sampling process, ensuring the appearance consistency between the source and edited videos. The Motion Attention Module (MA) enhances the model's motion editing ability by resolving the conflict between the skeleton features and the appearance features. Secondly, to effectively decouple motion and appearance of source video, we design a spatio-temporal two-stage learning strategy (STL). In the first stage, we focus on learning temporal features of human motion and propose recurrent causal attention (RCA) to ensure consistency between video frames. In the second stage, we shift focus on learning the appearance features of the source video. With Edit-Your-Motion, users can edit the motion of humans in the source video, creating more engaging and diverse content. Extensive qualitative and quantitative experiments, along with user preference studies, show that Edit-Your-Motion outperforms other methods.

In semi-supervised learning, methods that rely on confidence learning to generate pseudo-labels have been widely proposed. However, increasing research finds that when faced with noisy and biased data, the model's representation network is more reliable than the classification network. Additionally, label generation methods based on model predictions often show poor adaptability across different datasets, necessitating customization of the classification network. Therefore, we propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. We also introduce an adaptive method for selecting hyperparameters in HDL, enhancing its versatility. Moreover, HDL can be combined with general image encoders (e.g., CLIP) to serve as a fundamental data processing module. We extract embeddings from datasets with class-balanced and long-tailed distributions using pre-trained semi-supervised models. Subsequently, samples are re-labeled using HDL, and the re-labeled samples are used to further train the semi-supervised models. Experiments demonstrate improved model performance, validating the motivation that representation networks are more reliable than classifiers or predictors. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.

Chain-of-Thought (CoT) has been a widely adopted prompting method, eliciting impressive reasoning abilities of Large Language Models (LLMs). Inspired by the sequential thought structure of CoT, a number of Chain-of-X (CoX) methods have been developed to address various challenges across diverse domains and tasks involving LLMs. In this paper, we provide a comprehensive survey of Chain-of-X methods for LLMs in different contexts. Specifically, we categorize them by taxonomies of nodes, i.e., the X in CoX, and application tasks. We also discuss the findings and implications of existing CoX methods, as well as potential future directions. Our survey aims to serve as a detailed and up-to-date resource for researchers seeking to apply the idea of CoT to broader scenarios.

Building fair deep neural networks (DNNs) is a crucial step towards achieving trustworthy artificial intelligence. Delving into deeper factors that affect the fairness of DNNs is paramount and serves as the foundation for mitigating model biases. However, current methods are limited in accurately predicting DNN biases, relying solely on the number of training samples and lacking more precise measurement tools. Here, we establish a geometric perspective for analyzing the fairness of DNNs, comprehensively exploring how DNNs internally shape the intrinsic geometric characteristics of datasets-the intrinsic dimensions (IDs) of perceptual manifolds, and the impact of IDs on the fairness of DNNs. Based on multiple findings, we propose Intrinsic Dimension Regularization (IDR), which enhances the fairness and performance of models by promoting the learning of concise and ID-balanced class perceptual manifolds. In various image recognition benchmark tests, IDR significantly mitigates model bias while improving its performance., Comment: 8pages, 6figures, Submitted to TPAMI

Spatio-temporal forecasting is crucial in real-world dynamic systems, predicting future changes using historical data from diverse locations. Existing methods often prioritize the development of intricate neural networks to capture the complex dependencies of the data, yet their accuracy fails to show sustained improvement. Besides, these methods also overlook node heterogeneity, hindering customized prediction modules from handling diverse regional nodes effectively. In this paper, our goal is not to propose a new model but to present a novel low-rank adaptation framework as an off-the-shelf plugin for existing spatial-temporal prediction models, termed ST-LoRA, which alleviates the aforementioned problems through node-level adjustments. Specifically, we first tailor a node adaptive low-rank layer comprising multiple trainable low-rank matrices. Additionally, we devise a multi-layer residual fusion stacking module, injecting the low-rank adapters into predictor modules of various models. Across six real-world traffic datasets and six different types of spatio-temporal prediction models, our approach minimally increases the parameters and training time of the original models by less than 4%, still achieving consistent and sustained performance enhancement.

Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, most of these methods focus on a specific type of hallucination, e.g., entity or token errors, which limits their effectiveness in addressing various types of hallucinations exhibited in LLM outputs. To our best knowledge, in this paper we propose the first active learning framework to alleviate LLM hallucinations, reducing costly human annotations of hallucination needed. By measuring fine-grained hallucinations from errors in semantic frame, discourse and content verifiability in text summarization, we propose HAllucination Diversity-Aware Sampling (HADAS) to select diverse hallucinations for annotations in active learning for LLM finetuning. Extensive experiments on three datasets and different backbone models demonstrate advantages of our method in effectively and efficiently mitigating LLM hallucinations., Comment: Accepted to NAACL 2024