arXiv subjects

Peng Wang

Publications and source records attributed to Peng Wang.

At least 505 records · Page 28Linked to original sources

arXiv2024

Repro Samples Method for High-dimensional Logistic Model

This paper presents a novel method to make statistical inferences for both the model support and regression coefficients in a high-dimensional logistic regression model. Our method is based on the repro samples framework, in which we conduct statistical inference by generating artificial samples mimicking the actual data-generating process. The proposed method has two major advantages. Firstly, for model support, we introduce the first method for constructing model confidence set in a high-dimensional setting and the proposed method only requires a weak signal strength assumption. Secondly, in terms of regression coefficients, we establish confidence sets for any group of linear combinations of regression coefficients. Our simulation results demonstrate that the proposed method produces valid and small model confidence sets and achieves better coverage for regression coefficients than the state-of-the-art debiasing methods. Additionally, we analyze single-cell RNA-seq data on the immune response. Besides identifying genes previously proved as relevant in the literature, our method also discovers a significant gene that has not been studied before, revealing a potential new direction in understanding cellular immune response mechanisms.

stat.ME↗

arXiv2024

CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning

This paper explores the problem of continual learning (CL) of vision-language models (VLMs) in open domains, where the models need to perform continual updating and inference on a streaming of datasets from diverse seen and unseen domains with novel classes. Such a capability is crucial for various applications in open environments, e.g., AI assistants, autonomous driving systems, and robotics. Current CL studies mostly focus on closed-set scenarios in a single domain with known classes. Large pre-trained VLMs like CLIP have demonstrated superior zero-shot recognition ability, and a number of recent studies leverage this ability to mitigate catastrophic forgetting in CL, but they focus on closed-set CL in a single domain dataset. Open-domain CL of large VLMs is significantly more challenging due to 1) large class correlations and domain gaps across the datasets and 2) the forgetting of zero-shot knowledge in the pre-trained VLMs in addition to the knowledge learned from the newly adapted datasets. In this work we introduce a novel approach, termed CoLeCLIP, that learns an open-domain CL model based on CLIP. It addresses these challenges by a joint learning of a set of task prompts and a cross-domain class vocabulary. Extensive experiments on 11 domain datasets show that CoLeCLIP outperforms state-of-the-art methods for open-domain CL under both task- and class-incremental learning settings.

cs.CV↗

arXiv2024

Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning

In this study, we address the intricate challenge of multi-task dense prediction, encompassing tasks such as semantic segmentation, depth estimation, and surface normal estimation, particularly when dealing with partially annotated data (MTPSL). The complexity arises from the absence of complete task labels for each training image. Given the inter-related nature of these pixel-wise dense tasks, our focus is on mining and capturing cross-task relationships. Existing solutions typically rely on learning global image representations for global cross-task image matching, imposing constraints that, unfortunately, sacrifice the finer structures within the images. Attempting local matching as a remedy faces hurdles due to the lack of precise region supervision, making local alignment a challenging endeavor. The introduction of Segment Anything Model (SAM) sheds light on addressing local alignment challenges by providing free and high-quality solutions for region detection. Leveraging SAM-detected regions, the subsequent challenge lies in aligning the representations within these regions. Diverging from conventional methods that directly learn a monolithic image representation, our proposal involves modeling region-wise representations using Gaussian Distributions. Aligning these distributions between corresponding regions from different tasks imparts higher flexibility and capacity to capture intra-region structures, accommodating a broader range of tasks. This innovative approach significantly enhances our ability to effectively capture cross-task relationships, resulting in improved overall performance in partially supervised multi-task dense prediction scenarios. Extensive experiments conducted on two widely used benchmarks underscore the superior effectiveness of our proposed method, showcasing state-of-the-art performance even when compared to fully supervised methods.

cs.CV↗

arXiv2024

Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models

Zero-shot novel view synthesis (NVS) from a single image is an essential problem in 3D object understanding. While recent approaches that leverage pre-trained generative models can synthesize high-quality novel views from in-the-wild inputs, they still struggle to maintain 3D consistency across different views. In this paper, we present Consistent-1-to-3, which is a generative framework that significantly mitigates this issue. Specifically, we decompose the NVS task into two stages: (i) transforming observed regions to a novel view, and (ii) hallucinating unseen regions. We design a scene representation transformer and view-conditioned diffusion model for performing these two stages respectively. Inside the models, to enforce 3D consistency, we propose to employ epipolor-guided attention to incorporate geometry constraints, and multi-view attention to better aggregate multi-view information. Finally, we design a hierarchy generation paradigm to generate long sequences of consistent views, allowing a full 360-degree observation of the provided object image. Qualitative and quantitative evaluation over multiple datasets demonstrates the effectiveness of the proposed mechanisms against state-of-the-art approaches. Our project page is at https://jianglongye.com/consistent123/

cs.CV↗

arXiv2024

Open-Vocabulary Video Anomaly Detection

Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. However, current approaches are inherently limited to a closed-set setting and may struggle in open-world applications where there can be anomaly categories in the test data unseen during training. A few recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to detect unseen anomalies given seen anomalies and normal videos. However, such a setting focuses on predicting frame anomaly scores, having no ability to recognize the specific categories of anomalies, despite the fact that this ability is essential for building more informed video surveillance systems. This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pre-trained large models to detect and categorize seen and unseen anomalies. To this end, we propose a model that decouples OVVAD into two mutually complementary tasks -- class-agnostic detection and class-specific classification -- and jointly optimizes both tasks. Particularly, we devise a semantic knowledge injection module to introduce semantic knowledge from large language models for the detection task, and design a novel anomaly synthesis module to generate pseudo unseen anomaly videos with the help of large vision generation models for the classification task. These semantic knowledge and synthesis anomalies substantially extend our model's capability in detecting and categorizing a variety of seen and unseen anomalies. Extensive experiments on three widely-used benchmarks demonstrate our model achieves state-of-the-art performance on OVVAD task.

cs.CV↗

arXiv2024

Nonlinear Stability of Black Holes with a Stable Light Ring

Recently, ultracompact objects have been found to be susceptible to a new nonlinear instability, known as the light-ring instability, triggered by stable light rings. This discovery raises concerns about the viability of these objects as alternatives to black holes. In this work, we investigate the presence of the light-ring instability in scalarized Reissner-Nordström black holes, which have been previously shown to admit stable light rings. We employ fully nonlinear numerical evolutions of both scalarized black holes with and without stable light rings, perturbing them initially with spherically symmetric scalar perturbations. Our simulations demonstrate the long-term stability of these scalarized black holes, suggesting that the presence of a stable light ring may not necessarily induce the light-ring instability.

gr-qc↗

arXiv2024

Variational quantum eigensolver with linear depth problem-inspired ansatz for solving portfolio optimization in finance

Great efforts have been dedicated in recent years to explore practical applications for noisy intermediate-scale quantum (NISQ) computers, which is a fundamental and challenging problem in quantum computing. As one of the most promising methods, the variational quantum eigensolver (VQE) has been extensively studied. In this paper, VQE is applied to solve portfolio optimization problems in finance by designing two hardware-efficient Dicke state ansatze that reach a maximum of 2n two-qubit gate depth and n^2/4 parameters, with n being the number of qubits used. Both ansatze are partitioning-friendly, allowing for the proposal of a highly scalable quantum/classical hybrid distributed computing (HDC) scheme. Combining simultaneous sampling, problem-specific measurement error mitigation, and fragment reuse techniques, we successfully implement the HDC experiments on the superconducting quantum computer Wu Kong with up to 55 qubits. The simulation and experimental results illustrate that the restricted expressibility of the ansatze, induced by the small number of parameters and limited entanglement, is advantageous for solving classical optimization problems with the cost function of the conditional value-at-risk (CVaR) for the NISQ era and beyond. Furthermore, the HDC scheme shows great potential for achieving quantum advantage in the NISQ era. We hope that the heuristic idea presented in this paper can motivate fruitful investigations in current and future quantum computing paradigms.

quant-ph↗

arXiv2024

Dcl-Net: Dual Contrastive Learning Network for Semi-Supervised Multi-Organ Segmentation

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

cs.CV↗

arXiv2024

The origin of lopsided satellite galaxy distribution around isolated systems in MillenniumTNG

Dwarf satellites in galaxy groups are distributed in an anisotropic and asymmetric manner, which is called the ``lopsided satellite distribution''. This lopsided signal has been observed not only in galaxy pairs but also in isolated systems. However, the physical origin of the lopsided signal in isolated systems is still unknown. In this work, we investigate this in the state-of-the-art hydrodynamical simulation of the MillenniumTNG Project by tracing each system back to high redshift. We find that the lopsided signal is dominated by satellites located in the outer regions of the halo and is also dominated by recently accreted satellites. The lopsided signal originates from the anisotropic accretion of galaxies from the surrounding large-scale structure and that, after accretion, the nonlinear evolution of satellites inside the dark-matter halo weakens the lopsidedness. The signal decreases as cosmic time passes because of a competition between anisotropic accretion and internal evolution within dark matter halos. Our findings provide a useful perspective for the study of galaxy evolution, especially for the origin of the spatial satellite galaxy distributions.

astro-ph.CO↗

arXiv2024

Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model

Video anomaly detection (VAD) has been paid increasing attention due to its potential applications, its current dominant tasks focus on online detecting anomalies% at the frame level, which can be roughly interpreted as the binary or multiple event classification. However, such a setup that builds relationships between complicated anomalous events and single labels, e.g., ``vandalism'', is superficial, since single labels are deficient to characterize anomalous events. In reality, users tend to search a specific video rather than a series of approximate videos. Therefore, retrieving anomalous events using detailed descriptions is practical and positive but few researches focus on this. In this context, we propose a novel task called Video Anomaly Retrieval (VAR), which aims to pragmatically retrieve relevant anomalous videos by cross-modalities, e.g., language descriptions and synchronous audios. Unlike the current video retrieval where videos are assumed to be temporally well-trimmed with short duration, VAR is devised to retrieve long untrimmed videos which may be partially relevant to the given query. To achieve this, we present two large-scale VAR benchmarks, UCFCrime-AR and XDViolence-AR, constructed on top of prevalent anomaly datasets. Meanwhile, we design a model called Anomaly-Led Alignment Network (ALAN) for VAR. In ALAN, we propose an anomaly-led sampling to focus on key segments in long untrimmed videos. Then, we introduce an efficient pretext task to enhance semantic associations between video-text fine-grained representations. Besides, we leverage two complementary alignments to further match cross-modal contents. Experimental results on two benchmarks reveal the challenges of VAR task and also demonstrate the advantages of our tailored method. Captions are publicly released at https://github.com/Roc-Ng/VAR.

cs.CV↗

arXiv2024

GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks

Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse fields, especially for open-ended tasks. While the idea is less explored in the graph domain, despite the availability of numerous powerful graph models (GMs), they are restricted to tasks in a pre-defined form. Although several methods applying LLMs to graphs have been proposed, they fail to simultaneously handle the pre-defined and open-ended tasks, with LLM as a node feature enhancer or as a standalone predictor. To break this dilemma, we propose to bridge the pretrained GM and LLM by a Translator, named GraphTranslator, aiming to leverage GM to handle the pre-defined tasks effectively and utilize the extended interface of LLMs to offer various open-ended tasks for GM. To train such Translator, we propose a Producer capable of constructing the graph-text alignment data along node information, neighbor information and model information. By translating node representation into tokens, GraphTranslator empowers an LLM to make predictions based on language instructions, providing a unified perspective for both pre-defined and open-ended tasks. Extensive results demonstrate the effectiveness of our proposed GraphTranslator on zero-shot node classification. The graph question answering experiments reveal our GraphTranslator potential across a broad spectrum of open-ended tasks through language instructions. Our code is available at: https://github.com/alibaba/GraphTranslator.

cs.AI↗

arXiv2024

USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields

Neural Radiance Fields (NeRF) has received much attention recently due to its impressive capability to represent 3D scene and synthesize novel view images. Existing works usually assume that the input images are captured by a global shutter camera. Thus, rolling shutter (RS) images cannot be trivially applied to an off-the-shelf NeRF algorithm for novel view synthesis. Rolling shutter effect would also affect the accuracy of the camera pose estimation (e.g. via COLMAP), which further prevents the success of NeRF algorithm with RS images. In this paper, we propose Unrolling Shutter Bundle Adjusted Neural Radiance Fields (USB-NeRF). USB-NeRF is able to correct rolling shutter distortions and recover accurate camera motion trajectory simultaneously under the framework of NeRF, by modeling the physical image formation process of a RS camera. Experimental results demonstrate that USB-NeRF achieves better performance compared to prior works, in terms of RS effect removal, novel view image synthesis as well as camera motion estimation. Furthermore, our algorithm can also be used to recover high-fidelity high frame-rate global shutter video from a sequence of RS images.

cs.CV↗

arXiv2024

CoGenT: A Content-oriented Generative-hit Framework for Content Delivery Networks

The service provided by content delivery networks (CDNs) may overlook content locality, leaving room for potential performance improvement. In this study, we explore the feasibility of leveraging generated data as a replacement for fetching data in missing scenarios based on content locality. Due to sufficient local computing resources and reliable generation efficiency, we propose a content-oriented generative-hit framework (CoGenT) for CDNs. CoGenT utilizes idle computing resources on edge nodes to generate requested data based on similar or related cached data to achieve hits. Our implementation in a real-world system demonstrates that CoGenT reduces the average access latency by half. Additionally, experiments conducted on a simulator also confirm that CoGenT can enhance existing caching algorithms, resulting in reduced latency and bandwidth usage.

cs.DC↗

arXiv2024

Observation of the In-plane Anomalous Hall Effect induced by Octupole in Magnetization Space

The Anomalous Hall Effect (AHE) manifests as a transverse voltage proportional to magnetization in ferromagnetic materials under the application of a charge current, being an indispensable tool for probing magnetism, especially in nanoscale devices. However, the AHE primarily sensitizes to out-of-plane magnetization, thereby hindering its capacity to discern the in-plane magnetization, a characteristic prevalent in ferromagnetic films. Here we challenge this conventional understanding by demonstrating the in-plane magnetization-induced AHE in iron and nickel, two ubiquitous ferromagnets. This observation of the in-plane AHE is remarkable as it contradicts existing theories that forbid such phenomena in cubic crystal systems. We trace the origin of this unanticipated phenomenon to a hitherto unconsidered octupole of the anomalous Hall conductivity in the magnetization space, a mechanism we propose could enable the detection of in-plane AHE in a wide range of ferromagnetic materials. This work realizes the in-plane AHE in common ferromagnets by exploiting the anomalous Hall conductivity octupole, revealing a new physical origin of the AHE and promising to revolutionize the design of magnetic devices and sensors.

cond-mat.mtrl-sci↗

arXiv2024

Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction

The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (\textsc{TableIE}) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I$^2$CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples.

cs.CL↗

arXiv2024

TransGPT: Multi-modal Generative Pre-trained Transformer for Transportation

Natural language processing (NLP) is a key component of intelligent transportation systems (ITS), but it faces many challenges in the transportation domain, such as domain-specific knowledge and data, and multi-modal inputs and outputs. This paper presents TransGPT, a novel (multi-modal) large language model for the transportation domain, which consists of two independent variants: TransGPT-SM for single-modal data and TransGPT-MM for multi-modal data. TransGPT-SM is finetuned on a single-modal Transportation dataset (STD) that contains textual data from various sources in the transportation domain. TransGPT-MM is finetuned on a multi-modal Transportation dataset (MTD) that we manually collected from three areas of the transportation domain: driving tests, traffic signs, and landmarks. We evaluate TransGPT on several benchmark datasets for different tasks in the transportation domain, and show that it outperforms baseline models on most tasks. We also showcase the potential applications of TransGPT for traffic analysis and modeling, such as generating synthetic traffic scenarios, explaining traffic phenomena, answering traffic-related questions, providing traffic recommendations, and generating traffic reports. This work advances the state-of-the-art of NLP in the transportation domain and provides a useful tool for ITS researchers and practitioners.

cs.CL↗

arXiv2024

Superconductivity in freestanding infinite-layer nickelate membranes

The observation of superconductivity in infinite-layer nickelates has attracted significant attention due to its potential as a new platform for exploring high $ \mathrm{\textit{T}}_{c} $ superconductivity. However, thus far, superconductivity has only been observed in epitaxial thin films, which limits the manipulation capabilities and modulation methods compared to two-dimensional exfoliated materials. Given the exceptionally giant strain tunability and stacking capability of freestanding membranes, separating superconducting nickelates from the as-grown substrate is a novel way to engineer the superconductivity and uncover the underlying physics. Herein, we report the synthesis of the superconducting freestanding $ \mathrm{La}_{0.8}\mathrm{Sr}_{0.2}\mathrm{Ni}\mathrm{O}_{2} $ membranes ($ \mathrm{\textit{T}}_{c}\mathrm{=}\mathrm{10.9}\;\mathrm{K} $), emphasizing the crucial roles of the interface engineering in the precursor phase film growth and the quick transfer process in achieving superconductivity. Our work offers a new versatile platform for investigating the superconductivity in nickelates, such as the pairing symmetry via constructing Josephson tunneling junctions and higher $ \mathrm{\textit{T}}_{c} $ values via high-pressure experiments.

cond-mat.supr-con↗

arXiv2024

VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis

The Gaussian reconstruction kernels have been proposed by Westover (1990) and studied by the computer graphics community back in the 90s, which gives an alternative representation of object 3D geometry from meshes and point clouds. On the other hand, current state-of-the-art (SoTA) differentiable renderers, Liu et al. (2019), use rasterization to collect triangles or points on each image pixel and blend them based on the viewing distance. In this paper, we propose VoGE, which utilizes the volumetric Gaussian reconstruction kernels as geometric primitives. The VoGE rendering pipeline uses ray tracing to capture the nearest primitives and blends them as mixtures based on their volume density distributions along the rays. To efficiently render via VoGE, we propose an approximate closeform solution for the volume density aggregation and a coarse-to-fine rendering strategy. Finally, we provide a CUDA implementation of VoGE, which enables real-time level rendering with a competitive rendering speed in comparison to PyTorch3D. Quantitative and qualitative experiment results show VoGE outperforms SoTA counterparts when applied to various vision tasks, e.g., object pose estimation, shape/texture fitting, and occlusion reasoning. The VoGE library and demos are available at: https://github.com/Angtian/VoGE.

cs.GR↗