arXiv subjects

Wei Jia

Publications and source records attributed to Wei Jia.

At least 55 records · Page 3Linked to original sources

arXiv2024

LegalAgentBench: Evaluating LLM Agents in Legal Domain

With the increasing intelligence and autonomy of LLM agents, their potential applications in the legal domain are becoming increasingly apparent. However, existing general-domain benchmarks cannot fully capture the complexity and subtle nuances of real-world judicial cognition and decision-making. Therefore, we propose LegalAgentBench, a comprehensive benchmark specifically designed to evaluate LLM Agents in the Chinese legal domain. LegalAgentBench includes 17 corpora from real-world legal scenarios and provides 37 tools for interacting with external knowledge. We designed a scalable task construction framework and carefully annotated 300 tasks. These tasks span various types, including multi-hop reasoning and writing, and range across different difficulty levels, effectively reflecting the complexity of real-world legal scenarios. Moreover, beyond evaluating final success, LegalAgentBench incorporates keyword analysis during intermediate processes to calculate progress rates, enabling more fine-grained evaluation. We evaluated eight popular LLMs, highlighting the strengths, limitations, and potential areas for improvement of existing models and methods. LegalAgentBench sets a new benchmark for the practical application of LLMs in the legal domain, with its code and data available at \url{https://github.com/CSHaitao/LegalAgentBench}.

cs.CL↗

arXiv2024

Lightweight Multiplane Images Network for Real-Time Stereoscopic Conversion from Planar Video

With the rapid development of stereoscopic display technologies, especially glasses-free 3D screens, and virtual reality devices, stereoscopic conversion has become an important task to address the lack of high-quality stereoscopic image and video resources. Current stereoscopic conversion algorithms typically struggle to balance reconstruction performance and inference efficiency. This paper proposes a planar video real-time stereoscopic conversion network based on multi-plane images (MPI), which consists of a detail branch for generating MPI and a depth-semantic branch for perceiving depth information. Unlike models that depend on explicit depth map inputs, the proposed method employs a lightweight depth-semantic branch to extract depth-aware features implicitly. To optimize the lightweight branch, a heavy training but light inference strategy is adopted, which involves designing a coarse-to-fine auxiliary branch that is only used during the training stage. In addition, the proposed method simplifies the MPI rendering process for stereoscopic conversion scenarios to further accelerate the inference. Experimental results demonstrate that the proposed method can achieve comparable performance to some state-of-the-art (SOTA) models and support real-time inference at 2K resolution. Compared to the SOTA TMPI algorithm, the proposed method obtains similar subjective quality while achieving over $40\times$ inference acceleration.

cs.CV↗

arXiv2024

Unveiling Higher-Order Topology via Polarized Topological Charges

Higher-order topological phases (HOTPs) host exotic topological states that go beyond the traditional bulk-boundary correspondence. Up to now, there is still a lack of experimentally measurable momentum-space topological characterization for the HOTPs, which is not conducive to revealing the essential properties of these topological states and also restricts their detection in quantum simulation systems. Here, we propose a concept of polarized topological charges to characterize chiral-symmetric HOTPs in momentum space, which further facilitates a feasible experimental scheme to detect the HOTPs in $^{87}$Rb cold atomic system. Remarkably, our characterization theory not only shows that the second-order (third-order) topological phases are determined by a quarter (negative eighth) of the total polarized topological charges, but also reveals that the higher-order topological phase transitions are identified by the creation or annihilation of polarized topological charges. Particularly, these polarized topological charges can be measured by pseudospin structures of the systems. Due to theoretical simplicity and observational intuitiveness, this work shall advance the broad studies of the HOTPs in both theory and experiment.

cond-mat.mes-hall↗

arXiv2024

Manifold-based Incomplete Multi-view Clustering via Bi-Consistency Guidance

Incomplete multi-view clustering primarily focuses on dividing unlabeled data into corresponding categories with missing instances, and has received intensive attention due to its superiority in real applications. Considering the influence of incomplete data, the existing methods mostly attempt to recover data by adding extra terms. However, for the unsupervised methods, a simple recovery strategy will cause errors and outlying value accumulations, which will affect the performance of the methods. Broadly, the previous methods have not taken the effectiveness of recovered instances into consideration, or cannot flexibly balance the discrepancies between recovered data and original data. To address these problems, we propose a novel method termed Manifold-based Incomplete Multi-view clustering via Bi-consistency guidance (MIMB), which flexibly recovers incomplete data among various views, and attempts to achieve biconsistency guidance via reverse regularization. In particular, MIMB adds reconstruction terms to representation learning by recovering missing instances, which dynamically examines the latent consensus representation. Moreover, to preserve the consistency information among multiple views, MIMB implements a biconsistency guidance strategy with reverse regularization of the consensus representation and proposes a manifold embedding measure for exploring the hidden structure of the recovered data. Notably, MIMB aims to balance the importance of different views, and introduces an adaptive weight term for each view. Finally, an optimization algorithm with an alternating iteration optimization strategy is designed for final clustering. Extensive experimental results on 6 benchmark datasets are provided to confirm that MIMB can significantly obtain superior results as compared with several state-of-the-art baselines.

cs.LG↗

arXiv2024

Assessing the Longitudinal Impact of Environmental Chemical Mixtures on Children's Neurodevelopment: A Bayesian Approach

This manuscript presents a novel Bayesian varying coefficient quantile regression (BVCQR) model designed to assess the longitudinal effects of chemical exposure mixtures on children's neurodevelopment. Recognizing the complexity and high-dimensionality of environmental exposures, the proposed approach addresses critical gaps in existing research by offering a method that can manage the sparsity of data and provide interpretable results. The proposed BVCQR model estimates the effects of mixtures on neurodevelopmental outcomes at specific ages, leveraging a horseshoe prior for sparsity and utilizing a Bayesian method for uncertainty quantification. Our simulations demonstrate the model's robustness and effectiveness in handling high-dimensional data, offering significant improvements over traditional models. The model's application to the Health Outcomes and Measures of the Environment (HOME) Study further illustrates its utility in identifying significant chemical exposures affecting children's growth and development. The findings underscore the potential of BVCQR in environmental health research, providing a sophisticated tool for analyzing the longitudinal impact of complex chemical mixtures, with implications for future studies aimed at understanding and mitigating environmental risks to child health.

stat.AP↗

arXiv2024

Surface Chern-Simons theory for third-order topological insulators and superconductors

Three-dimensional 3rd-order topological insulators (TOTIs) and superconductors (TOTSCs), as the highestorder topological phases hosting zero corner modes in physical dimension, has sparked extensive research interest. However, such topological states have not been discovered in reality due to the lack of experimental schemes of realization. Here, we propose a novel surface Chern-Simons (CS) theory for 3rd-order topological phases, and show that the theory enables a feasible and systematic design of TOTIs and TOTSCs. We show that the emergence of zero Dirac (Majorana) corner modes is entirely captured by an emergent $\mathbb{Z}_{2}$ CS term that can be further characterized by a novel two-particle Wess-Zumino (WZ) term uncovered here in the surfaces of three-dimensional topological materials. Importantly, our proposed CS term characterization and two-particle WZ term mechanism provide a unique perspective to design TOTIs (TOTSCs) in terms of minimal ingredients, feasibly guiding the search for underlying materials, with promising candidates being discussed. This work shall advance both the theoretical and experimental research for highest-order topological matters.

cond-mat.mes-hall↗

arXiv2023

High-Ratio Compression for Machine-Generated Data

Machine-generated data is rapidly growing and poses challenges for data-intensive systems, especially as the growth of data outpaces the growth of storage space. To cope with the storage issue, compression plays a critical role in storage engines, particularly for data-intensive applications, where high compression ratios and efficient random access are essential. However, existing compression techniques tend to focus on general-purpose and data block approaches, but overlook the inherent structure of machine-generated data and hence result in low-compression ratios or limited lookup efficiency. To address these limitations, we introduce the Pattern-Based Compression (PBC) algorithm, which specifically targets patterns in machine-generated data to achieve Pareto-optimality in most cases. Unlike traditional data block-based methods, PBC compresses data on a per-record basis, facilitating rapid random access. Our experimental evaluation demonstrates that PBC, on average, achieves a compression ratio twice as high as state-of-the-art techniques while maintaining competitive compression and decompression speeds.We also integrate PBC to a production database system and achieve improvement on both comparison ratio and throughput.

cs.DB↗

arXiv2023

RPG-Palm: Realistic Pseudo-data Generation for Palmprint Recognition

Palmprint recently shows great potential in recognition applications as it is a privacy-friendly and stable biometric. However, the lack of large-scale public palmprint datasets limits further research and development of palmprint recognition. In this paper, we propose a novel realistic pseudo-palmprint generation (RPG) model to synthesize palmprints with massive identities. We first introduce a conditional modulation generator to improve the intra-class diversity. Then an identity-aware loss is proposed to ensure identity consistency against unpaired training. We further improve the Bézier palm creases generation strategy to guarantee identity independence. Extensive experimental results demonstrate that synthetic pretraining significantly boosts the recognition model performance. For example, our model improves the state-of-the-art BézierPalm by more than $5\%$ and $14\%$ in terms of TAR@FAR=1e-6 under the $1:1$ and $1:3$ Open-set protocol. When accessing only $10\%$ of the real training data, our method still outperforms ArcFace with $100\%$ real training data, indicating that we are closer to real-data-free palmprint recognition.

cs.CV↗

arXiv2023

Enhancing Dynamic Image Advertising with Vision-Language Pre-training

In the multimedia era, image is an effective medium in search advertising. Dynamic Image Advertising (DIA), a system that matches queries with ad images and generates multimodal ads, is introduced to improve user experience and ad revenue. The core of DIA is a query-image matching module performing ad image retrieval and relevance modeling. Current query-image matching suffers from limited and inconsistent data, and insufficient cross-modal interaction. Also, the separate optimization of retrieval and relevance models affects overall performance. To address this issue, we propose a vision-language framework consisting of two parts. First, we train a base model on large-scale image-text pairs to learn general multimodal representation. Then, we fine-tune the base model on advertising business data, unifying relevance modeling and retrieval through multi-objective learning. Our framework has been implemented in Baidu search advertising system "Phoneix Nest". Online evaluation shows that it improves cost per mille (CPM) and click-through rate (CTR) by 1.04% and 1.865%.

cs.IR↗

arXiv2023

Learning In-context Learning for Named Entity Recognition

Named entity recognition in real-world applications suffers from the diversity of entity types, the emergence of new entity types, and the lack of high-quality annotations. To address the above problems, this paper proposes an in-context learning-based NER approach, which can effectively inject in-context NER ability into PLMs and recognize entities of novel types on-the-fly using only a few demonstrative instances. Specifically, we model PLMs as a meta-function $\mathcal{ λ_ {\text{instruction, demonstrations, text}}. M}$, and a new entity extractor can be implicitly constructed by applying new instruction and demonstrations to PLMs, i.e., $\mathcal{ (λ. M) }$(instruction, demonstrations) $\to$ $\mathcal{F}$ where $\mathcal{F}$ will be a new entity extractor, i.e., $\mathcal{F}$: text $\to$ entities. To inject the above in-context NER ability into PLMs, we propose a meta-function pre-training algorithm, which pre-trains PLMs by comparing the (instruction, demonstration)-initialized extractor with a surrogate golden extractor. Experimental results on 4 few-shot NER datasets show that our method can effectively inject in-context NER ability into PLMs and significantly outperforms the PLMs+fine-tuning counterparts.

cs.CL↗

arXiv2023

Unified characterization for higher-order topological phase transitions

Higher-order topological phase transitions (HOTPTs) are associated with closing either the bulk energy gap (type-I) or boundary energy gap (type-II) without changing symmetry, and conventionally the both transitions are captured in real space and characterized separately. Here we propose a momentum-space topological characterization of the HOTPTs, which unifies the both types of topological transitions and enables a precise detection by quench dynamics. Our unified characterization is based on a novel correspondence between the mass domain walls on real-space boundaries and the higher-order band-inversion surfaces (BIS) which are characteristic interfaces in the momentum subspace. The topological transitions occur when momentum-space topological nodes, dubbed higher-order topological charges, cross the higher-order BISs after proper projection. Particularly, the bulk (boundary) gap closes when all (part of) topological charges cross the BISs, characterizing the type-I (type-II) HOTPTs. These distinct dynamical behaviours of higher-order topological charges can be feasibly measured from quench dynamics driven with control in experiments. Our work opens an avenue to characterize and detect the two types of HOTPTs within a unified framework, and shall advance the research in both theory and experiment.

cond-mat.mes-hall↗

arXiv2023

Dynamical detection of mean-field topological phases in an interacting Chern insulator

Interactions generically have important effects on the topological quantum phases. For a quantum anomalous Hall (QAH) insulator, the presence of interactions can qualitatively change the topological phase diagram which, however, is typically hard to measure in the experiment. Here we propose a novel scheme based on quench dynamics to detect the mean-field topological phase diagram of an interacting Chern insulator described by QAH-Hubbard model, with nontrivial dynamical quantum physics being uncovered. We focus on the dynamical properties of the system at a weak to intermediate Hubbard interaction which mainly induces a ferromagnetic order under the mean-field level. Remarkably, three characteristic times $t_s$, $t_c$, and $t^*$ are found in the quench dynamics. The first two capture the emergence of dynamical self-consistent particle density and dynamical topological phase transition respectively, while the last one gives a linear scaling time on the topological phase boundaries. A more interesting result is that $t_s>t^*>t_c$ ($t^*<t_s<t_c$) occurs in repulsive (attractive) interaction and the Chern number is determined by any two characteristic time scales when the system is quenched from an initial nearly fully polarized state to the topologically nontrivial regimes, showing a dynamical way to determine equilibrium mean-field topological phase diagram via the time scales. Experimentally,the measurement of $t_s$ is challenging while $t_c$ and $t^*$ can be directly readout by measuring the spin polarizations of four Dirac points and the time-dependent particle density, respectively. Our work reveals the novel interacting effects on the topological phases and shall promote the experimental observation.

cond-mat.str-el↗

arXiv2023

Universal Information Extraction as Unified Semantic Matching

The challenge of information extraction (IE) lies in the diversity of label schemas and the heterogeneity of structures. Traditional methods require task-specific model design and rely heavily on expensive supervision, making them difficult to generalize to new schemas. In this paper, we decouple IE into two basic abilities, structuring and conceptualizing, which are shared by different tasks and schemas. Based on this paradigm, we propose to universally model various IE tasks with Unified Semantic Matching (USM) framework, which introduces three unified token linking operations to model the abilities of structuring and conceptualizing. In this way, USM can jointly encode schema and input text, uniformly extract substructures in parallel, and controllably decode target structures on demand. Empirical evaluation on 4 IE tasks shows that the proposed method achieves state-of-the-art performance under the supervised experiments and shows strong generalization ability in zero/few-shot transfer settings.

cs.CL↗

arXiv2022

Convolutional Long Short-Term Memory (convLSTM) for Spatio-Temporal Forecastings of Saturations and Pressure in the SACROC Field

A machine learning architecture composed of convolutional long short-term memory (convLSTM) is developed to predict spatio-temporal parameters in the SACROC oil field, Texas, USA. The spatial parameters are recorded at the end of each month for 30 years (360 months), approximately 83% (300 months) of which is used for training and the rest 17% (60 months) is kept for testing. The samples for the convLSTM models are prepared by choosing ten consecutive frames as input and ten consecutive frames shifted forward by one frame as output. Individual models are trained for oil, gas, and water saturations, and pressure using the Nesterov accelerated adaptive moment estimation (Nadam) optimization algorithm. A workflow is provided to comprehend the entire process of data extraction, preprocessing, sample preparation, training, testing of machine learning models, and error analysis. Overall, the convLSTM for spatio-temporal prediction shows promising results in predicting spatio-temporal parameters in porous media.

eess.IV↗

arXiv2022

Geometric Synthesis: A Free lunch for Large-scale Palmprint Recognition Model Pretraining

Palmprints are private and stable information for biometric recognition. In the deep learning era, the development of palmprint recognition is limited by the lack of sufficient training data. In this paper, by observing that palmar creases are the key information to deep-learning-based palmprint recognition, we propose to synthesize training data by manipulating palmar creases. Concretely, we introduce an intuitive geometric model which represents palmar creases with parameterized Bézier curves. By randomly sampling Bézier parameters, we can synthesize massive training samples of diverse identities, which enables us to pretrain large-scale palmprint recognition models. Experimental results demonstrate that such synthetically pretrained models have a very strong generalization ability: they can be efficiently transferred to real datasets, leading to significant performance improvements on palmprint recognition. For example, under the open-set protocol, our method improves the strong ArcFace baseline by more than 10\% in terms of TAR@1e-6. And under the closed-set protocol, our method reduces the equal error rate (EER) by an order of magnitude.

cs.CV↗

arXiv2022

Depth Estimation by Combining Binocular Stereo and Monocular Structured-Light

It is well known that the passive stereo system cannot adapt well to weak texture objects, e.g., white walls. However, these weak texture targets are very common in indoor environments. In this paper, we present a novel stereo system, which consists of two cameras (an RGB camera and an IR camera) and an IR speckle projector. The RGB camera is used both for depth estimation and texture acquisition. The IR camera and the speckle projector can form a monocular structured-light (MSL) subsystem, while the two cameras can form a binocular stereo subsystem. The depth map generated by the MSL subsystem can provide external guidance for the stereo matching networks, which can improve the matching accuracy significantly. In order to verify the effectiveness of the proposed system, we build a prototype and collect a test dataset in indoor scenes. The evaluation results show that the Bad 2.0 error of the proposed system is 28.2% of the passive stereo system when the network RAFT is used. The dataset and trained models are available at https://github.com/YuhuaXu/MonoStereoFusion.

cs.CV↗

arXiv2022

Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems

Adversarial Examples (AEs) can deceive Deep Neural Networks (DNNs) and have received a lot of attention recently. However, majority of the research on AEs is in the digital domain and the adversarial patches are static, which is very different from many real-world DNN applications such as Traffic Sign Recognition (TSR) systems in autonomous vehicles. In TSR systems, object detectors use DNNs to process streaming video in real time. From the view of object detectors, the traffic sign`s position and quality of the video are continuously changing, rendering the digital AEs ineffective in the physical world. In this paper, we propose a systematic pipeline to generate robust physical AEs against real-world object detectors. Robustness is achieved in three ways. First, we simulate the in-vehicle cameras by extending the distribution of image transformations with the blur transformation and the resolution transformation. Second, we design the single and multiple bounding boxes filters to improve the efficiency of the perturbation training. Third, we consider four representative attack vectors, namely Hiding Attack, Appearance Attack, Non-Target Attack and Target Attack. We perform a comprehensive set of experiments under a variety of environmental conditions, and considering illuminations in sunny and cloudy weather as well as at night. The experimental results show that the physical AEs generated from our pipeline are effective and robust when attacking the YOLO v5 based TSR system. The attacks have good transferability and can deceive other state-of-the-art object detectors. We launched HA and NTA on a brand-new 2021 model vehicle. Both attacks are successful in fooling the TSR system, which could be a life-threatening case for autonomous vehicles. Finally, we discuss three defense mechanisms based on image preprocessing, AEs detection, and model enhancing.

cs.CV↗

arXiv2021

From Noise to Feature: Exploiting Intensity Distribution as a Novel Soft Biometric Trait for Finger Vein Recognition

Most finger vein feature extraction algorithms achieve satisfactory performance due to their texture representation abilities, despite simultaneously ignoring the intensity distribution that is formed by the finger tissue, and in some cases, processing it as background noise. In this paper, we exploit this kind of noise as a novel soft biometric trait for achieving better finger vein recognition performance. First, a detailed analysis of the finger vein imaging principle and the characteristics of the image are presented to show that the intensity distribution that is formed by the finger tissue in the background can be extracted as a soft biometric trait for recognition. Then, two finger vein background layer extraction algorithms and three soft biometric trait extraction algorithms are proposed for intensity distribution feature extraction. Finally, a hybrid matching strategy is proposed to solve the issue of dimension difference between the primary and soft biometric traits on the score level. A series of rigorous contrast experiments on three open-access databases demonstrates that our proposed method is feasible and effective for finger vein recognition.

cs.CV↗