arXiv subjects

Jun Xu

Publications and source records attributed to Jun Xu.

At least 235 records · Page 13Linked to original sources

arXiv2024

Energy estimation of small-scale jets from the quiet-Sun region

Context. Solar jets play a role in the coronal heating and the supply of solar wind. Aims. This study calculated the energies of 23 small-scale jets emerging from a quiet-Sun region to investigate their contributions for coronal heating. Conclusions. Our observations suggest that although these jets cannot provide sufficient energy for the heating of the whole quiet-Sun coronal region, they are likely to account for a significant portion of the energy demand in the local regions where the jets occur.

astro-ph.SR↗

arXiv2024

OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning

Redundancy is a persistent challenge in Capsule Networks (CapsNet),leading to high computational costs and parameter counts. Although previous works have introduced pruning after the initial capsule layer, dynamic routing's fully connected nature and non-orthogonal weight matrices reintroduce redundancy in deeper layers. Besides, dynamic routing requires iterating to converge, further increasing computational demands. In this paper, we propose an Orthogonal Capsule Network (OrthCaps) to reduce redundancy, improve routing performance and decrease parameter counts. Firstly, an efficient pruned capsule layer is introduced to discard redundant capsules. Secondly, dynamic routing is replaced with orthogonal sparse attention routing, eliminating the need for iterations and fully connected structures. Lastly, weight matrices during routing are orthogonalized to sustain low capsule similarity, which is the first approach to introduce orthogonality into CapsNet as far as we know. Our experiments on baseline datasets affirm the efficiency and robustness of OrthCaps in classification tasks, in which ablation studies validate the criticality of each component. Remarkably, OrthCaps-Shallow outperforms other Capsule Network benchmarks on four datasets, utilizing only 110k parameters, which is a mere 1.25% of a standard Capsule Network's total. To the best of our knowledge, it achieves the smallest parameter count among existing Capsule Networks. Similarly, OrthCaps-Deep demonstrates competitive performance across four datasets, utilizing only 1.2% of the parameters required by its counterparts.

cs.CV↗

arXiv2024

Lattice piecewise affine approximation of explicit model predictive control with application to satellite attitude control

Satellite attitude cotrol is a crucial part of aerospace technology, and model predictive control(MPC) is one of the most promising controllers in this area, which will be less effective if real-time online optimization can not be achieved. Explicit MPC converts the online calculation into a table lookup process, however the solution is difficult to obtain if the system dimension is high or the constraints are complex. The lattice piecewise affine(PWA) function was used to represent the control law of explicit MPC, although the online calculation complexity is reduced, the offline calculation is still prohibitive for complex problems. In this paper, we use the sample points in the feasible region with their corresponding affine functions to construct the lattice PWA approximation of the optimal MPC controller designed for satellite attitude control. The asymptotic stability of satellite attitude control system under lattice PWA approximation has been proven, and simulations are executed to verify that the proposed method can achieve almost the same performance as linear online MPC with much lower online computational complexity and use less fuel than LQR method.

eess.SY↗

arXiv2024

Multi-agent Reinforcement Traffic Signal Control based on Interpretable Influence Mechanism and Biased ReLU Approximation

Traffic signal control is important in intelligent transportation system, of which cooperative control is difficult to realize but yet vital. Many methods model multi-intersection traffic networks as grids and address the problem using multi-agent reinforcement learning (RL). Despite these existing studies, there is an opportunity to further enhance our understanding of the connectivity and globality of the traffic networks by capturing the spatiotemporal traffic information with efficient neural networks in deep RL. In this paper, we propose a novel multi-agent actor-critic framework based on an interpretable influence mechanism with a centralized learning and decentralized execution method. Specifically, we first construct an actor-critic framework, for which the piecewise linear neural network (PWLNN), named biased ReLU (BReLU), is used as the function approximator to obtain a more accurate and theoretically grounded approximation. Finally, our proposed framework is validated on two synthetic traffic networks to coordinate signal control between intersections, achieving lower traffic delays across the entire traffic network compared to state-of-the-art (SOTA) performance.

cs.MA↗

arXiv2024

Comparing pion production in transport simulations of heavy-ion collisions at $270A$ MeV under controlled conditions

Within the TMEP, we present a detailed study of the performance of different transport models in Sn+Sn collisions at $270A$ MeV, and put particular emphasis on the production of pions and $Δ$ resonances, which have been used as probes of the nuclear symmetry energy. We prescribe a common and rather simple physics model, and follow in detail the results of 4 BUU models and 6 QMD models. The nucleonic evolution of the collision and the nucleonic observables in these codes do not completely converge, but the differences among the codes can be understood as being due to several reasons: the basic differences between BUU and QMD models in the representation of the phase-space distributions, computational differences in the mean-field evaluation, and differences in the adopted strategies for the Pauli blocking in the collision integrals. For pionic observables, we find that a higher maximum density leads to an enhanced pion yield and a reduced $π^-/π^+$ yield ratio, while a more effective Pauli blocking generally leads to a slightly suppressed pion yield and an enhanced $π^-/π^+$ yield ratio. We specifically investigate the effect of the Coulomb force, and find that it increases the total $π^-/π^+$ yield ratio but reduces the ratio at high pion energies, although differences in its implementations do not have a dominating role in the differences among the codes. Taking into account only the results of codes that strictly follow the homework specifications, we find a convergence of the codes in the final charged pion yield ratio to a $1σ$ deviation of about $5\%$. However, the uncertainty is expected to be reduced to about $1.6\%$ if the same or similar strategies and ingredients, i.e., an improved Pauli blocking and calculation of the non-linear term in the mean-field potential, are similarly used in all codes.

nucl-th↗

arXiv2024

ChatUIE: Exploring Chat-based Unified Information Extraction using Large Language Models

Recent advancements in large language models have shown impressive performance in general chat. However, their domain-specific capabilities, particularly in information extraction, have certain limitations. Extracting structured information from natural language that deviates from known schemas or instructions has proven challenging for previous prompt-based methods. This motivated us to explore domain-specific modeling in chat-based language models as a solution for extracting structured information from natural language. In this paper, we present ChatUIE, an innovative unified information extraction framework built upon ChatGLM. Simultaneously, reinforcement learning is employed to improve and align various tasks that involve confusing and limited samples. Furthermore, we integrate generation constraints to address the issue of generating elements that are not present in the input. Our experimental results demonstrate that ChatUIE can significantly improve the performance of information extraction with a slight decrease in chatting ability.

cs.CL↗

arXiv2024

Logic Rules as Explanations for Legal Case Retrieval

In this paper, we address the issue of using logic rules to explain the results from legal case retrieval. The task is critical to legal case retrieval because the users (e.g., lawyers or judges) are highly specialized and require the system to provide logical, faithful, and interpretable explanations before making legal decisions. Recently, research efforts have been made to learn explainable legal case retrieval models. However, these methods usually select rationales (key sentences) from the legal cases as explanations, failing to provide faithful and logically correct explanations. In this paper, we propose Neural-Symbolic enhanced Legal Case Retrieval (NS-LCR), a framework that explicitly conducts reasoning on the matching of legal cases through learning case-level and law-level logic rules. The learned rules are then integrated into the retrieval process in a neuro-symbolic manner. Benefiting from the logic and interpretable nature of the logic rules, NS-LCR is equipped with built-in faithful explainability. We also show that NS-LCR is a model-agnostic framework that can be plugged in for multiple legal retrieval models. To showcase NS-LCR's superiority, we enhance existing benchmarks by adding manually annotated logic rules and introducing a novel explainability metric using Large Language Models (LLMs). Our comprehensive experiments reveal NS-LCR's effectiveness for ranking, alongside its proficiency in delivering reliable explanations for legal case retrieval.

cs.IR↗

arXiv2024

On the Decision-Making Abilities in Role-Playing using Large Language Models

Large language models (LLMs) are now increasingly utilized for role-playing tasks, especially in impersonating domain-specific experts, primarily through role-playing prompts. When interacting in real-world scenarios, the decision-making abilities of a role significantly shape its behavioral patterns. In this paper, we concentrate on evaluating the decision-making abilities of LLMs post role-playing thereby validating the efficacy of role-playing. Our goal is to provide metrics and guidance for enhancing the decision-making abilities of LLMs in role-playing tasks. Specifically, we first use LLMs to generate virtual role descriptions corresponding to the 16 personality types of Myers-Briggs Type Indicator (abbreviated as MBTI) representing a segmentation of the population. Then we design specific quantitative operations to evaluate the decision-making abilities of LLMs post role-playing from four aspects: adaptability, exploration$\&$exploitation trade-off ability, reasoning ability, and safety. Finally, we analyze the association between the performance of decision-making and the corresponding MBTI types through GPT-4. Extensive experiments demonstrate stable differences in the four aspects of decision-making abilities across distinct roles, signifying a robust correlation between decision-making abilities and the roles emulated by LLMs. These results underscore that LLMs can effectively impersonate varied roles while embodying their genuine sociological characteristics.

cs.CL↗

arXiv2024

A Simple yet Effective Network based on Vision Transformer for Camouflaged Object and Salient Object Detection

Camouflaged object detection (COD) and salient object detection (SOD) are two distinct yet closely-related computer vision tasks widely studied during the past decades. Though sharing the same purpose of segmenting an image into binary foreground and background regions, their distinction lies in the fact that COD focuses on concealed objects hidden in the image, while SOD concentrates on the most prominent objects in the image. Previous works achieved good performance by stacking various hand-designed modules and multi-scale features. However, these carefully-designed complex networks often performed well on one task but not on another. In this work, we propose a simple yet effective network (SENet) based on vision Transformer (ViT), by employing a simple design of an asymmetric ViT-based encoder-decoder structure, we yield competitive results on both tasks, exhibiting greater versatility than meticulously crafted ones. Furthermore, to enhance the Transformer's ability to model local information, which is important for pixel-level binary segmentation tasks, we propose a local information capture module (LICM). We also propose a dynamic weighted loss (DW loss) based on Binary Cross-Entropy (BCE) and Intersection over Union (IoU) loss, which guides the network to pay more attention to those smaller and more difficult-to-find target objects according to their size. Moreover, we explore the issue of joint training of SOD and COD, and propose a preliminary solution to the conflict in joint training, further improving the performance of SOD. Extensive experiments on multiple benchmark datasets demonstrate the effectiveness of our method. The code is available at https://github.com/linuxsino/SENet.

cs.CV↗

arXiv2024

Transport properties of asymmetric nuclear matter in the spinodal region

We have studied the shear and bulk viscosities of asymmetric nuclear matter in the mechanical and chemical instability region based on IBUU transport simulations in a box system. The Green-Kubo method is used to calculate these viscosities with a prepared dynamically equilibrated nuclear system with hot clusters. While the behavior of the shear viscosity is largely affected by energy-dependent nucleon-nucleon cross sections, the bulk viscosity increases significantly in the presence of nuclear clusters compared to that in uniform nuclear matter. Increasing isospin asymmetry generally increases both viscosities, while their behaviors are qualitatively modified once the isospin asymmetry is large enough to affect significantly the spinodal region. Our calculation shows that the bulk viscosity is more sensitive to the nuclear clustering than the shear viscosity, and is thus a robust quantity related to the phase diagram of asymmetric nuclear matter.

nucl-th↗

arXiv2024

FairSync: Ensuring Amortized Group Exposure in Distributed Recommendation Retrieval

In pursuit of fairness and balanced development, recommender systems (RS) often prioritize group fairness, ensuring that specific groups maintain a minimum level of exposure over a given period. For example, RS platforms aim to ensure adequate exposure for new providers or specific categories of items according to their needs. Modern industry RS usually adopts a two-stage pipeline: stage-1 (retrieval stage) retrieves hundreds of candidates from millions of items distributed across various servers, and stage-2 (ranking stage) focuses on presenting a small-size but accurate selection from items chosen in stage-1. Existing efforts for ensuring amortized group exposures focus on stage-2, however, stage-1 is also critical for the task. Without a high-quality set of candidates, the stage-2 ranker cannot ensure the required exposure of groups. Previous fairness-aware works designed for stage-2 typically require accessing and traversing all items. In stage-1, however, millions of items are distributively stored in servers, making it infeasible to traverse all of them. How to ensure group exposures in the distributed retrieval process is a challenging question. To address this issue, we introduce a model named FairSync, which transforms the problem into a constrained distributed optimization problem. Specifically, FairSync resolves the issue by moving it to the dual space, where a central node aggregates historical fairness data into a vector and distributes it to all servers. To trade off the efficiency and accuracy, the gradient descent technique is used to periodically update the parameter of the dual vector. The experiment results on two public recommender retrieval datasets showcased that FairSync outperformed all the baselines, achieving the desired minimum level of exposures while maintaining a high level of retrieval accuracy.

cs.IR↗

arXiv2024

User Behavior Simulation with Large Language Model based Agents

Simulating high quality user behavior data has always been a fundamental problem in human-centered applications, where the major difficulty originates from the intricate mechanism of human decision process. Recently, substantial evidences have suggested that by learning huge amounts of web knowledge, large language models (LLMs) can achieve human-like intelligence. We believe these models can provide significant opportunities to more believable user behavior simulation. To inspire such direction, we propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans. Concerning potential applications, we simulate and study two social phenomenons including (1) information cocoons and (2) user conformity behaviors. This research provides novel simulation paradigms for human-centered applications.

cs.IR↗

arXiv2024

Sparsity via Sparse Group $k$-max Regularization

For the linear inverse problem with sparsity constraints, the $l_0$ regularized problem is NP-hard, and existing approaches either utilize greedy algorithms to find almost-optimal solutions or to approximate the $l_0$ regularization with its convex counterparts. In this paper, we propose a novel and concise regularization, namely the sparse group $k$-max regularization, which can not only simultaneously enhance the group-wise and in-group sparsity, but also casts no additional restraints on the magnitude of variables in each group, which is especially important for variables at different scales, so that it approximate the $l_0$ norm more closely. We also establish an iterative soft thresholding algorithm with local optimality conditions and complexity analysis provided. Through numerical experiments on both synthetic and real-world datasets, we verify the effectiveness and flexibility of the proposed method.

cs.LG↗

arXiv2024

List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation

The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List-aware retrieval aims to capture the list-level contextual features to return a better list, mainly including reranking and truncation. Reranking finely re-scores the documents in the list. Truncation dynamically determines the cut-off point of the ranked list to achieve the trade-off between overall relevance and avoiding misinformation from irrelevant documents. Previous studies treat them as two separate tasks and model them separately. However, the separation is not optimal. First, it is hard to share the contextual information of the ranking list between the two tasks. Second, the separate pipeline usually meets the error accumulation problem, where the small error from the reranking stage can largely affect the truncation stage. To solve these problems, we propose a Reranking-Truncation joint model (GenRT) that can perform the two tasks concurrently. GenRT integrates reranking and truncation via generative paradigm based on encoder-decoder architecture. We also design the novel loss functions for joint optimization to make the model learn both tasks. Sharing parameters by the joint model is conducive to making full use of the common modeling information of the two tasks. Besides, the two tasks are performed concurrently and co-optimized to solve the error accumulation problem between separate stages. Experiments on public learning-to-rank benchmarks and open-domain Q\&A tasks show that our method achieves SOTA performance on both reranking and truncation tasks for web search and retrieval-augmented LLMs.

cs.IR↗

arXiv2024

Three-dimensional QCD phase diagram in the pNJL model

Based on the three-flavor Polyakov-looped Nambu$-$Jona-Lasinio (pNJL) model, we have studied the structure of the three-dimensional QCD phase diagram with respect to the temperature, the baryon chemical potential, and the isospin chemical potential, by investigating the interplay among the chiral quark condensate, the pion condensate, and the Polyakov loop. While the pNJL model leads to qualitatively similar structure of the normal quark phase, the pion superfluid phase, and the Sarma phase as well as their phase boundaries, when compared to the NJL model, the inclusion of the Polyakov loop enlarges considerably the areas of the pion superfluid phase and the Sarma phase, and leads to critical end points at higher temperatures. With the contribution of the gluon dynamics effectively included, the present study is expected to give a more reliable prediction of the three-dimensional QCD phase diagram compared to that in the NJL model.

hep-ph↗

arXiv2024

AI in ESG for Financial Institutions: An Industrial Survey

The burgeoning integration of Artificial Intelligence (AI) into Environmental, Social, and Governance (ESG) initiatives within the financial sector represents a paradigm shift towards more sus-tainable and equitable financial practices. This paper surveys the industrial landscape to delineate the necessity and impact of AI in bolstering ESG frameworks. With the advent of stringent regulatory requirements and heightened stakeholder awareness, financial institutions (FIs) are increasingly compelled to adopt ESG criteria. AI emerges as a pivotal tool in navigating the complex in-terplay of financial activities and sustainability goals. Our survey categorizes AI applications across three main pillars of ESG, illustrating how AI enhances analytical capabilities, risk assessment, customer engagement, reporting accuracy and more. Further, we delve into the critical con-siderations surrounding the use of data and the development of models, underscoring the importance of data quality, privacy, and model robustness. The paper also addresses the imperative of responsible and sustainable AI, emphasizing the ethical dimensions of AI deployment in ESG-related banking processes. Conclusively, our findings suggest that while AI offers transformative potential for ESG in banking, it also poses significant challenges that necessitate careful consideration. The final part of the paper synthesizes the survey's insights, proposing a forward-looking stance on the adoption of AI in ESG practices. We conclude with recommendations with a reference architecture for future research and development, advocating for a balanced approach that leverages AI's strengths while mitigating its risks within the ESG domain.

cs.CY↗

arXiv2023

Spin dynamics in intermediate-energy heavy-ion collisions with rigorous angular momentum conservation

We have revisited the spin dynamics in intermediate-energy heavy-ion collisions based on the improved spin- and isospin-dependent Boltzmann-Uehling-Uhlenbeck transport model, particularly with the constraint of rigorous angular momentum conservation incorporated. We have studied the spin polarization of free nucleons and tritons/$^3$He as well as the spin alignment of deuterons, and predicted the flow splittings for their different spin states. We have also demonstrated that the spin-dependent potential may enhance dissipations and thus have a non-negligible effect on the spin-averaged transverse flow at low collision energies. When rigorous angular momentum conservation in each spin-dependent nucleon-nucleon collision is incorporated, it affects the overall dynamics, the flow, and also the spin polarization, while the effects of the spin-orbit potential on the spin-related observables are still appreciable. The well-developed SIBUU model could be further extended to include hyperons or vector mesons, or used as a hadronic afterburner for spin-related studies in relativistic heavy-ion collisions, with more inelastic channels incorporated in the future.

nucl-th↗

arXiv2023

Lightweight Improved Residual Network for Efficient Inverse Tone Mapping

The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the internet remain in 8-bit standard dynamic range (SDR) format. Therefore, converting SDR images to HDR ones by inverse tone mapping (ITM) is crucial to unlock the full potential of abundant media images. However, existing ITM methods are usually developed with complex network architectures requiring huge computational costs. In this paper, we propose a lightweight Improved Residual Network (IRNet) by enhancing the power of popular residual block for efficient ITM. Specifically, we propose a new Improved Residual Block (IRB) to extract and fuse multi-layer features for fine-grained HDR image reconstruction. Experiments on three benchmark datasets demonstrate that our IRNet achieves state-of-the-art performance on both the ITM and joint SR-ITM tasks. The code, models and data will be publicly available at https://github.com/ThisisVikki/ITM-baseline.

cs.CV↗