arXiv subjects

Jie Chen

Publications and source records attributed to Jie Chen.

At least 271 records · Page 15Linked to original sources

arXiv2024

PartFormer: Awakening Latent Diverse Representation from Vision Transformer for Object Re-Identification

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit on most distinct regions of training data, limiting its generalizability and attention to holistic object features. Meanwhile, due to the structural difference between CNN and ViT, fine-grained strategies that effectively address this issue in CNN do not continue to be successful in ViT. To address this issue, by observing the latent diverse representation hidden behind the multi-head attention, we present PartFormer, an innovative adaptation of ViT designed to overcome the granularity limitations in object Re-ID tasks. The PartFormer integrates a Head Disentangling Block (HDB) that awakens the diverse representation of multi-head self-attention without the typical loss of feature richness induced by concatenation and FFN layers post-attention. To avoid the homogenization of attention heads and promote robust part-based feature learning, two head diversity constraints are imposed: attention diversity constraint and correlation diversity constraint. These constraints enable the model to exploit diverse and discriminative feature representations from different attention heads. Comprehensive experiments on various object Re-ID benchmarks demonstrate the superiority of the PartFormer. Specifically, our framework significantly outperforms state-of-the-art by 2.4\% mAP scores on the most challenging MSMT17 dataset.

cs.CV↗

arXiv2024

Do Graph Neural Networks Work for High Entropy Alloys?

Graph neural networks (GNNs) have excelled in predictive modeling for both crystals and molecules, owing to the expressiveness of graph representations. High-entropy alloys (HEAs), however, lack chemical long-range order, limiting the applicability of current graph representations. To overcome this challenge, we propose a representation of HEAs as a collection of local environment (LE) graphs. Based on this representation, we introduce the LESets machine learning model, an accurate, interpretable GNN for HEA property prediction. We demonstrate the accuracy of LESets in modeling the mechanical properties of quaternary HEAs. Through analyses and interpretation, we further extract insights into the modeling and design of HEAs. In a broader sense, LESets extends the potential applicability of GNNs to disordered materials with combinatorial complexity formed by diverse constituents and their flexible configurations.

cs.LG↗

arXiv2024

A Digital Twin Framework Utilizing Machine Learning for Robust Predictive Maintenance: Enhancing Tire Health Monitoring

We introduce a novel digital twin framework for predictive maintenance of long-term physical systems. Using monitoring tire health as an application, we show how the digital twin framework can be used to enhance automotive safety and efficiency, and how the technical challenges can be overcome using a three-step approach. Firstly, for managing the data complexity over a long operation span, we employ data reduction techniques to concisely represent physical tires using historical performance and usage data. Relying on these data, for fast real-time prediction, we train a transformer-based model offline on our concise dataset to predict future tire health over time, represented as Remaining Casing Potential (RCP). Based on our architecture, our model quantifies both epistemic and aleatoric uncertainty, providing reliable confidence intervals around predicted RCP. Secondly, to incorporate real-time data, we update the predictive model in the digital twin framework, ensuring its accuracy throughout its life span with the aid of hybrid modeling and the use of discrepancy function. Thirdly, to assist decision making in predictive maintenance, we implement a Tire State Decision Algorithm, which strategically determines the optimal timing for tire replacement based on RCP forecasted by our transformer model. This approach ensures our digital twin accurately predicts system health, continually refines its digital representation, and supports predictive maintenance decisions. Our framework effectively embodies a physical system, leveraging big data and machine learning for predictive maintenance, model updates, and decision-making.

cs.LG↗

arXiv2024

Broadening of the Divertor Heat Flux Profile in High Confinement Tokamak Fusion Plasmas with Edge Pedestals Limited by Turbulence in DIII-D

Multi-machine empirical scaling predicts an extremely narrow heat exhaust layer in future high magnetic field tokamaks, producing high power densities that require mitigation. In the experiments presented, the width of this exhaust layer is nearly doubled using actuators to increase turbulent transport in the plasma edge. This is achieved in low collisionality, high confinement edge pedestals with their gradients limited by turbulent transport instead of large-scale, coherent instabilities. The exhaust heat flux profile width and divertor leg diffusive spreading both double as a high frequency band of turbulent fluctuations propagating in the electron diamagnetic direction doubles in amplitude. The results are quantitatively reproduced in electromagnetic XGC particle-in-cell simulations which show the heat flux carried by electrons emerges to broaden the heat flux profile, directly supported by Langmuir probe measurements.

physics.plasm-ph↗

arXiv2024

Coexistence of large anomalous Hall effect and topological magnetic skyrmions in a Weyl nodal ring ferromagnet Mn5Ge3

Topological magnetic materials are expected to show multiple transport responses because of their unusual bulk electronic topology in momentum space and topological spin texture in real space. However, such multiple topological properties-hosting materials are rare in nature. In this work, we reveal the coexistence of a large tunable anomalous Hall effect and topological magnetic skyrmions in a Weyl nodal ring ferromagnet Mn5Ge3, by using electrical transport and Lorentz transmission electronic microscope (TEM) measurements. It was found that the intrinsic anomalous Hall conductivity (AHC) can reach up to 979.7 S/cm with current along [120] and magnetic field along [001] of the Mn5Ge3 single crystals. Our theoretical calculations reveal that the large AHC is closely related with two Weyl nodal rings in band structure near the Fermi level and is strongly modified by the content of Ge. Moreover, our Lorentz-TEM images and micromagnetic simulation results, together with the sizable topological Hall effect clearly point to the robust formation of magnetic skyrmions over a wide temperature-magnetic field region. These results prove Mn5Ge3 as a rare magnetic topological nodal-line semimetal with great significance to explore novel multiple topological phenomena, which facilitates the development of spintronics.

cond-mat.mtrl-sci↗

arXiv2024

The Shape of Money Laundering: Subgraph Representation Learning on the Blockchain with the Elliptic2 Dataset

Subgraph representation learning is a technique for analyzing local structures (or shapes) within complex networks. Enabled by recent developments in scalable Graph Neural Networks (GNNs), this approach encodes relational information at a subgroup level (multiple connected nodes) rather than at a node level of abstraction. We posit that certain domain applications, such as anti-money laundering (AML), are inherently subgraph problems and mainstream graph techniques have been operating at a suboptimal level of abstraction. This is due in part to the scarcity of annotated datasets of real-world size and complexity, as well as the lack of software tools for managing subgraph GNN workflows at scale. To enable work in fundamental algorithms as well as domain applications in AML and beyond, we introduce Elliptic2, a large graph dataset containing 122K labeled subgraphs of Bitcoin clusters within a background graph consisting of 49M node clusters and 196M edge transactions. The dataset provides subgraphs known to be linked to illicit activity for learning the set of "shapes" that money laundering exhibits in cryptocurrency and accurately classifying new criminal activity. Along with the dataset we share our graph techniques, software tooling, promising early experimental results, and new domain insights already gleaned from this approach. Taken together, we find immediate practical value in this approach and the potential for a new standard in anti-money laundering and forensic analytics in cryptocurrencies and other financial networks.

cs.LG↗

arXiv2024

Towards Effective and Efficient Continual Pre-training of Large Language Models

Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks. To make the CPT approach more traceable, this paper presents a technical report for continually pre-training Llama-3 (8B), which significantly enhances the Chinese language ability and scientific reasoning ability of the backbone model. To enhance the new abilities while retaining the original abilities, we design specific data mixture and curriculum strategies by utilizing existing datasets and synthesizing high-quality datasets. Specifically, we synthesize multidisciplinary scientific question and answer (QA) pairs based on related web pages, and subsequently incorporate these synthetic data to improve the scientific reasoning ability of Llama-3. We refer to the model after CPT as Llama-3-SynE (Synthetic data Enhanced Llama-3). We also present the tuning experiments with a relatively small model -- TinyLlama, and employ the derived findings to train the backbone model. Extensive experiments on a number of evaluation benchmarks show that our approach can largely improve the performance of the backbone models, including both the general abilities (+8.81 on C-Eval and +6.31 on CMMLU) and the scientific reasoning abilities (+12.00 on MATH and +4.13 on SciEval), without hurting the original capacities. Our model, data, and codes are available at https://github.com/RUC-GSAI/Llama-3-SynE.

cs.CL↗

arXiv2024

Connected sum and crossing numbers of flat virtual knots

The connected sum of two flat virtual knots depends on the choice of diagrams and basepoints. We show that any minimal crossing diagram of a composite flat virtual knot is a connected sum diagram. We also show the crossing number of flat virtual knots is super-additive under connected sum.

math.GT↗

arXiv2024

ParCo: Part-Coordinating Text-to-Motion Synthesis

We study a challenging task: text-to-motion synthesis, aiming to generate motions that align with textual descriptions and exhibit coordinated movements. Currently, the part-based methods introduce part partition into the motion synthesis process to achieve finer-grained generation. However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts. Moreover, introducing finer-grained part concepts poses computational complexity challenges. In this paper, we propose Part-Coordinating Text-to-Motion Synthesis (ParCo), endowed with enhanced capabilities for understanding part motions and communication among different part motion generators, ensuring a coordinated and fined-grained motion synthesis. Specifically, we discretize whole-body motion into multiple part motions to establish the prior concept of different parts. Afterward, we employ multiple lightweight generators designed to synthesize different part motions and coordinate them through our part coordination module. Our approach demonstrates superior performance on common benchmarks with economic computations, including HumanML3D and KIT-ML, providing substantial evidence of its effectiveness. Code is available at https://github.com/qrzou/ParCo .

cs.CV↗

arXiv2024

Giant second harmonic generation in supertwisted WS2 spirals grown in step edge particle induced non-Euclidean surfaces

In moiré crystals resulting from the stacking of twisted two-dimensional (2D) layered materials, a subtle adjustment in the twist angle surprisingly gives rise to a wide range of correlated optical and electrical properties. Herein, we report the synthesis of supertwisted WS2 spirals and the observation of giant second harmonic generation (SHG) in these spirals. Supertwisted WS2 spirals featuring different twist angles are synthesized on a Euclidean or step-edge particle-induced non-Euclidean surface using a carefully designed water-assisted chemical vapor deposition. We observed an oscillatory dependence of SHG intensity on layer number, attributed to atomically phase-matched nonlinear dipoles within layers of supertwisted spiral crystals where inversion symmetry is restored. Through an investigation into the twist angle evolution of SHG intensity, we discovered that the stacking model between layers plays a crucial role in determining the nonlinearity, and the SHG signals in supertwisted spirals exhibit enhancements by a factor of 2 to 136 when compared with the SHG of the single-layer structure. These findings provide an efficient method for the rational growth of 2D twisted structures and the implementation of twist angle adjustable endowing them great potential for exploring strong coupling correlation physics and applications in the field of twistronics.

physics.optics↗

arXiv2024

Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation

In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not require complex teacher models or information from extra sensors. Specifically, for the teacher model training, we propose to noise the label and then incorporate it into input to effectively boost the lightweight teacher performance. To ensure the robustness of the teacher model against the introduced noise, we propose a dual-path consistency training strategy featuring a distance loss between the outputs of two paths. For the student model training, we keep it consistent with the standard distillation for simplicity. Our approach not only boosts the efficacy of knowledge distillation but also increases the flexibility in selecting teacher and student models. To demonstrate the advantages of our Label Assisted Distillation (LAD) method, we conduct extensive experiments on five challenging datasets including Cityscapes, ADE20K, PASCAL-VOC, COCO-Stuff 10K, and COCO-Stuff 164K, five popular models: FCN, PSPNet, DeepLabV3, STDC, and OCRNet, and results show the effectiveness and generalization of our approach. We posit that incorporating labels into the input, as demonstrated in our work, will provide valuable insights into related fields. Code is available at https://github.com/skyshoumeng/Label_Assisted_Distillation.

cs.CV↗

arXiv2024

Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation

Text-to-motion generation requires not only grounding local actions in language but also seamlessly blending these individual actions to synthesize diverse and realistic global motions. However, existing motion generation methods primarily focus on the direct synthesis of global motions while neglecting the importance of generating and controlling local actions. In this paper, we propose the local action-guided motion diffusion model, which facilitates global motion generation by utilizing local actions as fine-grained control signals. Specifically, we provide an automated method for reference local action sampling and leverage graph attention networks to assess the guiding weight of each local action in the overall motion synthesis. During the diffusion process for synthesizing global motion, we calculate the local-action gradient to provide conditional guidance. This local-to-global paradigm reduces the complexity associated with direct global motion generation and promotes motion diversity via sampling diverse actions as conditions. Extensive experiments on two human motion datasets, i.e., HumanML3D and KIT, demonstrate the effectiveness of our method. Furthermore, our method provides flexibility in seamlessly combining various local actions and continuous guiding weight adjustment, accommodating diverse user preferences, which may hold potential significance for the community. The project page is available at https://jpthu17.github.io/GuidedMotion-project/.

cs.CV↗

arXiv2024

LLMBox: A Comprehensive Library for Large Language Models

To facilitate the research on large language models (LLMs), this paper presents a comprehensive and unified library, LLMBox, to ease the development, use, and evaluation of LLMs. This library is featured with three main merits: (1) a unified data interface that supports the flexible implementation of various training strategies, (2) a comprehensive evaluation that covers extensive tasks, datasets, and models, and (3) more practical consideration, especially on user-friendliness and efficiency. With our library, users can easily reproduce existing methods, train new models, and conduct comprehensive performance comparisons. To rigorously test LLMBox, we conduct extensive experiments in a diverse coverage of evaluation settings, and experimental results demonstrate the effectiveness and efficiency of our library in supporting various implementations related to LLMs. The detailed introduction and usage guidance can be found at https://github.com/RUCAIBox/LLMBox.

cs.CL↗

arXiv2024

Efficient factored gradient descent algorithm for quantum state tomography

Reconstructing the state of quantum many-body systems is of fundamental importance in quantum information tasks, but extremely challenging due to the curse of dimensionality. In this work, we present an efficient quantum tomography protocol that combines the state-factored with eigenvalue mapping to address the rank-deficient issue and incorporates a momentum-accelerated gradient descent algorithm to speed up the optimization process. We implement extensive numerical experiments to demonstrate that our factored gradient descent algorithm efficiently mitigates the rank-deficient problem and admits orders of magnitude better tomography accuracy and faster convergence. We also find that our method can accomplish the full-state tomography of random 11-qubit mixed states within one minute.

quant-ph↗

arXiv2024

Kinetics of Rayleigh-Taylor instability in van der Waals fluid: the influence of compressibility

Early studies on Rayleigh-Taylor instability (RTI) primarily relied on the Navier-Stokes (NS) model. As research progresses, it becomes increasingly evident that the kinetic information that the NS model failed to capture is of great value for identifying and even controlling the RTI process; simultaneously, the lack of analysis techniques for complex physical fields results in a significant waste of data information. In addition, early RTI studies mainly focused on the incompressible case and the weakly compressible case. In the case of strong compressibility, the density of the fluid from the upper layer (originally heavy fluid) may become smaller than that of the surrounding (originally light) fluid, thus invalidating the early method of distinguishing light and heavy fluids based on density. In this paper, tracer particles are incorporated into a single-fluid discrete Boltzmann method (DBM) model that considers the van der Waals potential. By using tracer particles to label the matter-particle sources, a careful study of the matter-mixing and energy-mixing processes of the RTI evolution is realized in the single-fluid framework. The effects of compressibility on the evolution of RTI are examined mainly through the analysis of bubble and spike velocities, the ratio of area occupied by heavy fluid, and various entropy generation rates of the system. It is demonstrated that: (1) compressibility has a suppressive effect on the spike velocity, and this suppressive impact diminishes as the Atwood number ($At$) increases. The influence of compressibility on bubble velocity shows a staged behavior with increasing $At$. (2) The impact of compressibility on the entropy production rate associated with the heat flow (${\dot{S}_{NOEF}}$) is related to the stages of RTI evolution.

physics.flu-dyn↗

arXiv2024

Time-optimal Flight in Cluttered Environments via Safe Reinforcement Learning

This paper addresses the problem of guiding a quadrotor through a predefined sequence of waypoints in cluttered environments, aiming to minimize the flight time while avoiding collisions. Previous approaches either suffer from prolonged computational time caused by solving complex non-convex optimization problems or are limited by the inherent smoothness of polynomial trajectory representations, thereby restricting the flexibility of movement. In this work, we present a safe reinforcement learning approach for autonomous drone racing with time-optimal flight in cluttered environments. The reinforcement learning policy, trained using safety and terminal rewards specifically designed to enforce near time-optimal and collision-free flight, outperforms current state-of-the-art algorithms. Additionally, experimental results demonstrate the efficacy of the proposed approach in achieving both minimum flight time and obstacle avoidance objectives in complex environments, with a commendable $66.7\%$ success rate in unseen, challenging settings.

cs.RO↗

arXiv2024

A Distributed Iterative Tikhonov Method for Networked Monotone Aggregative Hierarchical Stochastic Games

We consider a class of nonsmooth aggregative games over networks in stochastic regimes, where each player is characterized by a composite cost function $f_i+r_i$, $f_i$ is a smooth expectation-valued function dependent on its own strategy and an aggregate function of rival strategies, and $r_i$ is a nonsmooth convex function of its strategy with an efficient prox-evaluation. We design a fully distributed iterative proximal stochastic gradient method overlaid by a Tikhonov regularization, where each player may independently choose its steplengths and regularization parameters while meeting some coordination requirements. Under a monotonicity assumption on the pseudo-gradient mapping, we prove the almost sure convergence to the least-norm Nash equilibrium. In addition, when each $r_i$ is an indicator function of a compact convex set, we establish the convergence rate associated with the expected gap function at the time-averaged sequence. We further establish high probability bounds for the gap function via both Markov's inequality as well as a more refined argument that leverages Azuma's inequality. Furthermore, we consider the extension to the private hierarchical regime where each player is a leader with respect to a collection of private followers competing in a strongly monotone game, parametrized by leader decisions. By leveraging a convolution-smoothing framework, we present amongst the first fully distributed schemes for computing a Nash equilibrium of a game complicated by such a hierarchical structure. Based on this framework, we extend the rate statements to accommodate the computation of a hierarchical stochastic Nash equilibrium by using a Fitzpatrick gap function. Finally, we validate the proposed methods on a networked Nash-Cournot equilibrium problem and a hierarchical generalization, observing that regularization has a beneficial impact on empirical behavior.

math.OC↗

arXiv2024

Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models

Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs). Studies have shown that synthetic data can effectively improve the performance of LLMs on downstream benchmarks. However, despite its potential benefits, our analysis suggests that there may be inherent flaws in synthetic data. The uniform format of synthetic data can lead to pattern overfitting and cause significant shifts in the output distribution, thereby reducing the model's instruction-following capabilities. Our work delves into these specific flaws associated with question-answer (Q-A) pairs, a prevalent type of synthetic data, and presents a method based on unlearning techniques to mitigate these flaws. The empirical results demonstrate the effectiveness of our approach, which can reverse the instruction-following issues caused by pattern overfitting without compromising performance on benchmarks at relatively low cost. Our work has yielded key insights into the effective use of synthetic data, aiming to promote more robust and efficient LLM training.

cs.CL↗