arXiv subjects

Chang Liu

Publications and source records attributed to Chang Liu.

At least 613 records · Page 34Linked to original sources

arXiv2024

Adam: Dense Retrieval Distillation with Adaptive Dark Examples

To improve the performance of the dual-encoder retriever, one effective approach is knowledge distillation from the cross-encoder ranker. Existing works construct the candidate passages following the supervised learning setting where a query is paired with a positive passage and a batch of negatives. However, through empirical observation, we find that even the hard negatives from advanced methods are still too trivial for the teacher to distinguish, preventing the teacher from transferring abundant dark knowledge to the student through its soft label. To alleviate this issue, we propose ADAM, a knowledge distillation framework that can better transfer the dark knowledge held in the teacher with Adaptive Dark exAMples. Different from previous works that only rely on one positive and hard negatives as candidate passages, we create dark examples that all have moderate relevance to the query through mixing-up and masking in discrete space. Furthermore, as the quality of knowledge held in different training instances varies as measured by the teacher's confidence score, we propose a self-paced distillation strategy that adaptively concentrates on a subset of high-quality instances to conduct our dark-example-based knowledge distillation to help the student learn better. We conduct experiments on two widely-used benchmarks and verify the effectiveness of our method.

cs.CL↗

arXiv2024

Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction

Predicting the mean-field Hamiltonian matrix in density functional theory is a fundamental formulation to leverage machine learning for solving molecular science problems. Yet, its applicability is limited by insufficient labeled data for training. In this work, we highlight that Hamiltonian prediction possesses a self-consistency principle, based on which we propose self-consistency training, an exact training method that does not require labeled data. It distinguishes the task from predicting other molecular properties by the following benefits: (1) it enables the model to be trained on a large amount of unlabeled data, hence addresses the data scarcity challenge and enhances generalization; (2) it is more efficient than running DFT to generate labels for supervised training, since it amortizes DFT calculation over a set of queries. We empirically demonstrate the better generalization in data-scarce and out-of-distribution scenarios, and the better efficiency over DFT labeling. These benefits push forward the applicability of Hamiltonian prediction to an ever-larger scale.

cs.LG↗

arXiv2024

Self-supervised Feature-Gate Coupling for Dynamic Network Pruning

Gating modules have been widely explored in dynamic network pruning to reduce the run-time computational cost of deep neural networks while preserving the representation of features. Despite the substantial progress, existing methods remain ignoring the consistency between feature and gate distributions, which may lead to distortion of gated features. In this paper, we propose a feature-gate coupling (FGC) approach aiming to align distributions of features and gates. FGC is a plug-and-play module, which consists of two steps carried out in an iterative self-supervised manner. In the first step, FGC utilizes the $k$-Nearest Neighbor method in the feature space to explore instance neighborhood relationships, which are treated as self-supervisory signals. In the second step, FGC exploits contrastive learning to regularize gating modules with generated self-supervisory signals, leading to the alignment of instance neighborhood relationships within the feature and gate spaces. Experimental results validate that the proposed FGC method improves the baseline approach with significant margins, outperforming the state-of-the-arts with better accuracy-computation trade-off. Code is publicly available.

cs.CV↗

arXiv2024

Gaia22dkvLb: A Microlensing Planet Potentially Accessible to Radial-Velocity Characterization

We report discovering an exoplanet from following up a microlensing event alerted by Gaia. The event Gaia22dkv is toward a disk source rather than the traditional bulge microlensing fields. Our primary analysis yields a Jovian planet with M_p = 0.59^{+0.15}_{-0.05} M_J at a projected orbital separation r_perp = 1.4^{+0.8}_{-0.3} AU, and the host is a ~1.1 M_sun turnoff star at ~1.3 kpc. At r'~14, the host is far brighter than any previously discovered microlensing planet host, opening up the opportunity of testing the microlensing model with radial velocity (RV) observations. RV data can be used to measure the planet's orbital period and eccentricity, and they also enable searching for inner planets of the microlensing cold Jupiter, as expected from the ''inner-outer correlation'' inferred from Kepler and RV discoveries. Furthermore, we show that Gaia astrometric microlensing will not only allow precise measurements of its angular Einstein radius theta_E, but also directly measure the microlens parallax vector and unambiguously break a geometric light-curve degeneracy, leading to definitive characterization of the lens system.

astro-ph.EP↗

arXiv2024

Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning

Although vision models such as Contrastive Language-Image Pre-Training (CLIP) show impressive generalization performance, their zero-shot robustness is still limited under Out-of-Distribution (OOD) scenarios without fine-tuning. Instead of undesirably providing human supervision as commonly done, it is possible to take advantage of Multi-modal Large Language Models (MLLMs) that hold powerful visual understanding abilities. However, MLLMs are shown to struggle with vision problems due to the incompatibility of tasks, thus hindering their utilization. In this paper, we propose to effectively leverage MLLMs to conduct Machine Vision Therapy which aims to rectify the noisy predictions from vision models. By fine-tuning with the denoised labels, the learning model performance can be boosted in an unsupervised manner. To solve the incompatibility issue, we propose a novel Denoising In-Context Learning (DICL) strategy to align vision tasks with MLLMs. Concretely, by estimating a transition matrix that captures the probability of one class being confused with another, an instruction containing a correct exemplar and an erroneous one from the most probable noisy class can be constructed. Such an instruction can help any MLLMs with ICL ability to detect and rectify incorrect predictions of vision models. Through extensive experiments on ImageNet, WILDS, DomainBed, and other OOD datasets, we carefully validate the quantitative and qualitative effectiveness of our method. Our code is available at https://github.com/tmllab/Machine_Vision_Therapy.

cs.CV↗

arXiv2024

Networked Integrated Sensing and Communications for 6G Wireless Systems

Integrated sensing and communication (ISAC) is envisioned as a key pillar for enabling the upcoming sixth generation (6G) communication systems, requiring not only reliable communication functionalities but also highly accurate environmental sensing capabilities. In this paper, we design a novel networked ISAC framework to explore the collaboration among multiple users for environmental sensing. Specifically, multiple users can serve as powerful sensors, capturing back scattered signals from a target at various angles to facilitate reliable computational imaging. Centralized sensing approaches are extremely sensitive to the capability of the leader node because it requires the leader node to process the signals sent by all the users. To this end, we propose a two-step distributed cooperative sensing algorithm that allows low-dimensional intermediate estimate exchange among neighboring users, thus eliminating the reliance on the centralized leader node and improving the robustness of sensing. This way, multiple users can cooperatively sense a target by exploiting the block-wise environment sparsity and the interference cancellation technique. Furthermore, we analyze the mean square error of the proposed distributed algorithm as a networked sensing performance metric and propose a beamforming design for the proposed network ISAC scheme to maximize the networked sensing accuracy and communication performance subject to a transmit power constraint. Simulation results validate the effectiveness of the proposed algorithm compared with the state-of-the-art algorithms.

eess.SP↗

arXiv2024

LaCon: Late-Constraint Diffusion for Steerable Guided Image Synthesis

Diffusion models have demonstrated impressive abilities in generating photo-realistic and creative images. To offer more controllability for the generation process, existing studies, termed as early-constraint methods in this paper, leverage extra conditions and incorporate them into pre-trained diffusion models. Particularly, some of them adopt condition-specific modules to handle conditions separately, where they struggle to generalize across other conditions. Although follow-up studies present unified solutions to solve the generalization problem, they also require extra resources to implement, e.g., additional inputs or parameter optimization, where more flexible and efficient solutions are expected to perform steerable guided image synthesis. In this paper, we present an alternative paradigm, namely Late-Constraint Diffusion (LaCon), to simultaneously integrate various conditions into pre-trained diffusion models. Specifically, LaCon establishes an alignment between the external condition and the internal features of diffusion models, and utilizes the alignment to incorporate the target condition, guiding the sampling process to produce tailored results. Experimental results on COCO dataset illustrate the effectiveness and superior generalization capability of LaCon under various conditions and settings. Ablation studies investigate the functionalities of different components in LaCon, and illustrate its great potential to serve as an efficient solution to offer flexible controllability for diffusion models.

cs.CV↗

arXiv2024

Phase-field analysis for brittle fracture in ferroelectric materials with flexoelectric effect

Understanding the nature of brittle failure in ferroelectric materials is essential, but difficult due to the complex interaction between mechanical and electrical concentrated fields near the crack tip. In this work, an extended phase-field model incorporating multiple order parameters is constructed to analyze the coupled evolution of fracture and domain behavior in ferroelectric materials. The strain gradient is incorporated into the governing equations to evaluate the impact of the flexoelectric effect during the crack propagation process. Our advanced phase-field model demonstrated that, with the consideration of the flexoelectric effect, both the crack extension rate and crack path are related to the initial polarization direction. This phenomenon is associated with the eigenstrain induced by the flexoelectric effect. This study provides in-depth insight into the fracture behavior of ferroelectric materials. The developed model framework can also be employed to investigate electromechanical coupling failures in more complex ferroelectric structures.

cond-mat.mtrl-sci↗

arXiv2024

Observation of Spin Splitting in Room-Temperature Metallic Antiferromagnet CrSb

Recently, unconventional antiferromagnets that enable the splitting of electronic spins have been theoretically proposed and experimentally realized, where the magnetic sublattices containing moments pointing at different directions are connected by a novel set of symmetries. Such spin splitting (SS) is substantial, $k$-dependent, and independent of the spin-orbit coupling strength, making these magnets promising materials for antiferromagnetic spintronics. Here, combined with angle-resolved photoemission spectroscopy (ARPES) and density functional theory (DFT) calculations, we perform a systematic study on CrSb, a metallic spin-split antiferromagnet candidate with $T_N$ = 703 K. Our data reveals the electronic structure of CrSb along both out-of-plane and in-plane momentum directions, which renders anisotropic $k$-dependent SS and agrees well with the calculational results. The magnitude of such SS reaches up to at least 0.8 eV at non-high-symmetry momentum points, which is significantly higher than the largest known SOC-induced SS. This compound expands the choice of materials in the field of antiferromagnetic spintronics and is likely to stimulate subsequent investigations of high-efficiency spintronic devices that are functional at room temperature.

cond-mat.mtrl-sci↗

arXiv2024

Towards the Quantized Anomalous Hall effect in AlO$_x$-capped MnBi$_2$Te$_4$

The quantum anomalous Hall effect in layered antiferromagnet MnBi$_2$Te$_4$ harbors a rich interplay between magnetism and topology, holding a significant promise for low-power electronic devices and topological antiferromagnetic spintronics. In recent years, MnBi$_2$Te$_4$ has garnered considerable attention as the only known material to exhibit the antiferromagnetic quantum anomalous Hall effect. However, this field faces significant challenges as realizing quantized transport at zero magnetic fields depends critically on fabricating high-quality device. In this article, we address the detrimental influences of fabrication on MnBi$_2$Te$_4$ by simply depositing an AlO$_x$ thin layer on the surface prior to fabrications. Optical contrast and magnetotransport measurements on over 50 samples demonstrate that AlO$_x$ can effectively preserve the pristine state of the samples and significantly enhance the anomalous Hall effect towards quantization. Scaling analysis reveals the Berry curvature dominated mechanism of the anomalous Hall effect at various magnetic configurations. By adjusting the gate voltage, we uncover a gate independent antiferromagnetism in MnBi$_2$Te$_4$. Our experiment not only pave the way for fabricating high-quality transport devices but also advance the exploration of exotic quantum physics in 2D materials.

cond-mat.mtrl-sci↗

arXiv2024

GraCo: Granularity-Controllable Interactive Segmentation

Interactive Segmentation (IS) segments specific objects or parts in the image according to user input. Current IS pipelines fall into two categories: single-granularity output and multi-granularity output. The latter aims to alleviate the spatial ambiguity present in the former. However, the multi-granularity output pipeline suffers from limited interaction flexibility and produces redundant results. In this work, we introduce Granularity-Controllable Interactive Segmentation (GraCo), a novel approach that allows precise control of prediction granularity by introducing additional parameters to input. This enhances the customization of the interactive system and eliminates redundancy while resolving ambiguity. Nevertheless, the exorbitant cost of annotating multi-granularity masks and the lack of available datasets with granularity annotations make it difficult for models to acquire the necessary guidance to control output granularity. To address this problem, we design an any-granularity mask generator that exploits the semantic property of the pre-trained IS model to automatically generate abundant mask-granularity pairs without requiring additional manual annotation. Based on these pairs, we propose a granularity-controllable learning strategy that efficiently imparts the granularity controllability to the IS model. Extensive experiments on intricate scenarios at object and part levels demonstrate that our GraCo has significant advantages over previous methods. This highlights the potential of GraCo to be a flexible annotation tool, capable of adapting to diverse segmentation scenarios. The project page: https://zhao-yian.github.io/GraCo.

cs.CV↗

arXiv2024

Antiferromagnetic Quantum Anomalous Hall Effect Modulated by Spin Flips and Flops

The interplay between nontrivial band topology and layered antiferromagnetism in MnBi2Te4 has opened up a new avenue for exploring topological phases of matter. Representative examples include the quantum anomalous Hall effect and axion insulator state observed in odd and even number layers of MnBi2Te4, when the top and bottom surfaces have parallel and antiparallel spin alignments respectively. The rich and complex spin dynamics associated with the van der Waals antiferromagnetic order is expected to generate novel topological phases and phase transitions that are unique to MnBi2Te4. Here we fabricate a device of 7-septuple-layer MnBi2Te4 covered with AlOx capping layer, which enables the investigation of antiferromagnetic quantum anomalous Hall effect over wide parameter spaces. By tuning the gate voltage and perpendicular magnetic field, we uncover a cascade of quantum phase transitions that can be attributed to the influence of spin configurations on charge transport. Furthermore, we find that an in-plane magnetic field enhances both the coercive field and exchange gap of the surface state, in sharp contrast to that in ferromagnetic quantum anomalous Hall state. We propose that these peculiar features arise from the spin flip and flop transitions inherent to van der Waals antiferromagnet. The versatile tunability of the quantum anomalous Hall effect in MnBi2Te4 paves the way for potential applications in topological antiferromagnetic spintronics.

cond-mat.mtrl-sci↗

arXiv2024

MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures

Accurate and fast prediction of materials properties is central to the digital transformation of materials design. However, the vast design space and diverse operating conditions pose significant challenges for accurately modeling arbitrary material candidates and forecasting their properties. We present MatterSim, a deep learning model actively learned from large-scale first-principles computations, for efficient atomistic simulations at first-principles level and accurate prediction of broad material properties across the periodic table, spanning temperatures from 0 to 5000 K and pressures up to 1000 GPa. Out-of-the-box, the model serves as a machine learning force field, and shows remarkable capabilities not only in predicting ground-state material structures and energetics, but also in simulating their behavior under realistic temperatures and pressures, signifying an up to ten-fold enhancement in precision compared to the prior best-in-class. This enables MatterSim to compute materials' lattice dynamics, mechanical and thermodynamic properties, and beyond, to an accuracy comparable with first-principles methods. Specifically, MatterSim predicts Gibbs free energies for a wide range of inorganic solids with near-first-principles accuracy and achieves a 15 meV/atom resolution for temperatures up to 1000K compared with experiments. This opens an opportunity to predict experimental phase diagrams of materials at minimal computational cost. Moreover, MatterSim also serves as a platform for continuous learning and customization by integrating domain-specific data. The model can be fine-tuned for atomistic simulations at a desired level of theory or for direct structure-to-property predictions, achieving high data efficiency with a reduction in data requirements by up to 97%.

cond-mat.mtrl-sci↗

arXiv2024

Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers

Poisoning-based backdoor attacks expose vulnerabilities in the data preparation stage of deep neural network (DNN) training. The DNNs trained on the poisoned dataset will be embedded with a backdoor, making them behave well on clean data while outputting malicious predictions whenever a trigger is applied. To exploit the abundant information contained in the input data to output label mapping, our scheme utilizes the network trained from the clean dataset as a trigger generator to produce poisons that significantly raise the success rate of backdoor attacks versus conventional approaches. Specifically, we provide a new categorization of triggers inspired by the adversarial technique and develop a multi-label and multi-payload Poisoning-based backdoor attack with Positive Triggers (PPT), which effectively moves the input closer to the target label on benign classifiers. After the classifier is trained on the poisoned dataset, we can generate an input-label-aware trigger to make the infected classifier predict any given input to any target label with a high possibility. Under both dirty- and clean-label settings, we show empirically that the proposed attack achieves a high attack success rate without sacrificing accuracy across various datasets, including SVHN, CIFAR10, GTSRB, and Tiny ImageNet. Furthermore, the PPT attack can elude a variety of classical backdoor defenses, proving its effectiveness.

cs.CV↗

arXiv2024

Intra-task Mutual Attention based Vision Transformer for Few-Shot Learning

Humans possess remarkable ability to accurately classify new, unseen images after being exposed to only a few examples. Such ability stems from their capacity to identify common features shared between new and previously seen images while disregarding distractions such as background variations. However, for artificial neural network models, determining the most relevant features for distinguishing between two images with limited samples presents a challenge. In this paper, we propose an intra-task mutual attention method for few-shot learning, that involves splitting the support and query samples into patches and encoding them using the pre-trained Vision Transformer (ViT) architecture. Specifically, we swap the class (CLS) token and patch tokens between the support and query sets to have the mutual attention, which enables each set to focus on the most useful information. This facilitates the strengthening of intra-class representations and promotes closer proximity between instances of the same class. For implementation, we adopt the ViT-based network architecture and utilize pre-trained model parameters obtained through self-supervision. By leveraging Masked Image Modeling as a self-supervised training task for pre-training, the pre-trained model yields semantically meaningful representations while successfully avoiding supervision collapse. We then employ a meta-learning method to fine-tune the last several layers and CLS token modules. Our strategy significantly reduces the num- ber of parameters that require fine-tuning while effectively uti- lizing the capability of pre-trained model. Extensive experiments show that our framework is simple, effective and computationally efficient, achieving superior performance as compared to the state-of-the-art baselines on five popular few-shot classification benchmarks under the 5-shot and 1-shot scenarios

cs.CV↗

arXiv2024

Towards Understanding Worldwide Cross-cultural Differences in Implicit Driving Cues: Review, Comparative Analysis, and Research Roadmap

Recognizing and understanding implicit driving cues across diverse cultures is imperative for fostering safe and efficient global transportation systems, particularly when training new immigrants holding driving licenses from culturally disparate countries. Additionally, it is essential to consider cross-cultural differences in the development of Automated Driving features tailored to different countries. Previous piloting studies have compared and analyzed cross-cultural differences in selected implicit driving cues, but they typically examine only limited countries. However, a comprehensive worldwide comparison and analysis are lacking. This study conducts a thorough review of existing literature, online blogs, and expert insights from diverse countries to investigate cross-cultural disparities in driving behaviors, specifically focusing on implicit cues such as non-verbal communication (e.g., hand gestures, signal lighting, honking), norms, and social expectations. Through comparative analysis, variations in driving cues are illuminated across different cultural contexts. Based on the findings and identified gaps, a research roadmap is proposed for future research to further explore and address these differences, aiming to enhance intercultural communication, improve road safety, and increase transportation efficiency on a global scale. This paper presents the pioneering work towards a comprehensive understanding of the implicit driving cues across cultures. Moreover, this understanding will inform the development of automated driving systems tailored to different countries considering cross-cultural differences.

cs.SI↗

arXiv2024

Solving the train-platforming problem via a two-level Lagrangian Relaxation approach

High-speed railway stations are crucial junctions in high-speed railway networks. Compared to operations on the tracks between stations, trains have more routing possibilities within stations. As a result, track allocation at a station is relatively complicated. In this study, we aim to solve the train platforming problem for a busy high-speed railway station by considering comprehensive track resources and interlocking configurations. A two-level space-time network is constructed to capture infrastructure information at various levels of detail from both macroscopic and microscopic perspectives. Additionally, we propose a nonlinear programming model that minimizes a weighted sum of total travel time and total deviation time for trains at the station. We apply a Two-level Lagrangian Relaxation (2-L LR) to a linearized version of the model and demonstrate how this induces a decomposable train-specific path choice problem at the macroscopic level that is guided by Lagrange multipliers associated with microscopic resource capacity violation. As case studies, the proposed model and solution approach are applied to a small virtual railway station and a high-speed railway hub station located on the busiest high-speed railway line in China. Through a comparison of other approaches that include Logic-based Benders Decomposition (LBBD), we highlight the superiority of the proposed method; on realistic instances, the 2-L LR method finds solution that are, on average, approximately 2% from optimality. Finally, we test algorithm performance at the operational level and obtain near-optimal solutions, with optimality gaps of approximately 1%, in a very short time.

math.OC↗

arXiv2024

Large Language Models for Networking: Workflow, Advances and Challenges

The networking field is characterized by its high complexity and rapid iteration, requiring extensive expertise to accomplish network tasks, ranging from network design, configuration, diagnosis and security. The inherent complexity of these tasks, coupled with the ever-changing landscape of networking technologies and protocols, poses significant hurdles for traditional machine learning-based methods. These methods often struggle to generalize and automate complex tasks in networking, as they require extensive labeled data, domain-specific feature engineering, and frequent retraining to adapt to new scenarios. However, the recent emergence of large language models (LLMs) has sparked a new wave of possibilities in addressing these challenges. LLMs have demonstrated remarkable capabilities in natural language understanding, generation, and reasoning. These models, trained on extensive data, can benefit the networking domain. Some efforts have already explored the application of LLMs in the networking domain and revealed promising results. By reviewing recent advances, we present an abstract workflow to describe the fundamental process involved in applying LLM for Networking. We introduce the highlights of existing works by category and explain in detail how they operate at different stages of the workflow. Furthermore, we delve into the challenges encountered, discuss potential solutions, and outline future research prospects. We hope that this survey will provide insight for researchers and practitioners, promoting the development of this interdisciplinary research field.

cs.NI↗