arXiv subjects

Chang Liu

Publications and source records attributed to Chang Liu.

At least 703 records · Page 39Linked to original sources

arXiv2023

UNIDEAL: Curriculum Knowledge Distillation Federated Learning

Federated Learning (FL) has emerged as a promising approach to enable collaborative learning among multiple clients while preserving data privacy. However, cross-domain FL tasks, where clients possess data from different domains or distributions, remain a challenging problem due to the inherent heterogeneity. In this paper, we present UNIDEAL, a novel FL algorithm specifically designed to tackle the challenges of cross-domain scenarios and heterogeneous model architectures. The proposed method introduces Adjustable Teacher-Student Mutual Evaluation Curriculum Learning, which significantly enhances the effectiveness of knowledge distillation in FL settings. We conduct extensive experiments on various datasets, comparing UNIDEAL with state-of-the-art baselines. Our results demonstrate that UNIDEAL achieves superior performance in terms of both model accuracy and communication efficiency. Additionally, we provide a convergence analysis of the algorithm, showing a convergence rate of O(1/T) under non-convex conditions.

cs.LG↗

arXiv2023

Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis

Large Language Models (LLMs) have garnered considerable interest within both academic and industrial. Yet, the application of LLMs to graph data remains under-explored. In this study, we evaluate the capabilities of four LLMs in addressing several analytical problems with graph data. We employ four distinct evaluation metrics: Comprehension, Correctness, Fidelity, and Rectification. Our results show that: 1) LLMs effectively comprehend graph data in natural language and reason with graph topology. 2) GPT models can generate logical and coherent results, outperforming alternatives in correctness. 3) All examined LLMs face challenges in structural reasoning, with techniques like zero-shot chain-of-thought and few-shot prompting showing diminished efficacy. 4) GPT models often produce erroneous answers in multi-answer tasks, raising concerns in fidelity. 5) GPT models exhibit elevated confidence in their outputs, potentially hindering their rectification capacities. Notably, GPT-4 has demonstrated the capacity to rectify responses from GPT-3.5-turbo and its own previous iterations. The code is available at: https://github.com/Ayame1006/LLMtoGraph.

cs.AI↗

arXiv2023

Towards Real-World Burst Image Super-Resolution: Benchmark and Method

Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios. In this paper, we establish a large-scale real-world burst super-resolution dataset, i.e., RealBSR, to explore the faithful reconstruction of image details from multiple frames. Furthermore, we introduce a Federated Burst Affinity network (FBAnet) to investigate non-trivial pixel-wise displacements among images under real-world image degradation. Specifically, rather than using pixel-wise alignment, our FBAnet employs a simple homography alignment from a structural geometry aspect and a Federated Affinity Fusion (FAF) strategy to aggregate the complementary information among frames. Those fused informative representations are fed to a Transformer-based module of burst representation decoding. Besides, we have conducted extensive experiments on two versions of our datasets, i.e., RealBSR-RAW and RealBSR-RGB. Experimental results demonstrate that our FBAnet outperforms existing state-of-the-art burst SR methods and also achieves visually-pleasant SR image predictions with model details. Our dataset, codes, and models are publicly available at https://github.com/yjsunnn/FBANet.

cs.CV↗

arXiv2023

Observation of integer and fractional quantum anomalous Hall effects in twisted bilayer MoTe2

The interplay between strong correlations and topology can lead to the emergence of intriguing quantum states of matter. One well-known example is the fractional quantum Hall effect, where exotic electron fluids with fractionally charged excitations form in partially filled Landau levels. The emergence of topological moiré flat bands provides exciting opportunities to realize the lattice analogs of both the integer and fractional quantum Hall states without the need for an external magnetic field. These states are known as the integer and fractional quantum anomalous Hall (IQAH and FQAH) states. Here, we present direct transport evidence of the existence of both IQAH and FQAH states in twisted bilayer MoTe2 (AA stacked). At zero magnetic field, we observe well-quantized Hall resistance of h/e2 around moiré filling factor ν = -1 (corresponding to one hole per moiré unit cell), and nearly-quantized Hall resistance of 3h/2e2 around ν = -2/3, respectively. Concomitantly, the longitudinal resistance exhibits distinct minima around ν = -1 and -2/3. The application of an electric field induces topological quantum phase transition from the IQAH state to a charge transfer insulator at ν = -1, and from the FQAH state to a generalized Wigner crystal state, further transitioning to a metallic state at ν = -2/3. Our study paves the way for the investigation of fractionally charged excitations and anyonic statistics at zero magnetic field based on semiconductor moiré materials.

cond-mat.mes-hall↗

arXiv2023

UATVR: Uncertainty-Adaptive Text-Video Retrieval

With the explosive growth of web videos and emerging large-scale vision-language pre-training models, e.g., CLIP, retrieving videos of interest with text instructions has attracted increasing attention. A common practice is to transfer text-video pairs to the same embedding space and craft cross-modal interactions with certain entities in specific granularities for semantic correspondence. Unfortunately, the intrinsic uncertainties of optimal entity combinations in appropriate granularities for cross-modal queries are understudied, which is especially critical for modalities with hierarchical semantics, e.g., video, text, etc. In this paper, we propose an Uncertainty-Adaptive Text-Video Retrieval approach, termed UATVR, which models each look-up as a distribution matching procedure. Concretely, we add additional learnable tokens in the encoders to adaptively aggregate multi-grained semantics for flexible high-level reasoning. In the refined embedding space, we represent text-video pairs as probabilistic distributions where prototypes are sampled for matching evaluation. Comprehensive experiments on four benchmarks justify the superiority of our UATVR, which achieves new state-of-the-art results on MSR-VTT (50.8%), VATEX (64.5%), MSVD (49.7%), and DiDeMo (45.8%). The code is available at https://github.com/bofang98/UATVR.

cs.CV↗

arXiv2023

DiffusionRet: Generative Text-Video Retrieval with Diffusion Model

Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i.e., p(candidates|query). While straightforward, this de facto paradigm overlooks the underlying data distribution p(query), which makes it challenging to identify out-of-distribution data. To address this limitation, we creatively tackle this task from a generative viewpoint and model the correlation between the text and the video as their joint probability p(candidates,query). This is accomplished through a diffusion-based text-video retrieval framework (DiffusionRet), which models the retrieval task as a process of gradually generating joint distribution from noise. During training, DiffusionRet is optimized from both the generation and discrimination perspectives, with the generator being optimized by generation loss and the feature extractor trained with contrastive loss. In this way, DiffusionRet cleverly leverages the strengths of both generative and discriminative methods. Extensive experiments on five commonly used text-video retrieval benchmarks, including MSRVTT, LSMDC, MSVD, ActivityNet Captions, and DiDeMo, with superior performances, justify the efficacy of our method. More encouragingly, without any modification, DiffusionRet even performs well in out-domain retrieval settings. We believe this work brings fundamental insights into the related fields. Code is available at https://github.com/jpthu17/DiffusionRet.

cs.CV↗

arXiv2023

Phases and magnetism at the microscale in compounds containing nominal Pb10-xCux(PO4)6O

Achieving superconductivity at room temperature could lead to substantial advancements in industry and technology. Recently, a compound known as Cu-doped lead-apatite, Pb10-xCux(PO4)6O (0.9 < x < 1.1), referred to as "LK-99", has been reported to exhibit unusual electrical and magnetic behaviors that appear to resemble a superconducting transition above room temperature. In this work we collected multiphase samples containing the nominal Pb10-xCux(PO4)6O phase (no superconductivity observed in our measured samples), synthesized by three independent groups, and studied their chemical, magnetic, and electrical properties at the microscale to overcome difficulties in bulk measurements. Through the utilization of optical, scanning electron, atomic force, and scanning diamond nitrogen-vacancy microscopy techniques, we are able to establish a link between local magnetic properties and specific microscale chemical phases. Our findings indicate that while the Pb10-xCux(PO4)6O phase seems to have a mixed magnetism contribution, a significant fraction of the diamagnetic response can be attributed to Cu-rich regions (e.g., Cu2S derived from a reagent used in the synthesis). Additionally, our electrical measurements reveal the phenomenon of current path switch and a change in resistance states of Cu2S. This provides a potential explanation for the electrical behavior observed in compounds related to Pb10-xCux(PO4)6O.

cond-mat.mtrl-sci↗

arXiv2023

MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions

This paper strives for motion expressions guided video segmentation, which focuses on segmenting objects in video content based on a sentence describing the motion of the objects. Existing referring video object datasets typically focus on salient objects and use language expressions that contain excessive static attributes that could potentially enable the target object to be identified in a single frame. These datasets downplay the importance of motion in video content for language-guided video object segmentation. To investigate the feasibility of using motion expressions to ground and segment objects in videos, we propose a large-scale dataset called MeViS, which contains numerous motion expressions to indicate target objects in complex environments. We benchmarked 5 existing referring video object segmentation (RVOS) methods and conducted a comprehensive comparison on the MeViS dataset. The results show that current RVOS methods cannot effectively address motion expression-guided video segmentation. We further analyze the challenges and propose a baseline approach for the proposed MeViS dataset. The goal of our benchmark is to provide a platform that enables the development of effective language-guided video segmentation algorithms that leverage motion expressions as a primary cue for object segmentation in complex video scenes. The proposed MeViS dataset has been released at https://henghuiding.github.io/MeViS.

cs.CV↗

arXiv2023

Informative Path Planning of Autonomous Vehicle for Parking Occupancy Estimation

Parking occupancy estimation holds significant potential in facilitating parking resource management and mitigating traffic congestion. Existing approaches employ robotic systems to detect the occupancy status of individual parking spaces and primarily focus on enhancing detection accuracy through perception pipelines. However, these methods often overlook the crucial aspect of robot path planning, which can hinder the accurate estimation of the entire parking area. In light of these limitations, we introduce the problem of informative path planning for parking occupancy estimation using autonomous vehicles and formulate it as a Partially Observable Markov Decision Process (POMDP) task. Then, we develop an occupancy state transition model and introduce a Bayes filter to estimate occupancy based on noisy sensor measurements. Subsequently, we propose the Monte Carlo Bayes Filter Tree, a computationally efficient algorithm that leverages progressive widening to generate informative paths. We demonstrate that the proposed approach outperforms the benchmark methods in diverse simulation environments, effectively striking a balance between optimality and computational efficiency.

cs.RO↗

arXiv2023

Increasing the Rate of Magnesium Intercalation Underneath Epitaxial Graphene on 6H-SiC(0001)

Magnesium intercalated 'quasi-freestanding' bilayer graphene on 6H-SiC(0001) (Mg-QFSBLG) has many favorable properties (e.g., highly n-type doped, relatively stable in ambient conditions). However, intercalation of Mg underneath monolayer graphene is challenging, requiring multiple intercalation steps. Here, we overcome these challenges and subsequently increase the rate of Mg intercalation by laser patterning (ablating) the graphene to form micron-sized discontinuities. We then use low energy electron diffraction to verify Mg-intercalation and conversion to Mg-QFSBLG, and X-ray photoelectron spectroscopy to determine the Mg intercalation rate for patterned and non-patterned samples. By modeling Mg intercalation with the Verhulst equation, we find that the intercalation rate increase for the patterned sample is 4.5$\pm$1.7. Since the edge length of the patterned sample is $\approx$5.2 times that of the non-patterned sample, the model implies that the increased intercalation rate is proportional to the increase in edge length. Moreover, Mg intercalation likely begins at graphene discontinuities in pristine samples (not step edges or flat terraces), where the 2D-like crystal growth of Mg-silicide proceeds. Our laser patterning technique may enable the rapid intercalation of other atomic or molecular species, thereby expanding upon the library of intercalants used to modify the characteristics of graphene, or other 2D materials and heterostructures.

cond-mat.mtrl-sci↗

arXiv2023

Parameter inference for coalescing massive black hole binaries using deep learning

In the 2030s, a new era of gravitational-wave (GW) observations will dawn as multiple space-based GW detectors, such as the Laser Interferometer Space Antenna, Taiji and TianQin, open the millihertz window for GW astronomy. These detectors are poised to detect a multitude of GW signals emitted by different sources. It is a challenging task for GW data analysis to recover the parameters of these sources at a low computational cost. Generally, the matched filtering approach entails exploring an extensive parameter space for all resolvable sources, incurring a substantial cost owing to the generation of GW waveform templates. To alleviate the challenge, we make an attempt to perform parameter inference for coalescing massive black hole binaries (MBHBs) using deep learning. The model trained in this work has the capability to produce 50,000 posterior samples for redshifted total mass, mass ratio, coalescence time and luminosity distance of a MBHB in about twenty seconds. Our model can serve as a potent data pre-processing tool, reducing the volume of parameter space by more than four orders of magnitude for MBHB signals with a signal-to-noise ratio larger than 100. Moreover, the model exhibits robustness when handling input data that contains multiple MBHB signals.

astro-ph.IM↗

arXiv2023

Fast Matrix Multiplication Without Tears: A Constraint Programming Approach

It is known that the multiplication of an $N \times M$ matrix with an $M \times P$ matrix can be performed using fewer multiplications than what the naive $NMP$ approach suggests. The most famous instance of this is Strassen's algorithm for multiplying two $2\times 2$ matrices in 7 instead of 8 multiplications. This gives rise to the constraint satisfaction problem of fast matrix multiplication, where a set of $R < NMP$ multiplication terms must be chosen and combined such that they satisfy correctness constraints on the output matrix. Despite its highly combinatorial nature, this problem has not been exhaustively examined from that perspective, as evidenced for example by the recent deep reinforcement learning approach of AlphaTensor. In this work, we propose a simple yet novel Constraint Programming approach to find non-commutative algorithms for fast matrix multiplication or provide proof of infeasibility otherwise. We propose a set of symmetry-breaking constraints and valid inequalities that are particularly helpful in proving infeasibility. On the feasible side, we find that exploiting solver performance variability in conjunction with a sparsity-based problem decomposition enables finding solutions for larger (feasible) instances of fast matrix multiplication. Our experimental results using CP Optimizer demonstrate that we can find fast matrix multiplication algorithms for matrices up to $3\times 3$ in a short amount of time.

cs.AI↗

arXiv2023

Adaptive Region Selection for Active Learning in Whole Slide Image Semantic Segmentation

The process of annotating histological gigapixel-sized whole slide images (WSIs) at the pixel level for the purpose of training a supervised segmentation model is time-consuming. Region-based active learning (AL) involves training the model on a limited number of annotated image regions instead of requesting annotations of the entire images. These annotation regions are iteratively selected, with the goal of optimizing model performance while minimizing the annotated area. The standard method for region selection evaluates the informativeness of all square regions of a specified size and then selects a specific quantity of the most informative regions. We find that the efficiency of this method highly depends on the choice of AL step size (i.e., the combination of region size and the number of selected regions per WSI), and a suboptimal AL step size can result in redundant annotation requests or inflated computation costs. This paper introduces a novel technique for selecting annotation regions adaptively, mitigating the reliance on this AL hyperparameter. Specifically, we dynamically determine each region by first identifying an informative area and then detecting its optimal bounding box, as opposed to selecting regions of a uniform predefined shape and size as in the standard method. We evaluate our method using the task of breast cancer metastases segmentation on the public CAMELYON16 dataset and show that it consistently achieves higher sampling efficiency than the standard method across various AL step sizes. With only 2.6\% of tissue area annotated, we achieve full annotation performance and thereby substantially reduce the costs of annotating a WSI dataset. The source code is available at https://github.com/DeepMicroscopy/AdaptiveRegionSelection.

cs.CV↗

arXiv2023

Gas-Kinetic Scheme for Partially Ionized Plasma in Hydrodynamic Regime

Most plasmas are only partially ionized. To better understand the dynamics of these plasmas, the behaviors of a mixture of neutral species and plasma in ideal magnetohydrodynamic states are investigated. The current approach is about the construction of coupled kinetic models for the neutral gas, electron, and proton, and the development of the corresponding gas-kinetic scheme (GKS) for the solution in the continuum flow regime. The scheme is validated in the 1D Riemann problem for an enlarged system with the interaction from the Euler waves of the neutral gas and magnetohydrodynamic ones of the plasma. Additionally, the Orszag-Tang vortex problem across different ionized states is tested to examine the influence of neutrals on the MHD wave evolution. These tests demonstrate that the proposed scheme can capture the fundamental features of ideal partially ionized plasma, and a transition in the wave structure from the ideal MHD solution of the fully ionized plasma to the Euler solution of the neutral gas is obtained.

physics.comp-ph↗

arXiv2023

GujiBERT and GujiGPT: Construction of Intelligent Information Processing Foundation Language Models for Ancient Texts

In the context of the rapid development of large language models, we have meticulously trained and introduced the GujiBERT and GujiGPT language models, which are foundational models specifically designed for intelligent information processing of ancient texts. These models have been trained on an extensive dataset that encompasses both simplified and traditional Chinese characters, allowing them to effectively handle various natural language processing tasks related to ancient books, including but not limited to automatic sentence segmentation, punctuation, word segmentation, part-of-speech tagging, entity recognition, and automatic translation. Notably, these models have exhibited exceptional performance across a range of validation tasks using publicly available datasets. Our research findings highlight the efficacy of employing self-supervised methods to further train the models using classical text corpora, thus enhancing their capability to tackle downstream tasks. Moreover, it is worth emphasizing that the choice of font, the scale of the corpus, and the initial model selection all exert significant influence over the ultimate experimental outcomes. To cater to the diverse text processing preferences of researchers in digital humanities and linguistics, we have developed three distinct categories comprising a total of nine model variations. We believe that by sharing these foundational language models specialized in the domain of ancient texts, we can facilitate the intelligent processing and scholarly exploration of ancient literary works and, consequently, contribute to the global dissemination of China's rich and esteemed traditional culture in this new era.

cs.CL↗

arXiv2023

Rydberg atom-based radio frequency sensors: amplitude regime sensing

Rydberg atom-based radio frequency electromagnetic field sensors are drawing wide-spread interest because of their unique properties, such as small size, dielectric construction, and self-calibration. These photonic sensors use lasers to prepare atoms and read out the atomic response to a radio frequency electromagnetic field based on electromagnetically induced transparency, or related phenomena. Much of the theoretical work has focused on the Autler-Townes splitting induced by the radio frequency wave. The amplitude regime, where the change in transmission observed on resonance is measured to determine electric field strength, has received less attention. In this paper, we deliver analytic expressions that are useful for calculating the absorption coefficient and sensitivity in the amplitude regime. We describe the approximations that we applied to obtain the analytic expressions and demonstrate their validity over a large range of the interesting parameter space. The effect of the thermal motion of the atoms is explicitly addressed. Residual Doppler shifts are shown to limit sensitivity. An analytic expression for the amplitude regime of Rydberg atom-based sensing has not, to our knowledge, been obtained previously. The expressions, approximations and descriptions presented in the paper are important for maximizing the sensitivity of Rydberg atom-based sensors and for providing insight into the physics of multi-level interference phenomena.

physics.atom-ph↗

arXiv2023

Entanglement Transition and Replica Wormhole in the Dissipative Sachdev-Ye-Kitaev Model

Recent discoveries have highlighted the significance of replica wormholes in resolving the information paradox and establishing the unitarity of black hole evaporation. In this letter, we propose the dissipative Sachdev-Ye-Kitaev model (SYK) as a minimal quantum model that exhibits entanglement dynamics with features qualitatively similar to replica wormholes. As a demonstration, we investigate the entanglement growth of a pair of dissipative SYK models initialized in a thermofield double state (TFD). In the regime of large $N$ with weak dissipation, we observe a first-order entanglement transition characterized by a switch of the dominant saddle point: from replica diagonal solutions for short times to replica wormhole-like off-diagonal solutions for long times. Furthermore, we show that signature of replica wormholes persists even at moderate $N \lesssim 30$ by using the Monte Carlo quantum trajectory method. Our work paves the way for explorations of replica wormhole physics in quantum simulators.

quant-ph↗

arXiv2023

WiCo: Win-win Cooperation of Bottom-up and Top-down Referring Image Segmentation

The top-down and bottom-up methods are two mainstreams of referring segmentation, while both methods have their own intrinsic weaknesses. Top-down methods are chiefly disturbed by Polar Negative (PN) errors owing to the lack of fine-grained cross-modal alignment. Bottom-up methods are mainly perturbed by Inferior Positive (IP) errors due to the lack of prior object information. Nevertheless, we discover that two types of methods are highly complementary for restraining respective weaknesses but the direct average combination leads to harmful interference. In this context, we build Win-win Cooperation (WiCo) to exploit complementary nature of two types of methods on both interaction and integration aspects for achieving a win-win improvement. For the interaction aspect, Complementary Feature Interaction (CFI) provides fine-grained information to top-down branch and introduces prior object information to bottom-up branch for complementary feature enhancement. For the integration aspect, Gaussian Scoring Integration (GSI) models the gaussian performance distributions of two branches and weightedly integrates results by sampling confident scores from the distributions. With our WiCo, several prominent top-down and bottom-up combinations achieve remarkable improvements on three common datasets with reasonable extra costs, which justifies effectiveness and generality of our method.

cs.CV↗