arXiv subjects

Jun Liu

Publications and source records attributed to Jun Liu.

At least 379 records · Page 21Linked to original sources

arXiv2024

One-Sided Device-Independent Random Number Generation Through Fiber Channels

Randomness is an essential resource and plays important roles in various applications ranging from cryptography to simulation of complex systems. Certified randomness from quantum process is ensured to have the element of privacy but usually relies on the device's behavior. To certify randomness without the characterization for device, it is crucial to realize the one-sided device-independent random number generation based on quantum steering, which guarantees security of randomness and relaxes the demands of one party's device. Here, we distribute quantum steering between two distant users through a 2 km fiber channel and generate quantum random numbers at the remote station with untrustworthy device. We certify the steering-based randomness by reconstructing covariance matrix of the Gaussian entangled state shared between distant parties. Then, the quantum random numbers with a generation rate of 7.06 Mbits/s are extracted from the measured amplitude quadrature fluctuation of the state owned by the remote party. Our results demonstrate the first realization of steering-based random numbers extraction in a practical fiber channel, which paves the way to the quantum random numbers generation in asymmetric networks.

quant-ph↗

arXiv2024

Fast and Efficient 2-bit LLM Inference on GPU: 2/4/16-bit in a Weight Matrix with Asynchronous Dequantization

Large language models (LLMs) have demonstrated impressive abilities in various domains while the inference cost is expensive. Many previous studies exploit quantization methods to reduce LLM inference cost by reducing latency and memory consumption. Applying 2-bit single-precision weight quantization brings >3% accuracy loss, so the state-of-the-art methods use mixed-precision methods for LLMs (e.g. Llama2-7b, etc.) to improve the accuracy. However, challenges still exist: (1) Uneven distribution in weight matrix. (2) Large speed degradation by adding sparse outliers. (3) Time-consuming dequantization operations on GPUs. To tackle these challenges and enable fast and efficient LLM inference on GPUs, we propose the following techniques in this paper. (1) Intra-weight mixed-precision quantization. (2) Exclusive 2-bit sparse outlier with minimum speed degradation. (3) Asynchronous dequantization. We conduct extensive experiments on different model families (e.g. Llama3, etc.) and model sizes. We achieve 2.91-bit for each weight considering all scales/zeros for different models with negligible loss. As a result, with our 2/4/16 mixed-precision quantization for each weight matrix and asynchronous dequantization during inference, our design achieves an end-to-end speedup for Llama2-7b is 1.74x over the original model, and we reduce both runtime cost and total cost by up to 2.53x and 2.29x with less GPU requirements.

cs.LG↗

arXiv2024

COSMIC: Compress Satellite Images Efficiently via Diffusion Compensation

With the rapidly increasing number of satellites in space and their enhanced capabilities, the amount of earth observation images collected by satellites is exceeding the transmission limits of satellite-to-ground links. Although existing learned image compression solutions achieve remarkable performance by using a sophisticated encoder to extract fruitful features as compression and using a decoder to reconstruct, it is still hard to directly deploy those complex encoders on current satellites' embedded GPUs with limited computing capability and power supply to compress images in orbit. In this paper, we propose COSMIC, a simple yet effective learned compression solution to transmit satellite images. We first design a lightweight encoder (i.e. reducing FLOPs by 2.6~5x) on satellite to achieve a high image compression ratio to save satellite-to-ground links. Then, for reconstructions on the ground, to deal with the feature extraction ability degradation due to simplifying encoders, we propose a diffusion-based model to compensate image details when decoding. Our insight is that satellite's earth observation photos are not just images but indeed multi-modal data with a nature of Text-to-Image pairing since they are collected with rich sensor data (e.g. coordinates, timestamp, etc.) that can be used as the condition for diffusion generation. Extensive experiments show that COSMIC outperforms state-of-the-art baselines on both perceptual and distortion metrics.

eess.IV↗

arXiv2024

Fix the Tests: Augmenting LLMs to Repair Test Cases with Static Collector and Neural Reranker

During software evolution, it is advocated that test code should co-evolve with production code. In real development scenarios, test updating may lag behind production code changing, which may cause compilation failure or bring other troubles. Existing techniques based on pre-trained language models can be directly adopted to repair obsolete tests caused by such unsynchronized code changes, especially syntactic-related ones. However, the lack of task-oriented contextual information affects the repair accuracy on large-scale projects. Starting from an obsolete test, the key challenging task is precisely identifying and constructing Test-Repair-Oriented Contexts (TROCtxs) from the whole repository within a limited token size. In this paper, we propose SYNTER (SYNtactic-breaking-changes-induced TEst Repair), a novel approach based on LLMs to automatically repair obsolete test cases via precise and concise TROCtxs construction. Inspired by developers' programming practices, we design three types of TROCtx: class context, usage context, and environment context. Given an obsolete test case to repair, SYNTER firstly collects the related code information for each type of TROCtx through static analysis techniques automatically. Then, it generates reranking queries to identify the most relevant TROCtxs, which will be taken as the repair-required key contexts and be input to the large language model for the final test repair. To evaluate the effectiveness of SYNTER, we construct a benchmark dataset that contains a set of obsolete tests caused by syntactic breaking changes. The experimental results show that SYNTER outperforms baseline approaches both on textual- and intent-matching metrics. With the augmentation of constructed TROCtxs, hallucinations are reduced by 57.1%.

cs.SE↗

arXiv2024

Koopman-Based Learning of Infinitesimal Generators without Operator Logarithm

The Koopman operator has gained significant attention in recent years for its ability to verify evolutionary properties of continuous-time nonlinear systems by lifting state variables into an infinite-dimensional linear vector space. The challenge remains in providing estimations for transitional properties pertaining to the system's vector fields based on discrete-time observations. To retrieve such infinitesimal system transition information, leveraging the structure of Koopman operator learning, current literature focuses on developing techniques free of time derivatives through the use of the Koopman operator logarithm. However, the soundness of these methods has so far been demonstrated only for maintaining effectiveness within a restrictive function space, together with knowledge of the operator spectrum properties. To better adapt to the practical applications in learning and control of unknown systems, we propose a logarithm-free technique for learning the infinitesimal generator without disrupting the Koopman operator learning framework. This approach claims compatibility with other system verification tools using the same set of training data. We provide numerical examples to demonstrate its effectiveness in applications of system identification and stability prediction.

math.DS↗

arXiv2024

DisC-GS: Discontinuity-aware Gaussian Splatting

Recently, Gaussian Splatting, a method that represents a 3D scene as a collection of Gaussian distributions, has gained significant attention in addressing the task of novel view synthesis. In this paper, we highlight a fundamental limitation of Gaussian Splatting: its inability to accurately render discontinuities and boundaries in images due to the continuous nature of Gaussian distributions. To address this issue, we propose a novel framework enabling Gaussian Splatting to perform discontinuity-aware image rendering. Additionally, we introduce a Bézier-boundary gradient approximation strategy within our framework to keep the "differentiability" of the proposed discontinuity-aware rendering process. Extensive experiments demonstrate the efficacy of our framework.

cs.CV↗

arXiv2024

Aqua-Sim Fourth Generation: Towards General and Intelligent Simulation for Underwater Acoustic Networks

Simulators are essential to troubleshoot and optimize Underwater Acoustic Network (UAN) schemes (network protocols and communication technologies) before real field experiments. However, due to programming differences between the above two contents, most existing simulators concentrate on one while weakening the other, leading to non-generic simulations and biased performance results. Moreover, novel UAN schemes increasingly integrate Artificial Intelligence (AI) techniques, yet existing simulators lack support for necessary AI frameworks, failing to train and evaluate these intelligent methods. On the other hand, these novel schemes consider more UAN characteristics involving more complex parameter configurations, which also challenges simulators in flexibility and fineness. To keep abreast of advances in UANs, we propose the Fourth Generation (FG) ns-3-based simulator Aqua-Sim~FG, enhancing the general and intelligent simulation ability. On the basis of retaining previous generations' functions, we design a new general architecture, which is compatible with various programming languages, including MATLAB, C++, and Python. In this way, Aqua-Sim~FG provides a general environment to simulate communication technologies, network protocols, and AI models simultaneously. In addition, we expand six new features from node and communication levels by considering the latest UAN methods' requirements, which enhances the simulation flexibility and fineness of Aqua-Sim~FG. Experimental results show that Aqua-Sim~FG can simulate UANs' performance realistically, reflect intelligent methods' problems in real-ocean scenarios, and provide more effective troubleshooting and optimization for actual UANs. The basic simulator is available at https://github.com/JLU-smartocean/aqua-sim-fg.

cs.NI↗

arXiv2024

Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance.

cs.CV↗

arXiv2024

Efficient and Effective Retrieval of Dense-Sparse Hybrid Vectors using Graph-based Approximate Nearest Neighbor Search

ANNS for embedded vector representations of texts is commonly used in information retrieval, with two important information representations being sparse and dense vectors. While it has been shown that combining these representations improves accuracy, the current method of conducting sparse and dense vector searches separately suffers from low scalability and high system complexity. Alternatively, building a unified index faces challenges with accuracy and efficiency. To address these issues, we propose a graph-based ANNS algorithm for dense-sparse hybrid vectors. Firstly, we propose a distribution alignment method to improve accuracy, which pre-samples dense and sparse vectors to analyze their distance distribution statistic, resulting in a 1%$\sim$9% increase in accuracy. Secondly, to improve efficiency, we design an adaptive two-stage computation strategy that initially computes dense distances only and later computes hybrid distances. Further, we prune the sparse vectors to speed up the calculation. Compared to naive implementation, we achieve $\sim2.1\times$ acceleration. Thorough experiments show that our algorithm achieves 8.9x$\sim$11.7x throughput at equal accuracy compared to existing hybrid vector search algorithms.

cs.IR↗

arXiv2024

A Digital Twin-based Intelligent Network Architecture for Underwater Acoustic Sensor Networks

Underwater acoustic sensor networks (UASNs) drive toward strong environmental adaptability, intelligence, and multifunctionality. However, due to unique UASN characteristics, such as long propagation delay, dynamic channel quality, and high attenuation, existing studies present untimeliness, inefficiency, and inflexibility in real practice. Digital twin (DT) technology is promising for UASNs to break the above bottlenecks by providing high-fidelity status prediction and exploring optimal schemes. In this article, we propose a Digital Twin-based Network Architecture (DTNA), enhancing UASNs' environmental adaptability, intelligence, and multifunctionality. By extracting real UASN information from local (node) and global (network) levels, we first design a layered architecture to improve the DT replica fidelity and UASN control flexibility. In local DT, we develop a resource allocation paradigm (RAPD), which rapidly perceives performance variations and iteratively optimizes allocation schemes to improve real-time environmental adaptability of resource allocation algorithms. In global DT, we aggregate decentralized local DT data and propose a collaborative Multi-agent reinforcement learning framework (CMFD) and a task-oriented network slicing (TNSD). CMFD patches scarce real data and provides extensive DT data to accelerate AI model training. TNSD unifies heterogeneous tasks' demand extraction and efficiently provides comprehensive network status, improving the flexibility of multi-task scheduling algorithms. Finally, practical and simulation experiments verify the high fidelity of DT. Compared with the original UASN architecture, experiment results demonstrate that DTNA can: (i) improve the timeliness and robustness of resource allocation; (ii) greatly reduce the training time of AI algorithms; (iii) more rapidly obtain network status for multi-task scheduling at a low cost.

cs.NI↗

arXiv2024

Measurement of gas properties for the ion-TPC of N$ν$DEx experiment

In the N$ν$DEx collaboration, a high-pressure gas TPC is being developed to search for the neutrinoless double beta decay. The use of electronegative $\mathrm{^{82}SeF_{6}}$ gas mandates an ion-TPC. The reconstruction of $z$ coordinate is to be realized exploiting the feature of multiple species of charge carriers. As the initial stage of the development, we studied the properties of the $\mathrm{SF_{6}}$ gas, which is non-toxic and has similar molecular structure to $\mathrm{SeF_{6}}$. In the paper we present the measurement of drift velocities and mobilities of the majority and minority negative charge carriers found in $\mathrm{SF_{6}}$ at a pressure of 750 Torr, slightly higher than the local atmospheric pressure. The reduced fields range between 3.0 and 5.5 Td. It was performed using a laser beam to ionize the gas inside a small TPC, with a drift length of 3.7 cm. A customized charge sensitive amplifier was developed to read out the anode signals induced by the slowly drifting ions. The reconstruction of $z$ coordinate using the difference in the velocities of the two carriers was also demonstrated.

physics.ins-det↗

arXiv2024

DEeR: Deviation Eliminating and Noise Regulating for Privacy-preserving Federated Low-rank Adaptation

Integrating low-rank adaptation (LoRA) with federated learning (FL) has received widespread attention recently, aiming to adapt pretrained foundation models (FMs) to downstream medical tasks via privacy-preserving decentralized training. However, owing to the direct combination of LoRA and FL, current methods generally undergo two problems, i.e., aggregation deviation, and differential privacy (DP) noise amplification effect. To address these problems, we propose a novel privacy-preserving federated finetuning framework called \underline{D}eviation \underline{E}liminating and Nois\underline{e} \underline{R}egulating (DEeR). Specifically, we firstly theoretically prove that the necessary condition to eliminate aggregation deviation is guaranteing the equivalence between LoRA parameters of clients. Based on the theoretical insight, a deviation eliminator is designed to utilize alternating minimization algorithm to iteratively optimize the zero-initialized and non-zero-initialized parameter matrices of LoRA, ensuring that aggregation deviation always be zeros during training. Furthermore, we also conduct an in-depth analysis of the noise amplification effect and find that this problem is mainly caused by the ``linear relationship'' between DP noise and LoRA parameters. To suppress the noise amplification effect, we propose a noise regulator that exploits two regulator factors to decouple relationship between DP and LoRA, thereby achieving robust privacy protection and excellent finetuning performance. Additionally, we perform comprehensive ablated experiments to verify the effectiveness of the deviation eliminator and noise regulator. DEeR shows better performance on public medical datasets in comparison with state-of-the-art approaches. The code is available at https://github.com/CUHK-AIM-Group/DEeR.

cs.CV↗

arXiv2024

Bi-temporal Gaussian Feature Dependency Guided Change Detection in Remote Sensing Images

Change Detection (CD) enables the identification of alterations between images of the same area captured at different times. However, existing CD methods still struggle to address pseudo changes resulting from domain information differences in multi-temporal images and instances of detail errors caused by the loss and contamination of detail features during the upsampling process in the network. To address this, we propose a bi-temporal Gaussian distribution feature-dependent network (BGFD). Specifically, we first introduce the Gaussian noise domain disturbance (GNDD) module, which approximates distribution using image statistical features to characterize domain information, samples noise to perturb the network for learning redundant domain information, addressing domain information differences from a more fundamental perspective. Additionally, within the feature dependency facilitation (FDF) module, we integrate a novel mutual information difference loss ($L_{MI}$) and more sophisticated attention mechanisms to enhance the capabilities of the network, ensuring the acquisition of essential domain information. Subsequently, we have designed a novel detail feature compensation (DFC) module, which compensates for detail feature loss and contamination introduced during the upsampling process from the perspectives of enhancing local features and refining global features. The BGFD has effectively reduced pseudo changes and enhanced the detection capability of detail information. It has also achieved state-of-the-art performance on four publicly available datasets - DSIFN-CD, SYSU-CD, LEVIR-CD, and S2Looking, surpassing baseline models by +8.58%, +1.28%, +0.31%, and +3.76% respectively, in terms of the F1-Score metric.

cs.CV↗

arXiv2024

QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation

Automatically generated questions often suffer from problems such as unclear expression or factual inaccuracies, requiring a reliable and comprehensive evaluation of their quality. Human evaluation is widely used in the field of question generation (QG) and serves as the gold standard for automatic metrics. However, there is a lack of unified human evaluation criteria, which hampers consistent and reliable evaluations of both QG models and automatic metrics. To address this, we propose QGEval, a multi-dimensional Evaluation benchmark for Question Generation, which evaluates both generated questions and existing automatic metrics across 7 dimensions: fluency, clarity, conciseness, relevance, consistency, answerability, and answer consistency. We demonstrate the appropriateness of these dimensions by examining their correlations and distinctions. Through consistent evaluations of QG models and automatic metrics with QGEval, we find that 1) most QG models perform unsatisfactorily in terms of answerability and answer consistency, and 2) existing metrics fail to align well with human judgments when evaluating generated questions across the 7 dimensions. We expect this work to foster the development of both QG technologies and their evaluation.

cs.CL↗

arXiv2024

Adaptive radar detection of subspace-based distributed target in power heterogeneous clutter

This paper investigates the problem of adaptive detection of distributed targets in power heterogeneous clutter. In the considered scenario, all the data share the identical structure of clutter covariance matrix, but with varying and unknown power mismatches. To address this problem, we iteratively estimate all the unknowns, including the coordinate matrix of the target, the clutter covariance matrix, and the corresponding power mismatches, and propose three detectors based on the generalized likelihood ratio test (GLRT), Rao and the Wald tests. The results from simulated and real data both illustrate that the detectors based on GLRT and Rao test have higher probabilities of detection (PDs) than the existing competitors. Among them, the Rao test-based detector exhibits the best overall detection performance. We also analyze the impact of the target extended dimensions, the signal subspace dimensions, and the number of training samples on the detection performance. Furthermore, simulation experiments also demonstrate that the proposed detectors have a constant false alarm rate (CFAR) property for the structure of clutter covariance matrix.

stat.ME↗

arXiv2024

Formally Verified Physics-Informed Neural Control Lyapunov Functions

Control Lyapunov functions are a central tool in the design and analysis of stabilizing controllers for nonlinear systems. Constructing such functions, however, remains a significant challenge. In this paper, we investigate physics-informed learning and formal verification of neural network control Lyapunov functions. These neural networks solve a transformed Hamilton-Jacobi-Bellman equation, augmented by data generated using Pontryagin's maximum principle. Similar to how Zubov's equation characterizes the domain of attraction for autonomous systems, this equation characterizes the null-controllability set of a controlled system. This principled learning of neural network control Lyapunov functions outperforms alternative approaches, such as sum-of-squares and rational control Lyapunov functions, as demonstrated by numerical examples. As an intermediate step, we also present results on the formal verification of quadratic control Lyapunov functions, which, aided by satisfiability modulo theories solvers, can perform surprisingly well compared to more sophisticated approaches and efficiently produce global certificates of null-controllability.

eess.SY↗

arXiv2024

3D-CT-GPT: Generating 3D Radiology Reports through Integration of Large Vision-Language Models

Medical image analysis is crucial in modern radiological diagnostics, especially given the exponential growth in medical imaging data. The demand for automated report generation systems has become increasingly urgent. While prior research has mainly focused on using machine learning and multimodal language models for 2D medical images, the generation of reports for 3D medical images has been less explored due to data scarcity and computational complexities. This paper introduces 3D-CT-GPT, a Visual Question Answering (VQA)-based medical visual language model specifically designed for generating radiology reports from 3D CT scans, particularly chest CTs. Extensive experiments on both public and private datasets demonstrate that 3D-CT-GPT significantly outperforms existing methods in terms of report accuracy and quality. Although current methods are few, including the partially open-source CT2Rep and the open-source M3D, we ensured fair comparison through appropriate data conversion and evaluation methodologies. Experimental results indicate that 3D-CT-GPT enhances diagnostic accuracy and report coherence, establishing itself as a robust solution for clinical radiology report generation. Future work will focus on expanding the dataset and further optimizing the model to enhance its performance and applicability.

cs.CV↗

arXiv2024

The Polarised IKKT Matrix Model

We establish a correspondence between a supersymmetric mass deformation of the IKKT matrix integral at large $N$ and a background of Euclidean type IIB string theory. Both sides have sixteen supersymmetries and an $SO(3)\times SO(7)$ symmetry. In the limit of large mass the integral is dominated by a fuzzy sphere saddle point. This saddle corresponds to a Euclidean $D1$-brane in a finite, Euclidean, ellipsoidal cavity. The cavity is supported by three-form NSNS flux that polarises $N$ $D$-instantons into the $D1$-brane. We furthermore use supersymmetric localisation to show that the deformed matrix integral can be reduced to a moduli space integral, allowing exact results away from the large mass limit. At small mass the $D1$-branes can backreact on the geometry, and we discuss the possible formulation of a `timeless' holography in such regimes.

hep-th↗