arXiv subjects

Jue Zhang

Publications and source records attributed to Jue Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2024

Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks

The rise of large language models (LLMs) has revolutionized user interactions with knowledge-based systems, enabling chatbots to synthesize vast amounts of information and assist with complex, exploratory tasks. However, LLM-based chatbots often struggle to provide personalized support, particularly when users start with vague queries or lack sufficient contextual information. This paper introduces the Collaborative Assistant for Personalized Exploration (CARE), a system designed to enhance personalization in exploratory tasks by combining a multi-agent LLM framework with a structured user interface. CARE's interface consists of a Chat Panel, Solution Panel, and Needs Panel, enabling iterative query refinement and dynamic solution generation. The multi-agent framework collaborates to identify both explicit and implicit user needs, delivering tailored, actionable solutions. In a within-subject user study with 22 participants, CARE was consistently preferred over a baseline LLM chatbot, with users praising its ability to reduce cognitive load, inspire creativity, and provide more tailored solutions. Our findings highlight CARE's potential to transform LLM-based systems from passive information retrievers to proactive partners in personalized problem-solving and exploration.

cs.HC↗

arXiv2024

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. Considering the redundancy in natural language, existing approaches compress prompts by removing tokens or lexical units according to their information entropy obtained from a causal language model such as LLaMa-7B. The challenge is that information entropy may be a suboptimal compression metric: (i) it only leverages unidirectional context and may fail to capture all essential information needed for prompt compression; (ii) it is not aligned with the prompt compression objective. To address these issues, we propose a data distillation procedure to derive knowledge from an LLM to compress prompts without losing crucial information, and meantime, introduce an extractive text compression dataset. We formulate prompt compression as a token classification problem to guarantee the faithfulness of the compressed prompt to the original one, and use a Transformer encoder as the base architecture to capture all essential information for prompt compression from the full bidirectional context. Our approach leads to lower latency by explicitly learning the compression objective with smaller models such as XLM-RoBERTa-large and mBERT. We evaluate our method on both in-domain and out-of-domain datasets, including MeetingBank, LongBench, ZeroScrolls, GSM8K, and BBH. Despite its small size, our model shows significant performance gains over strong baselines and demonstrates robust generalization ability across different LLMs. Additionally, our model is 3x-6x faster than existing prompt compression methods, while accelerating the end-to-end latency by 1.6x-2.9x with compression ratios of 2x-5x. Our code is available at https://aka.ms/LLMLingua-2.

cs.CL↗

arXiv2024

The Vision of Autonomic Computing: Can LLMs Make It a Reality?

The Vision of Autonomic Computing (ACV), proposed over two decades ago, envisions computing systems that self-manage akin to biological organisms, adapting seamlessly to changing environments. Despite decades of research, achieving ACV remains challenging due to the dynamic and complex nature of modern computing systems. Recent advancements in Large Language Models (LLMs) offer promising solutions to these challenges by leveraging their extensive knowledge, language understanding, and task automation capabilities. This paper explores the feasibility of realizing ACV through an LLM-based multi-agent framework for microservice management. We introduce a five-level taxonomy for autonomous service maintenance and present an online evaluation benchmark based on the Sock Shop microservice demo project to assess our framework's performance. Our findings demonstrate significant progress towards achieving Level 3 autonomy, highlighting the effectiveness of LLMs in detecting and resolving issues within microservice architectures. This study contributes to advancing autonomic computing by pioneering the integration of LLMs into microservice management frameworks, paving the way for more adaptive and self-managing computing systems. The code will be made available at https://aka.ms/ACV-LLM.

cs.AI↗

arXiv2024

AutoRAG-HP: Automatic Online Hyper-Parameter Tuning for Retrieval-Augmented Generation

Recent advancements in Large Language Models have transformed ML/AI development, necessitating a reevaluation of AutoML principles for the Retrieval-Augmented Generation (RAG) systems. To address the challenges of hyper-parameter optimization and online adaptation in RAG, we propose the AutoRAG-HP framework, which formulates the hyper-parameter tuning as an online multi-armed bandit (MAB) problem and introduces a novel two-level Hierarchical MAB (Hier-MAB) method for efficient exploration of large search spaces. We conduct extensive experiments on tuning hyper-parameters, such as top-k retrieved documents, prompt compression ratio, and embedding methods, using the ALCE-ASQA and Natural Questions datasets. Our evaluation from jointly optimization all three hyper-parameters demonstrate that MAB-based online learning methods can achieve Recall@5 $\approx 0.8$ for scenarios with prominent gradients in search space, using only $\sim20\%$ of the LLM API calls required by the Grid Search approach. Additionally, the proposed Hier-MAB approach outperforms other baselines in more challenging optimization scenarios. The code will be made available at https://aka.ms/autorag.

cs.CL↗

arXiv2024

TaskWeaver: A Code-First Agent Framework

Large Language Models (LLMs) have shown impressive abilities in natural language understanding and generation, leading to their widespread use in applications such as chatbots and virtual assistants. However, existing LLM frameworks face limitations in handling domain-specific data analytics tasks with rich data structures. Moreover, they struggle with flexibility to meet diverse user requirements. To address these issues, TaskWeaver is proposed as a code-first framework for building LLM-powered autonomous agents. It converts user requests into executable code and treats user-defined plugins as callable functions. TaskWeaver provides support for rich data structures, flexible plugin usage, and dynamic plugin selection, and leverages LLM coding capabilities for complex logic. It also incorporates domain-specific knowledge through examples and ensures the secure execution of generated code. TaskWeaver offers a powerful and flexible framework for creating intelligent conversational agents that can handle complex tasks and adapt to domain-specific scenarios. The code is open sourced at https://github.com/microsoft/TaskWeaver/.

cs.AI↗

arXiv2024

Demonstration of optical spring in an un-detuned cavity containing an optical parametric amplifier

Here we demonstrate the capacity to manipulate the optical spring (OS) effect by employing an optical parametric amplifier (OPA) within an optical cavity. We observed more than a factor of 2 increase in the OS frequency shift with the OPA. We also showed for the first time that the OS can be tuned by solely adjusting the OPA phase and showing an un-detuned cavity exhibiting an optical spring. The method can be applied to gravitational wave detectors in the signal recycling configuration to realize narrow bandwidth high sensitivity. The OS can be tuned to align the detector peak sensitivity frequency to known frequency continuous gravitational wave signals, dynamically tuned to track the gravitational wave signal from merging compact binaries or tuned to search for the post-merger signal of known binary coalescence.

physics.optics↗

arXiv2024

Experimental demonstration of the combined arm- and cavity-locking system for LISA

Laser frequency noise suppression is a critical requirement for the Laser Interferometer Space Antenna (LISA) mission to detect gravitational waves. The baseline laser stabilization is achieved using cavity pre-stabilization and a post-processing technique called Time-Delay-Interferometry (TDI). To enhance the margins for TDI, alternate laser locking schemes should be investigated. A novel stabilisation blending the excellent stability of the arm with the existing cavity reference has been shown theoretically to meet the first-generation TDI margins. This locking system was designed to be implemented as a firmware change and have minimal or no changes to the LISA hardware. This paper experimentally verifies the hybrid laser locking technique by utilizing two references - an optical cavity, and an interferometer with delay imparted using 10 km of optical fiber. The results indicate the viability of the combination of arm-cavity locking system for LISA. They show the key benefits envisioned by this technique; suppression of the cavity fluctuations by the arm sensor (by 21 dB in this demonstration) and reduction of Doppler pulling of the laser frequency, a key technical challenge for arm locking.

gr-qc↗

arXiv2024

RCInvestigator: Towards Better Investigation of Anomaly Root Causes in Cloud Computing Systems

Finding the root causes of anomalies in cloud computing systems quickly is crucial to ensure availability and efficiency since accurate root causes can guide engineers to take appropriate actions to address the anomalies and maintain customer satisfaction. However, it is difficult to investigate and identify the root causes based on large-scale and high-dimension monitoring data collected from complex cloud computing environments. Due to the inherently dynamic characteristics of cloud computing systems, the existing approaches in practice largely rely on manual analyses for flexibility and reliability, but massive unpredictable factors and high data complexity make the process time-consuming. Despite recent advances in automated detection and investigation approaches, the speed and quality of root cause analyses remain limited by the lack of expert involvement in these approaches. The limitations found in the current solutions motivate us to propose a visual analytics approach that facilitates the interactive investigation of the anomaly root causes in cloud computing systems. We identified three challenges, namely, a) modeling databases for the root cause investigation, b) inferring root causes from large-scale time series, and c) building comprehensible investigation results. In collaboration with domain experts, we addressed these challenges with RCInvestigator, a novel visual analytics system that establishes a tight collaboration between human and machine and assists experts in investigating the root causes of cloud computing system anomalies. We evaluated the effectiveness of RCInvestigator through two use cases based on real-world data and received positive feedback from experts.

cs.HC↗

arXiv2024

Towards Cloud Efficiency with Large-scale Workload Characterization

Cloud providers introduce features (e.g., Spot VMs, Harvest VMs, and Burstable VMs) and optimizations (e.g., oversubscription, auto-scaling, power harvesting, and overclocking) to improve efficiency and reliability. To effectively utilize these features, it's crucial to understand the characteristics of workloads running in the cloud. However, workload characteristics can be complex and depend on multiple signals, making manual characterization difficult and unscalable. In this study, we conduct the first large-scale examination of first-party workloads at Microsoft to understand their characteristics. Through an empirical study, we aim to answer the following questions: (1) What are the critical workload characteristics that impact efficiency and reliability on cloud platforms? (2) How do these characteristics vary across different workloads? (3) How can cloud platforms leverage these insights to efficiently characterize all workloads at scale? This study provides a deeper understanding of workload characteristics and their impact on cloud performance, which can aid in optimizing cloud services. Additionally, it identifies potential areas for future research.

cs.DC↗

arXiv2024

Workload Intelligence: Punching Holes Through the Cloud Abstraction

Today, cloud workloads are essentially opaque to the cloud platform. Typically, the only information the platform receives is the virtual machine (VM) type and possibly a decoration to the type (e.g., the VM is evictable). Similarly, workloads receive little to no information from the platform; generally, workloads might receive telemetry from their VMs or exceptional signals (e.g., shortly before a VM is evicted). The narrow interface between workloads and platforms has several drawbacks: (1) a surge in VM types and decorations in public cloud platforms complicates customer selection; (2) essential workload characteristics (e.g., low availability requirements, high latency tolerance) are often unspecified, hindering platform customization for optimized resource usage and cost savings; and (3) workloads may be unaware of potential optimizations or lack sufficient time to react to platform events. In this paper, we propose a framework, called Workload Intelligence (WI), for dynamic bi-directional communication between cloud workloads and cloud platform. Via WI, workloads can programmatically adjust their key characteristics, requirements, and even dynamically adapt behaviors like VM priorities. In the other direction, WI allows the platform to programmatically inform workloads about upcoming events, opportunities for optimization, among other scenarios. Because of WI, the cloud platform can drastically simplify its offerings, reduce its costs without fear of violating any workload requirements, and reduce prices to its customers on average by 48.8%.

cs.DC↗

arXiv2024

Does Lorentz-symmetric design boost network performance in jet physics?

In the deep learning era, improving the neural network performance in jet physics is a rewarding task as it directly contributes to more accurate physics measurements at the LHC. Recent research has proposed various network designs in consideration of the full Lorentz symmetry, but its benefit is still not systematically asserted, given that there remain many successful networks without taking it into account. We conduct a detailed study on the Lorentz-symmetric design. We propose two generalized approaches for modifying a network - these methods are experimented on Particle Flow Network, ParticleNet, and LorentzNet, and exhibit a general performance gain. We also reveal that the notable improvement attributed to the "pairwise mass" feature in the network is due to its introduction of a structure that fully complies with Lorentz symmetry. We confirm that Lorentz-symmetry preservation serves as a strong inductive bias of jet physics, hence calling for attention to such general recipes in future network designs.

hep-ph↗

arXiv2023

Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering

Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average due to its lack of specific domain knowledge. This issue has attracted widespread attention, but there are few relevant benchmarks available. In this paper, we provide a benchmark Question Answering (QA) dataset named MSQA, centered around Microsoft products and IT technical problems encountered by customers. This dataset contains industry cloud-specific QA knowledge, an area not extensively covered in general LLMs, making it well-suited for evaluating methods aiming to enhance LLMs' domain-specific capabilities. In addition, we propose a new model interaction paradigm that can empower LLM to achieve better performance on domain-specific tasks where it is not proficient. Extensive experiments demonstrate that the approach following our method outperforms the commonly used LLM with retrieval methods. We make our source code and sample data available at: https://aka.ms/Microsoft_QA.

cs.CL↗

arXiv2022

An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging

Deep learning methods have been increasingly adopted to study jets in particle physics. Since symmetry-preserving behavior has been shown to be an important factor for improving the performance of deep learning in many applications, Lorentz group equivariance - a fundamental spacetime symmetry for elementary particles - has recently been incorporated into a deep learning model for jet tagging. However, the design is computationally costly due to the analytic construction of high-order tensors. In this article, we introduce LorentzNet, a new symmetry-preserving deep learning model for jet tagging. The message passing of LorentzNet relies on an efficient Minkowski dot product attention. Experiments on two representative jet tagging benchmarks show that LorentzNet achieves the best tagging performance and improves significantly over existing state-of-the-art algorithms. The preservation of Lorentz symmetry also greatly improves the efficiency and generalization power of the model, allowing LorentzNet to reach highly competitive performance when trained on only a few thousand jets. Code and models are available at \url{https://github.com/sdogsq/LorentzNet-release}.

hep-ph↗

arXiv2021

Pseudo Supervised Solar Panel Mapping based on Deep Convolutional Networks with Label Correction Strategy in Aerial Images

Solar panel mapping has gained a rising interest in renewable energy field with the aid of remote sensing imagery. Significant previous work is based on fully supervised learning with classical classifiers or convolutional neural networks (CNNs), which often require manual annotations of pixel-wise ground-truth to provide accurate supervision. Weakly supervised methods can accept image-wise annotations which can help reduce the cost for pixel-level labelling. Inevitable performance gap, however, exists between weakly and fully supervised methods in mapping accuracy. To address this problem, we propose a pseudo supervised deep convolutional network with label correction strategy (PS-CNNLC) for solar panels mapping. It combines the benefits of both weak and strong supervision to provide accurate solar panel extraction. First, a convolutional neural network is trained with positive and negative samples with image-level labels. It is then used to automatically identify more positive samples from randomly selected unlabeled images. The feature maps of the positive samples are further processed by gradient-weighted class activation mapping to generate initial mapping results, which are taken as initial pseudo labels as they are generally coarse and incomplete. A progressive label correction strategy is designed to refine the initial pseudo labels and train an end-to-end target mapping network iteratively, thereby improving the model reliability. Comprehensive evaluations and ablation study conducted validate the superiority of the proposed PS-CNNLC.

eess.IV↗

arXiv2018

Searching for weak singlet charged scalar at lepton colliders

A weak singlet charged scalar exists in many new physics models beyond the Standard Model. The discovery potential of the singlet charged scalar is explored at future lepton colliders, e.g. the CEPC, ILC-350 and ILC-500. We demonstrate that one can discover the singlet charged scalar up to 118 GeV at the CEPC with an integrated luminosity of $5~\mathrm{ab}^{-1}$. At the ILC-350 and the ILC-500 with an integrated luminosity of $1~\mathrm{ab}^{-1}$ such a discovery limit can be further improved to 136 GeV and 160 GeV, respectively.

hep-ph↗

arXiv2018

Searching for Weak Singlet Charged Scalar at the Large Hadron Collider

Weak singlet charged scalar exists in many new physics models beyond the Standard Model. In this work we show that a light singlet charged scalar with mass above 65~GeV is still allowed by the LEP and LHC data. The interactions of the singlet charged scalar with the Standard Model particles are described by operators up to dimension-5. Dominant decay modes of the singlet charged scalar are obtained, and a subtlety involving field redefinition and gauge fixing due to a dimension-5 operator is also clarified. We demonstrate that it is promising to observe the singlet charged scalar at the LHC.

hep-ph↗

arXiv2018

Gravitational clustering of cosmic relic neutrinos in the Milky Way

The standard model of cosmology predicts the existence of cosmic neutrino background in the present Universe. To detect cosmic relic neutrinos in the vicinity of the Earth, it is necessary to evaluate the gravitational clustering effects on relic neutrinos in the Milky Way. Here we introduce a reweighting technique in the N-one-body simulation method, so that a single simulation can yield neutrino density profiles for different neutrino masses and phase space distributions. In light of current experimental results that favor small neutrino masses, the neutrino number density contrast around the Earth is found to be almost proportional to the square of neutrino mass. The density contrast-mass relation and the reweighting technique are useful for studying the phenomenology associated with the future detection of the cosmic neutrino background.

astro-ph.CO↗

arXiv2018

$ μ-τ$ Reflection Symmetry Embedded in Minimal Seesaw

We embed $μ-τ$ reflection symmetry into the minimal seesaw formalism, where two right-handed neutrinos are added to the Standard Model of particle physics. Assuming that both the left- and right-handed neutrino fields transform under $μ-τ$ reflection symmetry, we obtain the required forms of the neutrino Dirac mass matrix and the Majorana mass matrix for the right-handed neutrinos. To investigate the neutrino phenomenology at low energies, we first consider the breaking of $μ-τ$ reflection symmetry due to the renormalization group running, and then systematically study various breaking schemes by introducing explicit breaking terms at high energies.

hep-ph↗