arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 847 records · Page 47Linked to original sources

arXiv2024

Distribution-consistency Structural Causal Models

In the field of causal modeling, potential outcomes (PO) and structural causal models (SCMs) stand as the predominant frameworks. However, these frameworks face notable challenges in practically modeling counterfactuals, formalized as parameters of the joint distribution of potential outcomes. Counterfactual reasoning holds paramount importance in contemporary decision-making processes, especially in scenarios that demand personalized incentives based on the joint values of $(Y(0), Y(1))$. This paper begins with an investigation of the PO and SCM frameworks for modeling counterfactuals. Through the analysis, we identify an inherent model capacity limitation, termed as the ``degenerative counterfactual problem'', emerging from the consistency rule that is the cornerstone of both frameworks. To address this limitation, we introduce a novel \textit{distribution-consistency} assumption, and in alignment with it, we propose the Distribution-consistency Structural Causal Models (DiscoSCMs) offering enhanced capabilities to model counterfactuals. To concretely reveal the enhanced model capacity, we introduce a new identifiable causal parameter, \textit{the probability of consistency}, which holds practical significance within DiscoSCM alone, showcased with a personalized incentive example. Furthermore, we provide a comprehensive set of theoretical results about the ``Ladder of Causation'' within the DiscoSCM framework. We hope it opens new avenues for future research of counterfactual modeling, ultimately enhancing our understanding of causality and its real-world applications.

cs.AI↗

arXiv2024

Effective Structured Prompting by Meta-Learning and Representative Verbalizer

Prompt tuning for pre-trained masked language models (MLM) has shown promising performance in natural language processing tasks with few labeled examples. It tunes a prompt for the downstream task, and a verbalizer is used to bridge the predicted token and label prediction. Due to the limited training data, prompt initialization is crucial for prompt tuning. Recently, MetaPrompting (Hou et al., 2022) uses meta-learning to learn a shared initialization for all task-specific prompts. However, a single initialization is insufficient to obtain good prompts for all tasks and samples when the tasks are complex. Moreover, MetaPrompting requires tuning the whole MLM, causing a heavy burden on computation and memory as the MLM is usually large. To address these issues, we use a prompt pool to extract more task knowledge and construct instance-dependent prompts via attention. We further propose a novel soft verbalizer (RepVerb) which constructs label embedding from feature embeddings directly. Combining meta-learning the prompt pool and RepVerb, we propose MetaPrompter for effective structured prompting. MetaPrompter is parameter-efficient as only the pool is required to be tuned. Experimental results demonstrate that MetaPrompter performs better than the recent state-of-the-arts and RepVerb outperforms existing soft verbalizers.

cs.CL↗

arXiv2024

A Spatial-Constraint Model for Manipulating Static Visualizations

We propose a spatial-constraint approach for modeling spatial-based interactions and enabling interactive visualizations, which involves the manipulation of visualizations through selection, filtering, navigation, arrangement, and aggregation. We proposes a system that activates static visualizations by adding intelligent interactions, which is achieved by associating static visual objects with forces. Our force-directed technique facilitates smooth animated transitions of the visualizations between different interaction states. We showcase the effectiveness of our technique through usage scenarios that involve activating visualizations in real-world settings.

cs.HC↗

arXiv2024

Astronomical Test with CMOS on the 60-cm Telescope at the Xinglong Observatory, NAOC

This work shows details of an evaluation of an observational system comprising a CMOS detector, 60-cm telescope, and filter complement. The system's photometric precision and differential photometric precision, and extinction coefficients were assessed through observations of Supersky flat fields, open clusters, standard stars, and exoplanets. Photometry was precision achieved at the 0.02 mag level, while differential photometry of 0.004 mag precision. Extinction was found to be agreed with previous studies conducted at Xinglong Observatory. Ultimately, the results demonstrate this observing system is capable of precision scientific observations with CCD across the optical wavelengths.

astro-ph.IM↗

arXiv2024

Efficiently Detecting Reentrancy Vulnerabilities in Complex Smart Contracts

Reentrancy vulnerability as one of the most notorious vulnerabilities, has been a prominent topic in smart contract security research. Research shows that existing vulnerability detection presents a range of challenges, especially as smart contracts continue to increase in complexity. Existing tools perform poorly in terms of efficiency and successful detection rates for vulnerabilities in complex contracts. To effectively detect reentrancy vulnerabilities in contracts with complex logic, we propose a tool named SliSE. SliSE's detection process consists of two stages: Warning Search and Symbolic Execution Verification. In Stage I, SliSE utilizes program slicing to analyze the Inter-contract Program Dependency Graph (I-PDG) of the contract, and collects suspicious vulnerability information as warnings. In Stage II, symbolic execution is employed to verify the reachability of these warnings, thereby enhancing vulnerability detection accuracy. SliSE obtained the best performance compared with eight state-of-the-art detection tools. It achieved an F1 score of 78.65%, surpassing the highest score recorded by an existing tool of 9.26%. Additionally, it attained a recall rate exceeding 90% for detection of contracts on Ethereum. Overall, SliSE provides a robust and efficient method for detection of Reentrancy vulnerabilities for complex contracts.

cs.SE↗

arXiv2024

VLLaVO: Mitigating Visual Gap through LLMs

Recent advances achieved by deep learning models rely on the independent and identically distributed assumption, hindering their applications in real-world scenarios with domain shifts. To tackle this issue, cross-domain learning aims at extracting domain-invariant knowledge to reduce the domain shift between training and testing data. However, in visual cross-domain learning, traditional methods concentrate solely on the image modality, disregarding the potential benefits of incorporating the text modality. In this work, we propose VLLaVO, combining Vision language models and Large Language models as Visual cross-dOmain learners. VLLaVO uses vision-language models to convert images into detailed textual descriptions. A large language model is then finetuned on textual descriptions of the source/target domain generated by a designed instruction template. Extensive experimental results under domain generalization and unsupervised domain adaptation settings demonstrate the effectiveness of the proposed method.

cs.CV↗

arXiv2024

Task-Aware Low-Rank Adaptation of Segment Anything Model

The Segment Anything Model (SAM), with its remarkable zero-shot capability, has been proven to be a powerful foundation model for image segmentation tasks, which is an important task in computer vision. However, the transfer of its rich semantic information to multiple different downstream tasks remains unexplored. In this paper, we propose the Task-Aware Low-Rank Adaptation (TA-LoRA) method, which enables SAM to work as a foundation model for multi-task learning. Specifically, TA-LoRA injects an update parameter tensor into each layer of the encoder in SAM and leverages a low-rank tensor decomposition method to incorporate both task-shared and task-specific information. Furthermore, we introduce modified SAM (mSAM) for multi-task learning where we remove the prompt encoder of SAM and use task-specific no mask embeddings and mask decoder for each task. Extensive experiments conducted on benchmark datasets substantiate the efficacy of TA-LoRA in enhancing the performance of mSAM across multiple downstream tasks.

cs.CV↗

arXiv2024

Application of Quantum Machine Learning in a Higgs Physics Study at the CEPC

Machine learning has blossomed in recent decades and has become essential in many fields. It significantly solved some problems in particle physics -- particle reconstruction, event classification, etc. However, it is now time to break the limitation of conventional machine learning with quantum computing. A support-vector machine algorithm with a quantum kernel estimator (QSVM-Kernel) leverages high-dimensional quantum state space to identify a signal from backgrounds. In this study, we have pioneered employing this quantum machine learning algorithm to study the $e^{+}e^{-} \rightarrow ZH$ process at the Circular Electron-Positron Collider (CEPC), a proposed Higgs factory to study electroweak symmetry breaking of particle physics. Using 6 qubits on quantum computer simulators, we optimised the QSVM-Kernel algorithm and obtained a classification performance similar to the classical support-vector machine algorithm. Furthermore, we have validated the QSVM-Kernel algorithm using 6-qubits on quantum computer hardware from both IBM and Origin Quantum: the classification performances of both are approaching noiseless quantum computer simulators. In addition, the Origin Quantum hardware results are similar to the IBM Quantum hardware within the uncertainties in our study. Our study shows that state-of-the-art quantum computing technologies could be utilised by particle physics, a branch of fundamental science that relies on big experimental data.

hep-ex↗

arXiv2024

Conditional Score-Based Diffusion Model for Cortical Thickness Trajectory Prediction

Alzheimer's Disease (AD) is a neurodegenerative condition characterized by diverse progression rates among individuals, with changes in cortical thickness (CTh) closely linked to its progression. Accurately forecasting CTh trajectories can significantly enhance early diagnosis and intervention strategies, providing timely care. However, the longitudinal data essential for these studies often suffer from temporal sparsity and incompleteness, presenting substantial challenges in modeling the disease's progression accurately. Existing methods are limited, focusing primarily on datasets without missing entries or requiring predefined assumptions about CTh progression. To overcome these obstacles, we propose a conditional score-based diffusion model specifically designed to generate CTh trajectories with the given baseline information, such as age, sex, and initial diagnosis. Our conditional diffusion model utilizes all available data during the training phase to make predictions based solely on baseline information during inference without needing prior history about CTh progression. The prediction accuracy of the proposed CTh prediction pipeline using a conditional score-based model was compared for sub-groups consisting of cognitively normal, mild cognitive impairment, and AD subjects. The Bland-Altman analysis shows our diffusion-based prediction model has a near-zero bias with narrow 95% confidential interval compared to the ground-truth CTh in 6-36 months. In addition, our conditional diffusion model has a stochastic generative nature, therefore, we demonstrated an uncertainty analysis of patient-specific CTh prediction through multiple realizations.

eess.IV↗

arXiv2024

LEVA: Using Large Language Models to Enhance Visual Analytics

Visual analytics supports data analysis tasks within complex domain problems. However, due to the richness of data types, visual designs, and interaction designs, users need to recall and process a significant amount of information when they visually analyze data. These challenges emphasize the need for more intelligent visual analytics methods. Large language models have demonstrated the ability to interpret various forms of textual data, offering the potential to facilitate intelligent support for visual analytics. We propose LEVA, a framework that uses large language models to enhance users' VA workflows at multiple stages: onboarding, exploration, and summarization. To support onboarding, we use large language models to interpret visualization designs and view relationships based on system specifications. For exploration, we use large language models to recommend insights based on the analysis of system status and data to facilitate mixed-initiative exploration. For summarization, we present a selective reporting strategy to retrace analysis history through a stream visualization and generate insight reports with the help of large language models. We demonstrate how LEVA can be integrated into existing visual analytics systems. Two usage scenarios and a user study suggest that LEVA effectively aids users in conducting visual analytics.

cs.HC↗

arXiv2024

ERASOR++: Height Coding Plus Egocentric Ratio Based Dynamic Object Removal for Static Point Cloud Mapping

Mapping plays a crucial role in location and navigation within automatic systems. However, the presence of dynamic objects in 3D point cloud maps generated from scan sensors can introduce map distortion and long traces, thereby posing challenges for accurate mapping and navigation. To address this issue, we propose ERASOR++, an enhanced approach based on the Egocentric Ratio of Pseudo Occupancy for effective dynamic object removal. To begin, we introduce the Height Coding Descriptor, which combines height difference and height layer information to encode the point cloud. Subsequently, we propose the Height Stack Test, Ground Layer Test, and Surrounding Point Test methods to precisely and efficiently identify the dynamic bins within point cloud bins, thus overcoming the limitations of prior approaches. Through extensive evaluation on open-source datasets, our approach demonstrates superior performance in terms of precision and efficiency compared to existing methods. Furthermore, the techniques described in our work hold promise for addressing various challenging tasks or aspects through subsequent migration.

cs.CV↗

arXiv2024

SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting

We present SplattingAvatar, a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh, which renders over 300 FPS on a modern GPU and 30 FPS on a mobile device. We disentangle the motion and appearance of a virtual human with explicit mesh geometry and implicit appearance modeling with Gaussian Splatting. The Gaussians are defined by barycentric coordinates and displacement on a triangle mesh as Phong surfaces. We extend lifted optimization to simultaneously optimize the parameters of the Gaussians while walking on the triangle mesh. SplattingAvatar is a hybrid representation of virtual humans where the mesh represents low-frequency motion and surface deformation, while the Gaussians take over the high-frequency geometry and detailed appearance. Unlike existing deformation methods that rely on an MLP-based linear blend skinning (LBS) field for motion, we control the rotation and translation of the Gaussians directly by mesh, which empowers its compatibility with various animation techniques, e.g., skeletal animation, blend shapes, and mesh editing. Trainable from monocular videos for both full-body and head avatars, SplattingAvatar shows state-of-the-art rendering quality across multiple datasets.

cs.GR↗

arXiv2024

Dynamic Inertial Poser (DynaIP): Part-Based Motion Dynamics Learning for Enhanced Human Pose Estimation with Sparse Inertial Sensors

This paper introduces a novel human pose estimation approach using sparse inertial sensors, addressing the shortcomings of previous methods reliant on synthetic data. It leverages a diverse array of real inertial motion capture data from different skeleton formats to improve motion diversity and model generalization. This method features two innovative components: a pseudo-velocity regression model for dynamic motion capture with inertial sensors, and a part-based model dividing the body and sensor data into three regions, each focusing on their unique characteristics. The approach demonstrates superior performance over state-of-the-art models across five public datasets, notably reducing pose error by 19\% on the DIP-IMU dataset, thus representing a significant improvement in inertial sensor-based human pose estimation. Our codes are available at {\url{https://github.com/dx118/dynaip}}.

cs.CV↗

arXiv2024

Real-Time Adaptive Safety-Critical Control with Gaussian Processes in High-Order Uncertain Models

This paper presents an adaptive online learning framework for systems with uncertain parameters to ensure safety-critical control in non-stationary environments. Our approach consists of two phases. The initial phase is centered on a novel sparse Gaussian process (GP) framework. We first integrate a forgetting factor to refine a variational sparse GP algorithm, thus enhancing its adaptability. Subsequently, the hyperparameters of the Gaussian model are trained with a specially compound kernel, and the Gaussian model's online inferential capability and computational efficiency are strengthened by updating a solitary inducing point derived from new samples, in conjunction with the learned hyperparameters. In the second phase, we propose a safety filter based on high-order control barrier functions (HOCBFs), synergized with the previously trained learning model. By leveraging the compound kernel from the first phase, we effectively address the inherent limitations of GPs in handling high-dimensional problems for real-time applications. The derived controller ensures a rigorous lower bound on the probability of satisfying the safety specification. Finally, the efficacy of our proposed algorithm is demonstrated through real-time obstacle avoidance experiments executed using both a simulation platform and a real-world 7-DOF robot.

cs.LG↗

arXiv2024

Microcavity induced by few-layer GaSe crystal on silicon photonic crystal waveguide for efficient optical frequency conversion

We demonstrate the post-induction of high-quality microcavity on silicon photonic crystal (PC) waveguide by integrating few-layer GaSe crystal, which promises highly efficient on-chip optical frequency conversions. The integration of GaSe shifts the dispersion bands of the PC waveguide mode into the bandgap, resulting in localized modes confined by the bare PC waveguides. Thanks to the small contrast of refractive index at the boundaries of microcavity, it is reliably to obtain quality (Q) factors exceeding 10^4. With the enhanced light-GaSe interaction by the microcavity modes and high second-order nonlinearity of GaSe, remarkable second-harmonic generation (SHG) and sum-frequency generation (SFG) are achieved. A record-high on-chip SHG conversion efficiency of 131100% W^-1 is obtained, enabling the clear SHG imaging of the resonant modes with the pump of sub-milliwatts continuous-wave (CW) laser. Driven by a pump of on-resonance CW laser, strong SFGs are successfully carried out with the other pump of a CW laser spanning over the broad telecom-band. Broadband frequency conversion of an incoherent superluminescent light-emitting diode with low spectral power density is also realized in the integrated GaSe-PC waveguide. Our results are expected to provide new strategies for high-efficiency light-matter interactions, nonlinear photonics and light source generation in silicon photonic integrated circuits.

physics.optics↗

arXiv2024

Flexible Informed Trees (FIT*): Adaptive Batch-Size Approach in Informed Sampling-Based Path Planning

In path planning, anytime almost-surely asymptotically optimal planners dominate the benchmark of sampling-based planners. A notable example is Batch Informed Trees (BIT*), where planners iteratively determine paths to batches of vertices within the exploration area. However, utilizing a consistent batch size is inefficient for initial pathfinding and optimal performance, it relies on effective task allocation. This paper introduces Flexible Informed Trees (FIT*), a sampling-based planner that integrates an adaptive batch-size method to enhance the initial path convergence rate. FIT* employs a flexible approach in adjusting batch sizes dynamically based on the inherent dimension of the configuration spaces and the hypervolume of the n-dimensional hyperellipsoid. By applying dense and sparse sampling strategy, FIT* improves convergence rate while finding successful solutions faster with lower initial solution cost. This method enhances the planner's ability to handle confined, narrow spaces in the initial finding phase and increases batch vertices sampling frequency in the optimization phase. FIT* outperforms existing single-query, sampling-based planners on the tested problems in R^2 to R^8, and was demonstrated on a real-world mobile manipulation task.

cs.RO↗

arXiv2024

"It Felt Like Having a Second Mind": Investigating Human-AI Co-creativity in Prewriting with Large Language Models

Prewriting is the process of discovering and developing ideas before a first draft, which requires divergent thinking and often implies unstructured strategies such as diagramming, outlining, free-writing, etc. Although large language models (LLMs) have been demonstrated to be useful for a variety of tasks including creative writing, little is known about how users would collaborate with LLMs to support prewriting. The preferred collaborative role and initiative of LLMs during such a creativity process is also unclear. To investigate human-LLM collaboration patterns and dynamics during prewriting, we conducted a three-session qualitative study with 15 participants in two creative tasks: story writing and slogan writing. The findings indicated that during collaborative prewriting, there appears to be a three-stage iterative Human-AI Co-creativity process that includes Ideation, Illumination, and Implementation stages. This collaborative process champions the human in a dominant role, in addition to mixed and shifting levels of initiative that exist between humans and LLMs. This research also reports on collaboration breakdowns that occur during this process, user perceptions of using existing LLMs during Human-AI Co-creativity, and discusses design implications to support this co-creativity process.

cs.HC↗

arXiv2024

A Survey of Network Protocol Fuzzing: Model, Techniques and Directions

As one of the most successful and effective software testing techniques in recent years, fuzz testing has uncovered numerous bugs and vulnerabilities in modern software, including network protocol software. In contrast to other fuzzing targets, network protocol software exhibits its distinct characteristics and challenges, introducing a plethora of research questions that need to be addressed in the design and implementation of network protocol fuzzers. While some research work has evaluated and systematized the knowledge of general fuzzing techniques at a high level, there is a lack of similar analysis and summarization for fuzzing research specific to network protocols. This paper offers a comprehensive exposition of network protocol software's fuzzing-related features and conducts a systematic review of some representative advancements in network protocol fuzzing since its inception. We summarize state-of-the-art strategies and solutions in various aspects, propose a unified protocol fuzzing process model, and introduce the techniques involved in each stage of the model. At the same time, this paper also summarizes the promising research directions in the landscape of protocol fuzzing to foster exploration within the community for more efficient and intelligent modern network protocol fuzzing techniques.

cs.NI↗