Searcharxiv⌕ Search

arXiv subjects

Xinyi Wang

Publications and source records attributed to Xinyi Wang.

At least 181 records · Page 10Linked to original sources
arXiv2023

DANAA: Towards transferable attacks with double adversarial neuron attribution

While deep neural networks have excellent results in many fields, they are susceptible to interference from attacking samples resulting in erroneous judgments. Feature-level attacks are one of the effective attack types, which targets the learnt features in the hidden layers to improve its transferability across different models. Yet it is observed that the transferability has been largely impacted by the neuron importance estimation results. In this paper, a double adversarial neuron attribution attack method, termed `DANAA', is proposed to obtain more accurate feature importance estimation. In our method, the model outputs are attributed to the middle layer based on an adversarial non-linear path. The goal is to measure the weight of individual neurons and retain the features that are more important towards transferability. We have conducted extensive experiments on the benchmark datasets to demonstrate the state-of-the-art performance of our method. Our code is available at: https://github.com/Davidjinzb/DANAA

cs.CV↗
arXiv2023

Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning

Large Language Models (LLMs) have shown human-like reasoning abilities but still struggle with complex logical problems. This paper introduces a novel framework, Logic-LM, which integrates LLMs with symbolic solvers to improve logical problem-solving. Our method first utilizes LLMs to translate a natural language problem into a symbolic formulation. Afterward, a deterministic symbolic solver performs inference on the formulated problem. We also introduce a self-refinement module, which utilizes the symbolic solver's error messages to revise symbolic formalizations. We demonstrate Logic-LM's effectiveness on five logical reasoning datasets: ProofWriter, PrOntoQA, FOLIO, LogicalDeduction, and AR-LSAT. On average, Logic-LM achieves a significant performance boost of 39.2% over using LLM alone with standard prompting and 18.4% over LLM with chain-of-thought prompting. Our findings suggest that Logic-LM, by combining LLMs with symbolic logic, offers a promising avenue for faithful logical reasoning. Code and data are publicly available at https://github.com/teacherpeterpan/Logic-LLM.

cs.CL↗
arXiv2023

Magnetic Reconnection as the Key Mechanism in Sunspot Rotation Leading to Solar Eruption

The rotation of sunspots around their umbral center has long been considered as an important process in leading to solar eruptions, but the underlying mechanism remains unclear. A prevailing physical picture on how sunspot rotation leads to eruption is that, by twisting the coronal magnetic field lines from their footpoints, the rotation can build up a magnetic flux rope and drive it into some kinds of ideal magnetohydrodynamics (MHD) instabilities which initiate eruptions. Here with a data-inspired MHD simulation we studied the rotation of a large sunspot in solar active region NOAA 12158 leading to a major eruption, and found that it is distinct from prevailing theories based on ideal instabilities of twisted flux rope. The simulation suggests that, through successive rotation of the sunspot, the coronal magnetic field is sheared with a central current sheet created progressively within the sheared arcade before the eruption, but without forming a flux rope. Then the eruption is instantly triggered once fast reconnection sets in at the current sheet, while a highly twisted flux rope is created during the eruption. Furthermore, the simulation reveals an intermediate evolution stage between the quasi-static energy-storage phase and the impulsive eruption-acceleration phase. This stage may correspond to the slow-rise phase in observation and it enhances building up of the current sheet.

astro-ph.SR↗
arXiv2023

The Robust Semantic Segmentation UNCV2023 Challenge Results

This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural adversarial scenarios. The report presents the results of 19 submitted entries, with numerous techniques drawing inspiration from cutting-edge uncertainty quantification methodologies presented at prominent conferences in the fields of computer vision and machine learning and journals over the past few years. Within this document, the challenge is introduced, shedding light on its purpose and objectives, which primarily revolved around enhancing the robustness of semantic segmentation in urban scenes under varying natural adversarial conditions. The report then delves into the top-performing solutions. Moreover, the document aims to provide a comprehensive overview of the diverse solutions deployed by all participants. By doing so, it seeks to offer readers a deeper insight into the array of strategies that can be leveraged to effectively handle the inherent uncertainties associated with autonomous driving and semantic segmentation, especially within urban environments.

cs.CV↗
arXiv2023

Air Bumper: A Collision Detection and Reaction Framework for Autonomous MAV Navigation

Autonomous navigation in unknown environments with obstacles remains challenging for micro aerial vehicles (MAVs) due to their limited onboard computing and sensing resources. Although various collision avoidance methods have been developed, it is still possible for drones to collide with unobserved obstacles due to unpredictable disturbances, sensor limitations, and control uncertainty. Instead of completely avoiding collisions, this article proposes Air Bumper, a collision detection and reaction framework, for fully autonomous flight in 3D environments to improve the safety of drones. Our framework only utilizes the onboard inertial measurement unit (IMU) to detect and estimate collisions. We further design a collision recovery control for rapid recovery and collision-aware mapping to integrate collision information into general LiDAR-based sensing and planning frameworks. Our simulation and experimental results show that the quadrotor can rapidly detect, estimate, and recover from collisions with obstacles in 3D space and continue the flight smoothly with the help of the collision-aware map. Our Air Bumper will be released as open-source software on GitHub.

cs.RO↗
arXiv2023

FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning

Learning paradigms for large language models (LLMs) currently tend to fall within either in-context learning (ICL) or full fine-tuning. Each of these comes with their own trade-offs based on available data, model size, compute cost, ease-of-use, and final quality with neither solution performing well across-the-board. In this article, we first describe ICL and fine-tuning paradigms in a way that highlights their natural connections. Based on these connections, we propose a new learning paradigm called FIAT that fuses the best of these paradigms together, enabling prompt-engineered instructions and chain-of-thought reasoning with the very largest models while also using similar methods to perform parameter updates on a modestly-sized LLM with parameter-efficient tuning. We evaluate FIAT's effectiveness on a variety of multilingual tasks and observe that FIAT performs better than both ICL and fine-tuning at scales ranging from 100-10,000 training examples. We hope that FIAT provides a practical way of harnessing the full potential of LLMs without needing to make a hard choice between learning paradigms.

cs.CL↗
arXiv2023

QuCAT: A Combinatorial Testing Tool for Quantum Software

With the increased developments in quantum computing, the availability of systematic and automatic testing approaches for quantum programs is becoming increasingly essential. To this end, we present the quantum software testing tool QuCAT for combinatorial testing of quantum programs. QuCAT provides two functionalities of use. With the first functionality, the tool generates a test suite of a given strength (e.g., pair-wise). With the second functionality, it generates test suites with increasing strength until a failure is triggered or a maximum strength is reached. QuCAT uses two test oracles to check the correctness of test outputs. We assess the cost and effectiveness of QuCAT with 3 faulty versions of 5 quantum programs. Results show that combinatorial test suites with a low strength can find faults with limited cost, while a higher strength performs better to trigger some difficult faults with relatively higher cost. Repository: https://github.com/Simula-COMPLEX/qucat-tool Video: https://youtu.be/UsqgOudKLio

cs.SE↗
arXiv2023

Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies

Large language models (LLMs) have demonstrated remarkable performance across a wide array of NLP tasks. However, their efficacy is undermined by undesired and inconsistent behaviors, including hallucination, unfaithful reasoning, and toxic content. A promising approach to rectify these flaws is self-correction, where the LLM itself is prompted or guided to fix problems in its own output. Techniques leveraging automated feedback -- either produced by the LLM itself or some external system -- are of particular interest as they are a promising way to make LLM-based solutions more practical and deployable with minimal human feedback. This paper presents a comprehensive review of this emerging class of techniques. We analyze and taxonomize a wide array of recent work utilizing these strategies, including training-time, generation-time, and post-hoc correction. We also summarize the major applications of this strategy and conclude by discussing future directions and challenges.

cs.CL↗
arXiv2023

Multi-model fusion for Aerial Vision and Dialog Navigation based on human attention aids

Drones have been widely used in many areas of our daily lives. It relieves people of the burden of holding a controller all the time and makes drone control easier to use for people with disabilities or occupied hands. However, the control of aerial robots is more complicated compared to normal robots due to factors such as uncontrollable height. Therefore, it is crucial to develop an intelligent UAV that has the ability to talk to humans and follow natural language commands. In this report, we present an aerial navigation task for the 2023 ICCV Conversation History. Based on the AVDN dataset containing more than 3k recorded navigation trajectories and asynchronous human-robot conversations, we propose an effective method of fusion training of Human Attention Aided Transformer model (HAA-Transformer) and Human Attention Aided LSTM (HAA-LSTM) model, which achieves the prediction of the navigation routing points and human attention. The method not only achieves high SR and SPL metrics, but also shows a 7% improvement in GP metrics compared to the baseline model.

cs.CV↗
arXiv2023

Data-driven MHD simulation of a sunspot rotating active region leading to solar eruption

Solar eruptions are the leading driver of space weather, and it is vital for space weather forecast to understand in what conditions the solar eruptions can be produced and how they are initiated. The rotation of sunspots around their umbral center has long been considered as an important condition in causing solar eruptions. To unveil the underlying mechanisms, here we carried out a data-driven magnetohydrodynamics simulation for the event of a large sunspot with rotation for days in solar active region NOAA 12158 leading to a major eruption. The photospheric velocity as recovered from the time sequence of vector magnetograms are inputted directly at the bottom boundary of the numerical model as the driving flow. Our simulation successfully follows the long-term quasi-static evolution of the active region until the fast eruption, with magnetic field structure consistent with the observed coronal emission and onset time of simulated eruption matches rather well with the observations. Analysis of the process suggests that through the successive rotation of the sunspot the coronal magnetic field is sheared with a vertical current sheet created progressively, and once fast reconnection sets in at the current sheet, the eruption is instantly triggered, with a highly twisted flux rope originating from the eruption. This data-driven simulation stresses magnetic reconnection as the key mechanism in sunspot rotation leading to eruption.

astro-ph.SR↗
arXiv2023

UGC Quality Assessment: Exploring the Impact of Saliency in Deep Feature-Based Quality Assessment

The volume of User Generated Content (UGC) has increased in recent years. The challenge with this type of content is assessing its quality. So far, the state-of-the-art metrics are not exhibiting a very high correlation with perceptual quality. In this paper, we explore state-of-the-art metrics that extract/combine natural scene statistics and deep neural network features. We experiment with these by introducing saliency maps to improve perceptibility. We train and test our models using public datasets, namely, YouTube-UGC and KoNViD-1k. Preliminary results indicate that high correlations are achieved by using only deep features while adding saliency is not always boosting the performance. Our results and code will be made publicly available to serve as a benchmark for the research community and can be found on our project page: https://github.com/xinyiW915/SPIE-2023-Supplementary.

cs.CV↗
arXiv2023

Test Case Minimization with Quantum Annealers

Quantum annealers are specialized quantum computers for solving combinatorial optimization problems using special characteristics of quantum computing (QC), such as superposition, entanglement, and quantum tunneling. Theoretically, quantum annealers can outperform classical computers. However, the currently available quantum annealers are small-scale, i.e., they have limited quantum bits (qubits); hence, they currently cannot demonstrate the quantum advantage. Nonetheless, research is warranted to develop novel mechanisms to formulate combinatorial optimization problems for quantum annealing (QA). However, solving combinatorial problems with QA in software engineering remains unexplored. Toward this end, we propose BootQA, the very first effort at solving the test case minimization (TCM) problem with QA. In BootQA, we provide a novel formulation of TCM for QA, followed by devising a mechanism to incorporate bootstrap sampling to QA to optimize the use of qubits. We also implemented our TCM formulation in three other optimization processes: classical simulated annealing (SA), QA without problem decomposition, and QA with an existing D-Wave problem decomposition strategy, and conducted an empirical evaluation with three real-world TCM datasets. Results show that BootQA outperforms QA without problem decomposition and QA with the existing decomposition strategy in terms of effectiveness. Moreover, BootQA's effectiveness is similar to SA. Finally, BootQA has higher efficiency in terms of time when solving large TCM problems than the other three optimization processes.

cs.SE↗
arXiv2023

Non-parametric Probabilistic Time Series Forecasting via Innovations Representation

Probabilistic time series forecasting predicts the conditional probability distributions of the time series at a future time given past realizations. Such techniques are critical in risk-based decision-making and planning under uncertainties. Existing approaches are primarily based on parametric or semi-parametric time-series models that are restrictive, difficult to validate, and challenging to adapt to varying conditions. This paper proposes a nonparametric method based on the classic notion of {\em innovations} pioneered by Norbert Wiener and Gopinath Kallianpur that causally transforms a nonparametric random process to an independent and identical uniformly distributed {\em innovations process}. We present a machine-learning architecture and a learning algorithm that circumvent two limitations of the original Wiener-Kallianpur innovations representation: (i) the need for known probability distributions of the time series and (ii) the existence of a causal decoder that reproduces the original time series from the innovations representation. We develop a deep-learning approach and a Monte Carlo sampling technique to obtain a generative model for the predicted conditional probability distribution of the time series based on a weak notion of Wiener-Kallianpur innovations representation. The efficacy of the proposed probabilistic forecasting technique is demonstrated on a variety of electricity price datasets, showing marked improvement over leading benchmarks of probabilistic forecasting techniques.

cs.LG↗
arXiv2023

Approach to Hyperuniformity in a Metallic Glass-Forming Material Exhibiting a Fragile to Strong Glass Transition

We investigate a metallic glass-forming (GF) material (Al90Sm10) exhibiting a fragile-strong (FS) glass-formation by molecular dynamics simulation to better understand this highly distinctive pattern of glass-formation in which many of the usual phenomenological relations describing relaxation times and diffusion of OGF liquids no longer apply, and where instead genuine thermodynamic features are observed in response functions and little thermodynamic signature is exhibited at the glass transition temperature, Tg. Given the many unexpected similarities between the thermodynamics and dynamics of this metallic GF material with water, we first focus on the anomalous static scattering in this liquid, following recent studies on water, silicon and other FS GF liquids. In particular, we quantify the 'hyperuniformity index' H of our liquid which provides a quantitative measure of molecular 'jamming'. To gain insight into the T-dependence and magnitude of H, we also estimated another more familiar measure of particle localization, the Debye-Waller parameter $ $ describing the mean-square particle displacement on a timescale on the order of the fast relaxation time, and we also calculate H and $ $ for heated crystalline Cu. This comparative analysis between H and $ $ for crystalline and metallic glass materials allows us to understand the critical value of H on the order of $10^{-3}$ as being analogous to the Lindemann criterion for both the melting of crystals and the 'softening' of glasses. We further interpret the emergence of FS GF and liquid-liquid phase separation in this class of liquids to arise from a cooperative assembly process in the GF liquid.

cond-mat.soft↗
arXiv2023

XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languages

Data scarcity is a crucial issue for the development of highly multilingual NLP systems. Yet for many under-represented languages (ULs) -- languages for which NLP re-search is particularly far behind in meeting user needs -- it is feasible to annotate small amounts of data. Motivated by this, we propose XTREME-UP, a benchmark defined by: its focus on the scarce-data scenario rather than zero-shot; its focus on user-centric tasks -- tasks with broad adoption by speakers of high-resource languages; and its focus on under-represented languages where this scarce-data scenario tends to be most realistic. XTREME-UP evaluates the capabilities of language models across 88 under-represented languages over 9 key user-centric technologies including ASR, OCR, MT, and information access tasks that are of general utility. We create new datasets for OCR, autocomplete, semantic parsing, and transliteration, and build on and refine existing datasets for other tasks. XTREME-UP provides methodology for evaluating many modeling scenarios including text-only, multi-modal (vision, audio, and text),supervised parameter tuning, and in-context learning. We evaluate commonly used models on the benchmark. We release all code and scripts to train and evaluate models

cs.CL↗
arXiv2023

mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations

Multilingual sequence-to-sequence models perform poorly with increased language coverage and fail to consistently generate text in the correct target language in few-shot settings. To address these challenges, we propose mmT5, a modular multilingual sequence-to-sequence model. mmT5 utilizes language-specific modules during pre-training, which disentangle language-specific information from language-agnostic information. We identify representation drift during fine-tuning as a key limitation of modular generative models and develop strategies that enable effective zero-shot transfer. Our model outperforms mT5 at the same parameter sizes by a large margin on representative natural language understanding and generation tasks in 40+ languages. Compared to mT5, mmT5 raises the rate of generating text in the correct language under zero-shot settings from 7% to 99%, thereby greatly alleviating the source language hallucination problem.

cs.CL↗
arXiv2023

Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction

Continual few-shot relation extraction (RE) aims to continuously train a model for new relations with few labeled training data, of which the major challenges are the catastrophic forgetting of old relations and the overfitting caused by data sparsity. In this paper, we propose a new model, namely SCKD, to accomplish the continual few-shot RE task. Specifically, we design serial knowledge distillation to preserve the prior knowledge from previous models and conduct contrastive learning with pseudo samples to keep the representations of samples in different relations sufficiently distinguishable. Our experiments on two benchmark datasets validate the effectiveness of SCKD for continual few-shot RE and its superiority in knowledge transfer and memory utilization over state-of-the-art models.

cs.CL↗
arXiv2023

Sampling-based path planning under temporal logic constraints with real-time adaptation

Replanning in temporal logic tasks is extremely difficult during the online execution of robots. This study introduces an effective path planner that computes solutions for temporal logic goals and instantly adapts to non-static and partially unknown environments. Given prior knowledge and a task specification, the planner first identifies an initial feasible solution by growing a sampling-based search tree. While carrying out the computed plan, the robot maintains a solution library to continuously enhance the unfinished part of the plan and store backup plans. The planner updates existing plans when meeting unexpected obstacles or recognizing flaws in prior knowledge. Upon a high-level path is obtained, a trajectory generator tracks the path by dividing it into segments of motion primitives. Our planner is integrated into an autonomous mobile robot system, further deployed on a multicopter with limited onboard processing power. In simulation and real-world experiments, our planner is demonstrated to swiftly and effectively adjust to environmental uncertainties.

cs.RO↗