arXiv subjects

Yuchen Zhou

Publications and source records attributed to Yuchen Zhou.

At least 73 records · Page 4Linked to original sources

arXiv2024

CLAP: Learning Transferable Binary Code Representations with Natural Language Supervision

Binary code representation learning has shown significant performance in binary analysis tasks. But existing solutions often have poor transferability, particularly in few-shot and zero-shot scenarios where few or no training samples are available for the tasks. To address this problem, we present CLAP (Contrastive Language-Assembly Pre-training), which employs natural language supervision to learn better representations of binary code (i.e., assembly code) and get better transferability. At the core, our approach boosts superior transfer learning capabilities by effectively aligning binary code with their semantics explanations (in natural language), resulting a model able to generate better embeddings for binary code. To enable this alignment training, we then propose an efficient dataset engine that could automatically generate a large and diverse dataset comprising of binary code and corresponding natural language explanations. We have generated 195 million pairs of binary code and explanations and trained a prototype of CLAP. The evaluations of CLAP across various downstream tasks in binary analysis all demonstrate exceptional performance. Notably, without any task-specific training, CLAP is often competitive with a fully supervised baseline, showing excellent transferability. We release our pre-trained model and code at https://github.com/Hustcw/CLAP.

cs.SE↗

arXiv2023

How Far Have We Gone in Vulnerability Detection Using Large Language Models

As software becomes increasingly complex and prone to vulnerabilities, automated vulnerability detection is critically important, yet challenging. Given the significant successes of large language models (LLMs) in various tasks, there is growing anticipation of their efficacy in vulnerability detection. However, a quantitative understanding of their potential in vulnerability detection is still missing. To bridge this gap, we introduce a comprehensive vulnerability benchmark VulBench. This benchmark aggregates high-quality data from a wide range of CTF (Capture-the-Flag) challenges and real-world applications, with annotations for each vulnerable function detailing the vulnerability type and its root cause. Through our experiments encompassing 16 LLMs and 6 state-of-the-art (SOTA) deep learning-based models and static analyzers, we find that several LLMs outperform traditional deep learning approaches in vulnerability detection, revealing an untapped potential in LLMs. This work contributes to the understanding and utilization of LLMs for enhanced software security.

cs.AI↗

arXiv2023

Visualization of Mesoscopic Conductivity Fluctuations in Amorphous Semiconductor Thin-Film Transistors

Charge transport in amorphous semiconductors is considerably more complicated than process in crystalline materials due to abundant localized states. In addition to device-scale characterization, spatially resolved measurements are important to unveil electronic properties. Here, we report gigahertz conductivity mapping in amorphous indium gallium zinc oxide (a-IGZO) thin-film transistors by microwave impedance microscopy (MIM), which probes conductivity without Schottky barrier's influence. The difference between dc and microwave conductivities reflects the efficacy of the injection barrier in an accumulation-mode transistor. The conductivity exhibits significant nanoscale inhomogeneity in the subthreshold regime, presumably due to trapping and releasing from localized states. The characteristic length scale of local fluctuations, as determined by autocorrelation analysis, is about 200 nm. Using random-barrier model, we can simulate the spatial variation of potential landscape, which underlies the mesoscopic conductivity distribution. Our work provides an intuitive way to understand the charge transport mechanism in amorphous semiconductors at microscopic level.

cond-mat.dis-nn↗

arXiv2023

PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation

Open-world 3D part segmentation is pivotal in diverse applications such as robotics and AR/VR. Traditional supervised methods often grapple with limited 3D data availability and struggle to generalize to unseen object categories. PartSLIP, a recent advancement, has made significant strides in zero- and few-shot 3D part segmentation. This is achieved by harnessing the capabilities of the 2D open-vocabulary detection module, GLIP, and introducing a heuristic method for converting and lifting multi-view 2D bounding box predictions into 3D segmentation masks. In this paper, we introduce PartSLIP++, an enhanced version designed to overcome the limitations of its predecessor. Our approach incorporates two major improvements. First, we utilize a pre-trained 2D segmentation model, SAM, to produce pixel-wise 2D segmentations, yielding more precise and accurate annotations than the 2D bounding boxes used in PartSLIP. Second, PartSLIP++ replaces the heuristic 3D conversion process with an innovative modified Expectation-Maximization algorithm. This algorithm conceptualizes 3D instance segmentation as unobserved latent variables, and then iteratively refines them through an alternating process of 2D-3D matching and optimization with gradient descent. Through extensive evaluations, we show that PartSLIP++ demonstrates better performance over PartSLIP in both low-shot 3D semantic and instance-based object part segmentation tasks. Code released at https://github.com/zyc00/PartSLIP2.

cs.CV↗

arXiv2023

Heteroskedastic Tensor Clustering

Tensor clustering, which seeks to extract underlying cluster structures from noisy tensor observations, has gained increasing attention. One extensively studied model for tensor clustering is the tensor block model, which postulates the existence of clustering structures along each mode and has found broad applications in areas like multi-tissue gene expression analysis and multilayer network analysis. However, currently available computationally feasible methods for tensor clustering either are limited to handling i.i.d. sub-Gaussian noise or suffer from suboptimal statistical performance, which restrains their utility in applications that have to deal with heteroskedastic data and/or low signal-to-noise-ratio (SNR). To overcome these challenges, we propose a two-stage method, named $\mathsf{High\text{-}order~HeteroClustering}$ ($\mathsf{HHC}$), which starts by performing tensor subspace estimation via a novel spectral algorithm called $\mathsf{Thresholded~Deflated\text{-}HeteroPCA}$, followed by approximate $k$-means to obtain cluster nodes. Encouragingly, our algorithm provably achieves exact clustering as long as the SNR exceeds the computational limit (ignoring logarithmic factors); here, the SNR refers to the ratio of the pairwise disparity between nodes to the noise level, and the computational limit indicates the lowest SNR that enables exact clustering with polynomial runtime. Comprehensive simulation and real-data experiments suggest that our algorithm outperforms existing algorithms across various settings, delivering more reliable clustering performance.

math.ST↗

arXiv2023

Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?

Vision-Language Models (VLMs) are trained on vast amounts of data captured by humans emulating our understanding of the world. However, known as visual illusions, human's perception of reality isn't always faithful to the physical world. This raises a key question: do VLMs have the similar kind of illusions as humans do, or do they faithfully learn to represent reality? To investigate this question, we build a dataset containing five types of visual illusions and formulate four tasks to examine visual illusions in state-of-the-art VLMs. Our findings have shown that although the overall alignment is low, larger models are closer to human perception and more susceptible to visual illusions. Our dataset and initial findings will promote a better understanding of visual illusions in humans and machines and provide a stepping stone for future computational models that can better align humans and machines in perceiving and communicating about the shared visual world. The code and data are available at https://github.com/vl-illusion/dataset.

cs.AI↗

arXiv2023

Efficiently Visualizing Large Graphs

Most existing graph visualization methods based on dimension reduction are limited to relatively small graphs due to performance issues. In this work, we propose a novel dimension reduction method for graph visualization, called t-Distributed Stochastic Graph Neighbor Embedding (t-SGNE). t-SGNE is specifically designed to visualize cluster structures in the graph. As a variant of the standard t-SNE method, t-SGNE avoids the time-consuming computations of pairwise similarity. Instead, it uses the neighbor structures of the graph to reduce the time complexity from quadratic to linear, thus supporting larger graphs. In addition, to suit t-SGNE, we combined Laplacian Eigenmaps with the shortest path algorithm in graphs to form the graph embedding algorithm ShortestPath Laplacian Eigenmaps Embedding (SPLEE). Performing SPLEE to obtain a high-dimensional embedding of the large-scale graph and then using t-SGNE to reduce its dimension for visualization, we are able to visualize graphs with up to 300K nodes and 1M edges within 5 minutes and achieve approximately 10% improvement in visualization quality. Codes and data are available at https://github.com/Charlie-XIAO/embedding-visualization-test.

cs.LG↗

arXiv2023

kTrans: Knowledge-Aware Transformer for Binary Code Embedding

Binary Code Embedding (BCE) has important applications in various reverse engineering tasks such as binary code similarity detection, type recovery, control-flow recovery and data-flow analysis. Recent studies have shown that the Transformer model can comprehend the semantics of binary code to support downstream tasks. However, existing models overlooked the prior knowledge of assembly language. In this paper, we propose a novel Transformer-based approach, namely kTrans, to generate knowledge-aware binary code embedding. By feeding explicit knowledge as additional inputs to the Transformer, and fusing implicit knowledge with a novel pre-training task, kTrans provides a new perspective to incorporating domain knowledge into a Transformer framework. We inspect the generated embeddings with outlier detection and visualization, and also apply kTrans to 3 downstream tasks: Binary Code Similarity Detection (BCSD), Function Type Recovery (FTR) and Indirect Call Recognition (ICR). Evaluation results show that kTrans can generate high-quality binary code embeddings, and outperforms state-of-the-art (SOTA) approaches on downstream tasks by 5.2%, 6.8%, and 12.6% respectively. kTrans is publicly available at: https://github.com/Learner0x5a/kTrans-release

cs.SE↗

arXiv2023

Quantifying the Roles of Visual, Linguistic, and Visual-Linguistic Complexity in Verb Acquisition

Children typically learn the meanings of nouns earlier than the meanings of verbs. However, it is unclear whether this asymmetry is a result of complexity in the visual structure of categories in the world to which language refers, the structure of language itself, or the interplay between the two sources of information. We quantitatively test these three hypotheses regarding early verb learning by employing visual and linguistic representations of words sourced from large-scale pre-trained artificial neural networks. Examining the structure of both visual and linguistic embedding spaces, we find, first, that the representation of verbs is generally more variable and less discriminable within domain than the representation of nouns. Second, we find that if only one learning instance per category is available, visual and linguistic representations are less well aligned in the verb system than in the noun system. However, in parallel with the course of human language development, if multiple learning instances per category are available, visual and linguistic representations become almost as well aligned in the verb system as in the noun system. Third, we compare the relative contributions of factors that may predict learning difficulty for individual words. A regression analysis reveals that visual variability is the strongest factor that internally drives verb learning, followed by visual-linguistic alignment and linguistic variability. Based on these results, we conclude that verb acquisition is influenced by all three sources of complexity, but that the variability of visual structure poses the most significant challenge for verb learning.

cs.CL↗

arXiv2023

Energy-Delay Tradeoff in Helper-Assisted NOMA-MEC Systems: A Four-Sided Matching Algorithm

This paper designs a helper-assisted resource allocation strategy in non-orthogonal multiple access (NOMA)-enabled mobile edge computing (MEC) systems, in order to guarantee the quality of service (QoS) of the energy/delay-sensitive user equipments (UEs). To achieve a tradeoff between the energy consumption and the delay, we introduce a novel performance metric, called \emph{energy-delay tradeoff}, which is defined as the weighted sum of energy consumption and delay. The joint optimization of user association, resource block (RB) assignment, power allocation, task assignment, and computation resource allocation is formulated as a mixed-integer nonlinear programming problem with the aim of minimizing the maximal energy-delay tradeoff. Due to the non-convexity of the formulated problem with coupled and 0-1 variables, this problem cannot be directly solved with polynomial complexity. To tackle this challenge, we first decouple the formulated problem into a power allocation, task assignment and computation resource allocation (PATACRA) subproblem. Then, with the solution obtained from the PATACRA subproblem, we equivalently reformulate the original problem as a discrete user association and RB assignment (DUARA) problem. For the PATACRA subproblem, an iterative parametric convex approximation (IPCA) algorithm is proposed. Then, based on the solution obtained from the PATACRA subproblem, we first model the DUARA problem as a four-sided matching problem, and then propose a low-complexity four-sided UE-RB-helper-server matching (FS-URHSM) algorithm. Theoretical analysis demonstrates that the proposed algorithms are guaranteed to converge to stable solutions with polynomial complexity. Finally, simulation results are provided to show the superior performance of our proposed algorithm in terms of the energy consumption and the delay.

cs.IT↗

arXiv2022

Sparse Group Lasso: Optimal Sample Complexity, Convergence Rate, and Statistical Inference

We study sparse group Lasso for high-dimensional double sparse linear regression, where the parameter of interest is simultaneously element-wise and group-wise sparse. This problem is an important instance of the simultaneously structured model -- an actively studied topic in statistics and machine learning. In the noiseless case, matching upper and lower bounds on sample complexity are established for the exact recovery of sparse vectors and for stable estimation of approximately sparse vectors, respectively. In the noisy case, upper and matching minimax lower bounds for estimation error are obtained. We also consider the debiased sparse group Lasso and investigate its asymptotic property for the purpose of statistical inference. Finally, numerical studies are provided to support the theoretical results.

math.ST↗

arXiv2022

Optimal High-order Tensor SVD via Tensor-Train Orthogonal Iteration

This paper studies a general framework for high-order tensor SVD. We propose a new computationally efficient algorithm, tensor-train orthogonal iteration (TTOI), that aims to estimate the low tensor-train rank structure from the noisy high-order tensor observation. The proposed TTOI consists of initialization via TT-SVD (Oseledets, 2011) and new iterative backward/forward updates. We develop the general upper bound on estimation error for TTOI with the support of several new representation lemmas on tensor matricizations. By developing a matching information-theoretic lower bound, we also prove that TTOI achieves the minimax optimality under the spiked tensor model. The merits of the proposed TTOI are illustrated through applications to estimation and dimension reduction of high-order Markov processes, numerical studies, and a real data example on New York City taxi travel records. The software of the proposed algorithm is available online$^6$.

math.ST↗

arXiv2021

Inference for Low-rank Tensors -- No Need to Debias

In this paper, we consider the statistical inference for several low-rank tensor models. Specifically, in the Tucker low-rank tensor PCA or regression model, provided with any estimates achieving some attainable error rate, we develop the data-driven confidence regions for the singular subspace of the parameter tensor based on the asymptotic distribution of an updated estimate by two-iteration alternating minimization. The asymptotic distributions are established under some essential conditions on the signal-to-noise ratio (in PCA model) or sample size (in regression model). If the parameter tensor is further orthogonally decomposable, we develop the methods and non-asymptotic theory for inference on each individual singular vector. For the rank-one tensor PCA model, we establish the asymptotic distribution for general linear forms of principal components and confidence interval for each entry of the parameter tensor. Finally, numerical simulations are presented to corroborate our theoretical discoveries. In all these models, we observe that different from many matrix/vector settings in existing work, debiasing is not required to establish the asymptotic distribution of estimates or to make statistical inference on low-rank tensors. In fact, due to the widely observed statistical-computational-gap for low-rank tensor estimation, one usually requires stronger conditions than the statistical (or information-theoretic) limit to ensure the computationally feasible estimation is achievable. Surprisingly, such conditions ``incidentally" render a feasible low-rank tensor inference without debiasing.

math.ST↗

arXiv2021

High-dimensional Log-Error-in-Variable Regression with Applications to Microbial Compositional Data Analysis

In microbiome and genomic studies, the regression of compositional data has been a crucial tool for identifying microbial taxa or genes that are associated with clinical phenotypes. To account for the variation in sequencing depth, the classic log-contrast model is often used where read counts are normalized into compositions. However, zero read counts and the randomness in covariates remain critical issues. In this article, we introduce a surprisingly simple, interpretable, and efficient method for the estimation of compositional data regression through the lens of a novel high-dimensional log-error-in-variable regression model. The proposed method provides both corrections on sequencing data with possible overdispersion and simultaneously avoids any subjective imputation of zero read counts. We provide theoretical justifications with matching upper and lower bounds for the estimation error. The merit of the procedure is illustrated through real data analysis and simulation studies.

stat.ME↗

arXiv2020

On the Non-asymptotic and Sharp Lower Tail Bounds of Random Variables

The non-asymptotic tail bounds of random variables play crucial roles in probability, statistics, and machine learning. Despite much success in developing upper bounds on tail probability in literature, the lower bounds on tail probabilities are relatively fewer. In this paper, we introduce systematic and user-friendly schemes for developing non-asymptotic lower bounds of tail probabilities. In addition, we develop sharp lower tail bounds for the sum of independent sub-Gaussian and sub-exponential random variables, which match the classic Hoeffding-type and Bernstein-type concentration inequalities, respectively. We also provide non-asymptotic matching upper and lower tail bounds for a suite of distributions, including gamma, beta, (regular, weighted, and noncentral) chi-square, binomial, Poisson, Irwin-Hall, etc. We apply the result to establish the matching upper and lower bounds for extreme value expectation of the sum of independent sub-Gaussian and sub-exponential random variables. A statistical application of signal identification from sparse heterogeneous mixtures is finally considered.

math.PR↗

arXiv2020

MLPerf Inference Benchmark

Machine-learning (ML) hardware and software system demand is burgeoning. Driven by ML applications, the number of different ML inference systems has exploded. Over 100 organizations are building ML inference chips, and the systems that incorporate existing models span at least three orders of magnitude in power consumption and five orders of magnitude in performance; they range from embedded devices to data-center solutions. Fueling the hardware are a dozen or more software frameworks and libraries. The myriad combinations of ML hardware and ML software make assessing ML-system performance in an architecture-neutral, representative, and reproducible manner challenging. There is a clear need for industry-wide standard ML benchmarking and evaluation criteria. MLPerf Inference answers that call. In this paper, we present our benchmarking method for evaluating ML inference systems. Driven by more than 30 organizations as well as more than 200 ML engineers and practitioners, MLPerf prescribes a set of rules and best practices to ensure comparability across systems with wildly differing architectures. The first call for submissions garnered more than 600 reproducible inference-performance measurements from 14 organizations, representing over 30 systems that showcase a wide range of capabilities. The submissions attest to the benchmark's flexibility and adaptability.

cs.LG↗

arXiv2019

Coalesced TLB to Exploit Diverse Contiguity of Memory Mapping

The miss rate of TLB is crucial to the performance of address translation for virtual memory. To reduce the TLB misses, improving translation coverage of TLB has been an primary approach. Many previous works focus on coalescing multiple contiguously mapped pages of the memory mapping into a modified entry, which function well if the assumed contiguity of memory mapping is given. Unfortunately, scenarios of applications are complicated and the produced contiguity diversify. To gain better performance of translation, in this paper, we first introduce a complex but prevalent type of contiguity, mixed contiguity. Then we propose a HW-SW hybrid coalesced TLB structure which works well on all observed types of contiguity including this type. In our evaluation, the proposed scheme, K-bit Aligned TLB, outperforms the state-of-the-art work by reducing at lease 27% TLB misses on average over it using 16 benchmarks.

cs.DC↗

arXiv2019

Optimal Analysis of Subset-Selection Based L_p Low Rank Approximation

We study the low rank approximation problem of any given matrix $A$ over $\mathbb{R}^{n\times m}$ and $\mathbb{C}^{n\times m}$ in entry-wise $\ell_p$ loss, that is, finding a rank-$k$ matrix $X$ such that $\|A-X\|_p$ is minimized. Unlike the traditional $\ell_2$ setting, this particular variant is NP-Hard. We show that the algorithm of column subset selection, which was an algorithmic foundation of many existing algorithms, enjoys approximation ratio $(k+1)^{1/p}$ for $1\le p\le 2$ and $(k+1)^{1-1/p}$ for $p\ge 2$. This improves upon the previous $O(k+1)$ bound for $p\ge 1$ \cite{chierichetti2017algorithms}. We complement our analysis with lower bounds; these bounds match our upper bounds up to constant $1$ when $p\geq 2$. At the core of our techniques is an application of \emph{Riesz-Thorin interpolation theorem} from harmonic analysis, which might be of independent interest to other algorithmic designs and analysis more broadly. As a consequence of our analysis, we provide better approximation guarantees for several other algorithms with various time complexity. For example, to make the algorithm of column subset selection computationally efficient, we analyze a polynomial time bi-criteria algorithm which selects $O(k\log m)$ columns. We show that this algorithm has an approximation ratio of $O((k+1)^{1/p})$ for $1\le p\le 2$ and $O((k+1)^{1-1/p})$ for $p\ge 2$. This improves over the best-known bound with an $O(k+1)$ approximation ratio. Our bi-criteria algorithm also implies an exact-rank method in polynomial time with a slightly larger approximation ratio.

cs.LG↗