Related papers: RacerF: Lightweight Static Data Race Detection for…

In this paper, we present "Graph Feature Preprocessor", a software library for detecting typical money laundering patterns in financial transaction graphs in real time. These patterns are used to produce a rich set of transaction features…

We investigate parameter-efficient fine-tuning (PEFT) methods that can provide good accuracy under limited computational and memory budgets in the context of large language models (LLMs). We present a new PEFT method called Robust…

Vector autoregressive (VAR) models are widely used in multivariate time series analysis for describing the short-time dynamics of the data. The reduced-rank VAR models are of particular interest when dealing with high-dimensional and highly…

This paper addresses the problem of provably efficient and practically good on-the-fly determinacy race detection in task parallel programs that use futures. Prior works determinacy race detection have mostly focused on either task parallel…

The popularity of dynamic malware analysis has grown significantly, as it enables analysts to observe the behavior of executing samples, thereby enhancing malware detection and classification decisions. With the continuous increase in new…

Temporal action detection (TAD) is a challenging task which aims to temporally localize and recognize the human action in untrimmed videos. Current mainstream one-stage TAD approaches localize and classify action proposals relying on…

Face detection, as a fundamental technology for various applications, is always deployed on edge devices which have limited memory storage and low computing power. This paper introduces a Light and Fast Face Detector (LFFD) for edge…

Static analysis approximates the results of a program by examining only its syntax. For example, control-flow analysis (CFA) determines which syntactic lambdas (for functional languages) or (for object-oriented) methods may be invoked at…

Network and system security are incredibly critical issues now. Due to the rapid proliferation of malware, traditional analysis methods struggle with enormous samples. In this paper, we propose four easy-to-extract and small-scale features,…

Semi-Markov CRF has been proposed as an alternative to the traditional Linear Chain CRF for text segmentation tasks such as Named Entity Recognition (NER). Unlike CRF, which treats text segmentation as token-level prediction, Semi-CRF…

The strong temporal consistency of surveillance video enables compelling compression performance with traditional methods, but downstream vision applications operate on decoded image frames with a high data rate. Since it is not…

Malware detection and classification into families are critical tasks in cybersecurity, complicated by the continual evolution of malware to evade detection. This evolution introduces concept drift, in which the statistical properties of…

We propose a novel convolutional neural network approach to address the fine-grained recognition problem of multi-view dynamic facial action unit detection. We leverage recent gains in large-scale object recognition by formulating the task…

Autonomous racing presents unique challenges due to its non-linear dynamics, the high speed involved, and the critical need for real-time decision-making under dynamic and unpredictable conditions. Most traditional Reinforcement Learning…

Over the last few years, research in automatic sleep scoring has mainly focused on developing increasingly complex deep learning architectures. However, recently these approaches achieved only marginal improvements, often at the expense of…

The focus of this paper is on intrinsic methods to detect overfitting. By intrinsic methods, we mean methods that rely only on the model and the training data, as opposed to traditional methods (we call them extrinsic methods) that rely on…

Detecting buffer overruns from a source code is one of the most common and yet challenging tasks in program analysis. Current approaches have mainly relied on rigid rules and handcrafted features devised by a few experts, limiting…

To efficiently combat the spread of LLM-generated misinformation, we present RADAR, a Retrieval-Augmented Detector with Adversarial Refinement for robust fake news detection. Our approach employs a generator that rewrites real articles with…

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips…

Variable screening methods have been shown to be effective in dimension reduction under the ultra-high dimensional setting. Most existing screening methods are designed to rank the predictors according to their individual contributions to…