Related papers: Interpretation-enabled Software Reuse Detection Ba…
Software vulnerabilities are a serious and crucial concern. Typically, in a program or function consisting of hundreds or thousands of source code statements, there are only a few statements causing the corresponding vulnerabilities. Most…
Recent advances in LLM watermarking methods such as SynthID-Text by Google DeepMind offer promising solutions for tracing the provenance of AI-generated text. However, our robustness assessment reveals that SynthID-Text is vulnerable to…
Image-text retrieval (ITR) is a task to retrieve the relevant images/texts, given the query from another modality. The conventional dense retrieval paradigm relies on encoding images and texts into dense representations using dual-stream…
The increasing prevalence of large language models (LLMs) has significantly advanced text generation, but the human-like quality of LLM outputs presents major challenges in reliably distinguishing between human-authored and LLM-generated…
A typical compiler flow relies on a uni-directional sequence of translation/optimization steps that lower the program abstract representation, making it hard to preserve higher-level program information across each transformation step. On…
By a locally recoverable code (LRC), we will in this paper, mean a linear code in which a given code symbol can be recovered by taking a linear combination of at most $r$ other code symbols with $r << k$. A natural extension is to the local…
Research Replication Prediction (RRP) is the task of predicting whether a published research result can be replicated or not. Building an interpretable neural text classifier for RRP promotes the understanding of why a research paper is…
We derive a lower bound on the amount of information accessed to repair failed nodes within a single rack from any number of helper racks in the rack-aware storage model that allows collective information processing in the nodes that share…
This paper presents a configuration-first framework for evaluating cross-backend compatibility in deep learning systems deployed on CPU, GPU, and compiled runtimes. The framework decouples experiments from code using YAML, supports both…
Existing real-time text detectors reconstruct text contours by shrink-masks directly, which simplifies the framework and can make the model run fast. However, the strong dependence on predicted shrink-masks leads to unstable detection…
System reuse and cost are very important in software product line design area. Developers goal is to increase system reuse and decreasing cost and efforts for building components from scratch for each software configuration. This can be…
Text reuse is a methodological element of fundamental importance in humanities research: pieces of text that re-appear across different documents, verbatim or paraphrased, provide invaluable information about the historical spread and…
Recognition and retrieval of textual content from the large document collections have been a powerful use case for the document image analysis community. Often the word is the basic unit for recognition as well as retrieval. Systems that…
Recent research has shown that transformer networks can be used as differentiable search indexes by representing each document as a sequences of document ID tokens. These generative retrieval models cast the retrieval problem to a document…
Intelligent reflecting surface (IRS) has the potential to enhance sensing performance, due to its capability of reshaping the echo signals. Different from the existing literature, which has commonly focused on IRS beamforming optimization,…
There is a niche of companies responsible for intermediating the purchase of large batches of varied products for other companies, for which the main challenge is to perform product description standardization, i.e., matching an item…
The popularity of Android OS has made it an appealing target to malware developers. To evade detection, including by ML-based techniques, attackers invest in creating malware that closely resemble legitimate apps. In this paper, we propose…
Unifying text detection and text recognition in an end-to-end training fashion has become a new trend for reading text in the wild, as these two tasks are highly relevant and complementary. In this paper, we investigate the problem of scene…
Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust. Concept-based models aim to address this issue by learning tasks based on a set of human-understandable concepts.…
Despite the popularization of deep neural networks (DNNs) in many fields, it is still challenging to deploy state-of-the-art models to resource-constrained devices due to high computational overhead. Model pruning provides a feasible…