Related papers: Seneca: Taint-Based Call Graph Construction for Ja…

Circuit graph discovery has emerged as a fundamental approach to elucidating the skill mechanistic of language models. Despite the output faithfulness of circuit graphs, they suffer from atomic ablation, which causes the loss of causal…

We propose a kernel regression method to predict a target signal lying over a graph when an input observation is given. The input and the output could be two different physical quantities. In particular, the input may not be a graph signal…

Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…

Noise reduction techniques based on deep learning have demonstrated impressive performance in enhancing the overall quality of recorded speech. While these approaches are highly performant, their application in audio engineering can be…

Deep neural networks may easily memorize noisy labels present in real-world data, which degrades their ability to generalize. It is therefore important to track and evaluate the robustness of models against noisy label memorization. We…

Decentralized applications (dApps) consist of smart contracts that run on blockchains and clients that model collaborating parties. dApps are used to model financial and legal business functionality. Today, contracts and clients are written…

In this letter, we propose a novel image denoising method based on correlation preserving sparse coding. Because the instable and unreliable correlations among basis set can limit the performance of the dictionary-driven denoising methods,…

While there has been significant progress in solving the problems of image pixel labeling, object detection and scene classification, existing approaches normally address them separately. In this paper, we propose to tackle these problems…

We introduce SELECT (Scene tExt Label Errors deteCTion), a novel approach that leverages multi-modal training to detect label errors in real-world scene text datasets. Utilizing an image-text encoder and a character-level tokenizer, SELECT…

Rockfalls are a hazard for the safety of infrastructure as well as people. Identifying loose rocks by inspection of slopes adjacent to roadways and other infrastructure and removing them in advance can be an effective way to prevent…

Deep learning-based denoising models have been widely employed in vision tasks, functioning as filters to eliminate noise while retaining crucial semantic information. Additionally, they play a vital role in defending against adversarial…

Despite remarkable success in diverse web-based applications, Graph Neural Networks(GNNs) inherit and further exacerbate historical discrimination and social stereotypes, which critically hinder their deployments in high-stake domains such…

Signed Graph Neural Networks (SGNNs) are widely adopted to analyze complex patterns in signed graphs with both positive and negative links. Given the noisy nature of real-world connections, the robustness of SGNN has also emerged as a…

Multi-Label Remote Sensing Image Classification (MLRSIC) has received increasing research interest. Taking the cooccurrence relationship of multiple labels as additional information helps to improve the performance of this task. Current…

Most data intensive applications often access only a few fields of the objects they are operating on. Since NVM provides fast, byte-addressable access to durable memory, it is possible to access various fields of an object stored in NVM…

The popularity and wide adoption of JavaScript both at the client and server side makes its code analysis more important than ever before. Most of the algorithms for vulnerability analysis, coding issue detection, or type inference rely on…

Perceiving a scene most fully requires all the senses. Yet modeling how objects look and sound is challenging: most natural scenes and events contain multiple objects, and the audio track mixes all the sound sources together. We propose to…

Our ability to synthesize sensory data that preserves specific statistical properties of the real data has had tremendous implications on data privacy and big data analytics. The synthetic data can be used as a substitute for selective real…

We propose a novel deep architecture, SegNet, for semantic pixel wise image labelling. SegNet has several attractive properties; (i) it only requires forward evaluation of a fully learnt function to obtain smooth label predictions, (ii)…

Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees (up to some reasonable equivalence class). Common to all of these approaches is the assumption that…