A Change Detection Reality Check
In recent years, there has been an explosion of proposed change detection deep learning architectures in the remote sensing literature. These approaches claim to offer state-of the-art performance on...
View ArticleEvent-Keyed Summarization
We introduce event-keyed summarization (EKS), a novel task that marries traditional summarization and document-level event extraction, with the goal of generating a contextualized summary for a...
View ArticleArchitectural Neural Backdoors from First Principles
While previous research backdoored neural networks by changing their parameters, recent work uncovered a more insidious threat: backdoors embedded within the definition of the network's architecture....
View ArticleEfficient Incremental Belief Updates Using Weighted Virtual Observations
We present an algorithmic solution to the problem of incremental belief updating in the context of Monte Carlo inference in Bayesian statistical models represented by probabilistic programs. Given a...
View ArticleEfficient Resource Scheduling for Distributed Infrastructures Using...
In the past few decades, the rapid development of information and internet technologies has spawned massive amounts of data and information. The information explosion drives many enterprises or...
View ArticleORIENT: A Priority-Aware Energy-Efficient Approach for Latency-Sensitive...
Anticipation for 6G's arrival comes with growing concerns about increased energy consumption in computing and networking. The expected surge in connected devices and resource-demanding applications...
View ArticleCochCeps-Augment: A Novel Self-Supervised Contrastive Learning Using Cochlear...
Self-supervised learning (SSL) for automated speech recognition in terms of its emotional content, can be heavily degraded by the presence noise, affecting the efficiency of modeling the intricate...
View ArticleWhispers in the Machine: Confidentiality in LLM-integrated Systems
Large Language Models (LLMs) are increasingly integrated with external tools. While these integrations can significantly improve the functionality of LLMs, they also create a new attack surface where...
View ArticleTREET: TRansfer Entropy Estimation via Transformer
Transfer entropy (TE) is a measurement in information theory that reveals the directional flow of information between processes, providing valuable insights for a wide range of real-world applications....
View ArticleGenTranslate: Large Language Models are Generative Multilingual Speech and...
Recent advances in large language models (LLMs) have stepped forward the development of multilingual speech and machine translation by its reduced representation errors and incorporated external...
View ArticleDimVis: Interpreting Visual Clusters in Dimensionality Reduction With...
Dimensionality Reduction (DR) techniques such as t-SNE and UMAP are popular for transforming complex datasets into simpler visual representations. However, while effective in uncovering general dataset...
View ArticleLow-Rank Approximation of Structural Redundancy for Self-Supervised Learning
We study the data-generating mechanism for reconstructive SSL to shed light on its effectiveness. With an infinite amount of labeled samples, we provide a sufficient and necessary condition for perfect...
View ArticleGyroscope-Assisted Motion Deblurring Network
Image research has shown substantial attention in deblurring networks in recent years. Yet, their practical usage in real-world deblurring, especially motion blur, remains limited due to the lack of...
View ArticleEvaluating Co-Creativity using Total Information Flow
Co-creativity in music refers to two or more musicians or musical agents interacting with one another by composing or improvising music. However, this is a very subjective process and each musician has...
View ArticleTowards Principled Assessment of Tabular Data Synthesis Algorithms
Data synthesis has been advocated as an important approach for utilizing data while protecting data privacy. A large number of tabular data synthesis algorithms (which we call synthesizers) have been...
View ArticleForestColl: Efficient Collective Communications on Heterogeneous Network Fabrics
As modern DNN models grow ever larger, collective communications between the accelerators (allreduce, etc.) emerge as a significant performance bottleneck. Designing efficient communication schedules...
View ArticleTransfer learning with generative models for object detection on limited...
The availability of data is limited in some fields, especially for object detection tasks, where it is necessary to have correctly labeled bounding boxes around each object. A notable example of such...
View ArticleLearn to Teach: Improve Sample Efficiency in Teacher-student Learning for...
Simulation-to-reality (sim-to-real) transfer is a fundamental problem for robot learning. Domain Randomization, which adds randomization during training, is a powerful technique that effectively...
View ArticleRetrosynthesis Prediction via Search in (Hyper) Graph
Predicting reactants from a specified core product stands as a fundamental challenge within organic synthesis, termed retrosynthesis prediction. Recently, semi-template-based methods and...
View ArticleNICE: To Optimize In-Context Examples or Not?
Recent works have shown that large language models (LLMs) work remarkably well on a wide range of tasks through in-context learning and optimization of in-context examples (ICE). However, most of these...
View Article