Related papers: SWITCH: An Exemplar for Evaluating Self-Adaptive M…

Multimodal learning faces challenges in effectively fusing information from diverse modalities, especially when modality quality varies across samples. Dynamic fusion strategies, such as attention mechanism in Transformers, aim to address…

To best assist human designers with different styles, Machine Learning (ML) systems need to be able to adapt to them. However, there has been relatively little prior work on how and when to best adapt an ML system to a co-designer. In this…

Evaluating the performance of Multi-modal Large Language Models (MLLMs), integrating both point cloud and language, presents significant challenges. The lack of a comprehensive assessment hampers determining whether these models truly…

Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that…

Continual learning in environments with shifting data distributions is a challenging problem with several real-world applications. In this paper we consider settings in which the data distribution(task) shifts abruptly and the timing of…

Machine learning (ML) is increasingly being deployed in programmable data planes (switches and SmartNICs) to enable real-time traffic analysis, security monitoring, and in-network decision-making. Decision trees (DTs) are particularly…

Automated slicing aims to identify subsets of evaluation data where a trained model performs anomalously. This is an important problem for machine learning pipelines in production since it plays a key role in model debugging and comparison,…

Although much of the success of Deep Learning builds on learning good representations, a rigorous method to evaluate their quality is lacking. In this paper, we treat the evaluation of representations as a model selection problem and…

Split learning emerges as a promising paradigm for collaborative distributed model training, akin to federated learning, by partitioning neural networks between clients and a server without raw data exchange. However, sequential split…

Large Language Models (LLMs) have achieved impressive performance through Supervised Fine-tuning (SFT) on diverse instructional datasets. When training on multiple capabilities simultaneously, the mixture training dataset, governed by…

Supply chains (SCs), complex networks spanning from raw material acquisition to product delivery, with enterprises as interconnected nodes, play a pivotal role in organizational success. However, optimizing SCs remains challenging,…

Split federated learning (SFL) has emerged as a promising paradigm to democratize machine learning (ML) on edge devices by enabling layer-wise model partitioning. However, existing SFL approaches suffer significantly from the straggler…

Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities in reasoning, coding, and engineering tasks, it is…

Nowadays, IoT devices have an enlarging scope of activities spanning from sensing, computing to acting and even more, learning, reasoning and planning. As the number of IoT applications increases, these objects are becoming more and more…

Recent advancements in autonomous multi-agent systems (MAS) based on large language models (LLMs) have enhanced the application scenarios and improved the capability of LLMs to handle complex tasks. Despite demonstrating effectiveness,…

The exponential growth of internet connected systems has generated numerous challenges, such as spectrum shortage issues, which require efficient spectrum sharing (SS) solutions. Complicated and dynamic SS systems can be exposed to…

Edge computing decentralizes computing resources, allowing for novel applications in domains such as the Internet of Things (IoT) in healthcare and agriculture by reducing latency and improving performance. This decentralization is achieved…

Multimodal transformers integrate diverse data types like images, audio, and text, advancing tasks such as audio-visual understanding and image-text retrieval; yet their high parameterization limits deployment on resource-constrained edge…

MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indiscriminately flood the quadratic self-attention mechanism…

Detecting out of policy speech (OOPS) content is important but difficult. While machine learning is a powerful tool to tackle this challenging task, it is hard to break the performance ceiling due to factors like quantity and quality…