Related papers: A Fast and Efficient Conditional Learning for Tuna…

Transfer learning is often used to decrease the computational cost of model training, as fine-tuning a model allows a downstream task to leverage the features learned from the pre-training dataset and quickly adapt them to a new task. This…

Salient Object Detection (SOD) with deep learning often requires substantial computational resources and large annotated datasets, making it impractical for resource-constrained applications. Lightweight models address computational demands…

The majority of online continual learning (CL) advocates single-epoch training and imposes restrictions on the size of replay memory. However, single-epoch training would incur a different amount of computations per CL algorithm, and the…

A mainstream type of the state of the arts (SOTAs) based on convolutional neural network (CNN) for real image denoising contains two sub-problems, i.e., noise estimation and non-blind denoising. This paper considers real noise approximated…

Federated Learning (FL) has emerged as a new paradigm for training machine learning models distributively without sacrificing data security and privacy. Learning models on edge devices such as mobile phones is one of the most common use…

Foundational language models show a remarkable ability to learn new concepts during inference via context data. However, similar work for images lag behind. To address this challenge, we introduce FLoWN, a flow matching model that learns to…

While Transformers have achieved remarkable success in LLMs through superior scalability, their application in industrial-scale ranking models remains nascent, hindered by the challenges of high feature sparsity and low label density. In…

The fairness-aware online learning framework has arisen as a powerful tool for the continual lifelong learning setting. The goal for the learner is to sequentially learn new tasks where they come one after another over time and the learner…

Dynamic evaluation of language models (LMs) adapts model parameters at test time using gradient information from previous tokens and substantially improves LM performance. However, it requires over 3x more compute than standard inference.…

Post-training compression of Transformer models commonly relies on truncated singular value decomposition (SVD). However, enforcing a single shared subspace can degrade accuracy even at moderate compression. Sparse dictionary learning…

Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…

Federated learning is used for decentralized training of machine learning models on a large number (millions) of edge mobile devices. It is challenging because mobile devices often have limited communication bandwidth and local computation…

Deploying adversarially robust machine learning systems requires continuous trade-offs between robustness, cost, and latency. We present an autonomic decision-support framework providing a quantitative foundation for adaptive hardware…

Robotic perception in unstructured environments remains challenging despite the zero-shot capabilities of foundation models such as SAM. This work attributes performance degradation to non-uniform representation shifts across transformer…

Federated learning is a decentralized machine learning framework that enables collaborative model training without revealing raw data. Due to the diverse hardware and software limitations, a client may not always be available for the…

Resistive random access memory (ReRAM) is a promising technology that can perform low-cost and in-situ matrix-vector multiplication (MVM) in analog domain. Scientific computing requires high-precision floating-point (FP) processing.…

We address the challenging problem of efficient inference across many devices and resource constraints, especially on edge devices. Conventional approaches either manually design or use neural architecture search (NAS) to find a specialized…

Continual learning (CL) aims to extend deep models from static and enclosed environments to dynamic and complex scenarios, enabling systems to continuously acquire new knowledge of novel categories without forgetting previously learned…

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…

In 6G wireless networks, Artificial Intelligence (AI)-driven applications demand the adoption of Federated Learning (FL) to enable efficient and privacy-preserving model training across distributed devices. Over-The-Air Federated Learning…