Related papers: FAAST: Forward-Only Associative Learning via Close…

Turning memristor arrays from efficient inference engines into systems capable of on-chip learning has proved difficult. Weight updates have a high energy cost and cause device wear, analog states drift, and backpropagation requires a…

Adaptations facilitate efficient training of large backbone models, including diffusion models for image generation and transformer-based language models. While various adaptation techniques enhance performance with minimal computational…

Large language models have achieved remarkable success in various tasks. However, it is challenging for them to learn new tasks incrementally due to catastrophic forgetting. Existing approaches rely on experience replay, optimization…

Text-based speech editing aims to modify specific segments while preserving speaker identity and acoustic context. Existing methods rely on task-specific training, which incurs high data costs and struggles with temporal fidelity in…

Sparsity-aware training is an effective approach for transforming large language models (LLMs) into hardware-friendly sparse patterns, thereby reducing latency and memory consumption during inference. In this paper, we propose Continuous…

Despite recent advancements in deep learning, deep neural networks continue to suffer from performance degradation when applied to new data that differs from training data. Test-time adaptation (TTA) aims to address this challenge by…

In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Recently, the idea of backward compatible training (BCT) was proposed. To…

Existing models that achieve state-of-the-art (SOTA) performance on both clean and adversarially-perturbed images rely on convolution operations conditioned with feature-wise linear modulation (FiLM) layers. These layers require many new…

Training neural networks has traditionally relied on backpropagation (BP), a gradient-based algorithm that, despite its widespread success, suffers from key limitations in both biological and hardware perspectives. These include backward…

We introduce PACE, a backpropagation-free continual test-time adaptation system that directly optimizes the affine parameters of normalization layers. Existing derivative-free approaches struggle to balance runtime efficiency with learning…

Data-dependent secondary transforms, which aim to decorrelate coefficients of a separable primary transform, can improve residual coding efficiency; however, their deployment is often constrained by computational complexity. Recent video…

Persistent monitoring of a spatiotemporal fluid process requires data sampling and predictive modeling of the process being monitored. In this paper we present PASST algorithm: Predictive-model based Adaptive Sampling of a Spatio-Temporal…

In-context learning with attention enables large neural networks to make context-specific predictions by selectively focusing on relevant examples. Here, we adapt this idea to supervised learning procedures such as lasso regression and…

In finetuning a large pretrained model to downstream tasks, parameter-efficient fine-tuning (PEFT) methods can effectively finetune pretrained models with few trainable parameters, but suffer from high GPU memory consumption and slow…

In this work, we address music representation learning using convolution-free transformers. We build on top of existing spectrogram-based audio transformers such as AST and train our models on a supervised task using patchout training…

Foundation models are now a major focus of leading technology organizations due to their ability to generalize across diverse tasks. Existing approaches for adapting foundation models to new applications often rely on Federated Learning…

Fast adversarial training (FAT) is beneficial for improving the adversarial robustness of neural networks. However, previous FAT work has encountered a significant issue known as catastrophic overfitting when dealing with large perturbation…

Traffic prediction is a cornerstone of modern intelligent transportation systems and a critical task in spatio-temporal forecasting. Although advanced Spatio-temporal Graph Neural Networks (STGNNs) and pre-trained models have achieved…

Self-supervised learning has brought about a revolutionary paradigm shift in various computing domains, including NLP, vision, and biology. Recent approaches involve pre-training transformer models on vast amounts of unlabeled data, serving…

Fine-tuning is widely applied in image classification tasks as a transfer learning approach. It re-uses the knowledge from a source task to learn and obtain a high performance in target tasks. Fine-tuning is able to alleviate the challenge…