Related papers: Post-Training Statistical Calibration for Higher A…

Deep neural networks, and more recently large-scale generative models such as large language models (LLMs) and large vision-action models (LVAs), achieve remarkable performance across diverse domains, yet their prohibitive computational…

Weakly-supervised semantic segmentation (WSSS) has recently gained much attention for its promise to train segmentation models only with image-level labels. Existing WSSS methods commonly argue that the sparse coverage of CAM incurs the…

Recent research has focused on weight sparsity in deep neural network training to reduce FLOPs, aiming for improved efficiency (test accuracy w.r.t training FLOPs). However, sparse weight training often compromises accuracy, requiring…

Overfitting is one of the fundamental challenges when training convolutional neural networks and is usually identified by a diverging training and test loss. The underlying dynamics of how the flow of activations induce overfitting is…

Segment Anything Models (SAMs) are extensively used in computer vision for universal image segmentation, but deploying them on resource-constrained devices is challenging due to their high computational and memory demands. Post-Training…

The deployment of large language models (LLMs) is often constrained by their substantial computational and memory demands. While structured pruning presents a viable approach by eliminating entire network components, existing methods suffer…

Trainings of Large Language Models are generally bottlenecked by matrix multiplications. In the Transformer architecture, a large portion of these operations happens in the Feed Forward Network (FFN), and this portion increases for larger…

Label corruption, where training samples are mislabeled due to non-expert annotation or adversarial attacks, significantly degrades model performance. Acquiring large, perfectly labeled datasets is costly, and retraining models from scratch…

Despite great strides in language-guided manipulation, existing work has been constrained to table-top settings. Table-tops allow for perfect and consistent camera angles, properties are that do not hold in mobile manipulation. Task plans…

Post-training pruning is an effective approach for reducing the size and inference cost of large language models (LLMs), but existing methods often face a trade-off between pruning quality and computational efficiency. Heuristic pruning…

Lately, post-training quantization methods have gained considerable attention, as they are simple to use, and require only a small unlabeled calibration set. This small dataset cannot be used to fine-tune the model without significant…

Simultaneous localization and mapping (SLAM) is a critical capability in autonomous navigation, but in order to scale SLAM to the setting of "lifelong" SLAM, particularly under memory or computation constraints, a robot must be able to…

In recent years, Dynamic Sparse Training (DST) has emerged as an alternative to post-training pruning for generating efficient models. In principle, DST allows for a more memory efficient training process, as it maintains sparsity…

Network pruning focuses on algorithms that aim to reduce a given model's computational cost by removing a subset of its parameters while having minimal impact on performance. Throughout the last decade, the most widely used pruning paradigm…

With the advancement of deep models, research work on image captioning has led to a remarkable gain in raw performance over the last decade, along with increasing model complexity and computational cost. However, surprisingly works on…

Training Convolutional Neural Networks (CNNs) usually requires a large number of computational resources. In this paper, \textit{SparseTrain} is proposed to accelerate CNN training by fully exploiting the sparsity. It mainly involves three…

The rectified linear unit (ReLU) is a highly successful activation function in neural networks as it allows networks to easily obtain sparse representations, which reduces overfitting in overparameterized networks. However, in network…

Large Language Models (LLMs), while demonstrating remarkable capabilities across various applications, present significant challenges during inference due to their substantial model size, especially when deployed on edge devices. Activation…

Sparseness is a useful regularizer for learning in a wide range of applications, in particular in neural networks. This paper proposes a model targeted at classification tasks, where sparse activity and sparse connectivity are used to…

Neural network training is computationally and memory intensive. Sparse training can reduce the burden on emerging hardware platforms designed to accelerate sparse computations, but it can affect network convergence. In this work, we…