Related papers: Learning Second-Order Attentive Context for Effici…
The timeline of computer vision research is marked with advances in learning and utilizing efficient contextual representations. Most of them, however, are targeted at improving model performance on a single downstream task. We consider a…
Multimodal Large Language Models (MLLMs) incur significant computational cost from processing numerous vision tokens through all LLM layers. Prior pruning methods operate either before the LLM, limiting generality due to diverse…
Efficient modeling of long sequences of high-order data requires a more efficient architecture than Transformer. In this paper, we investigate two key aspects of extending linear recurrent models, especially those originally designed for…
LLMs have demonstrated remarkable proficiency in understanding tasks but continue to struggle with long-context comprehension, particularly with content located in the middle of extensive inputs. This limitation, known as the…
Outlier detection plays an essential role in many data-driven applications to identify isolated instances that are different from the majority. While many statistical learning and data mining techniques have been used for developing more…
Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In this work we systematically investigate how specific…
Dot-product attention has wide applications in computer vision and natural language processing. However, its memory and computational costs grow quadratically with the input size. Such growth prohibits its application on high-resolution…
Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…
Neural Processes (NPs) (Garnelo et al 2018a;b) approach regression by learning to map a context set of observed input-output pairs to a distribution over regression functions. Each function models the distribution of the output given an…
Soft attention in Transformer-based Large Language Models (LLMs) is susceptible to incorporating irrelevant information from the context into its latent representations, which adversely affects next token generations. To help rectify these…
We propose a new formulation for pruning convolutional kernels in neural networks to enable efficient inference. We interleave greedy criteria-based pruning with fine-tuning by backpropagation - a computationally efficient procedure that…
Non-uniform structured network pruning methods can effectively reduce Large Language Model (LLM) size by eliminating redundant channels or layers, offering lower performance degradation than uniform strategies. However, existing non-uniform…
Transformer architectures have achieved state-of-the-art results on a variety of sequence modeling tasks. However, their attention mechanism comes with a quadratic complexity in sequence lengths, making the computational overhead…
Recent research has focused on using convolutional neural networks (CNNs) as the backbones in two-view correspondence learning, demonstrating significant superiority over methods based on multilayer perceptrons. However, CNN backbones that…
The standard content-based attention mechanism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step. In this work, we propose an…
In multimodal large language models (MLLMs), the length of input visual tokens is often significantly greater than that of their textual counterparts, leading to a high inference cost. Many works aim to address this issue by removing…
Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time…
Deep Neural Networks (DNNs) have achieved remarkable success in many computer vision tasks recently, but the huge number of parameters and the high computation overhead hinder their deployments on resource-constrained edge devices. It is…
Large vision-language models (LVLMs) generally contain significantly more visual tokens than their textual counterparts, resulting in a considerable computational burden. Recent efforts have been made to tackle this issue by pruning visual…
The phenomena of in-context learning has typically been thought of as "learning from examples". In this work which focuses on Machine Translation, we present a perspective of in-context learning as the desired generation task maintaining…