相关论文: Modality-Aware Zero-Shot Pruning and Sparse Attent…

Attention-based architectures have achieved superior performance in multivariate time series forecasting but are computationally expensive. Techniques such as patching and adaptive masking have been developed to reduce their sizes and…

Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…

As its core computation, a self-attention mechanism gauges pairwise correlations across the entire input sequence. Despite favorable performance, calculating pairwise correlations is prohibitively costly. While recent work has shown the…

Attention is the cornerstone of modern Large Language Models (LLMs). Yet its quadratic complexity hinders efficiency and scalability, especially for long-context processing. A promising approach is to leverage sparsity in attention.…

Autonomous systems and smart-industry deployments increasingly split computation across near-sensor, edge, and cloud resources, where tight energy, latency, and reliability budgets demand run-time adaptivity. In practice, deciding what to…

Deployment of Transformer models on edge devices is becoming increasingly challenging due to the exponentially growing inference cost that scales quadratically with the number of tokens in the input sequence. Token pruning is an emerging…

Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data. To obtain more satisfactory performance, the crucial…

Integrating information from multiple modalities enhances the robustness of scene perception systems in autonomous vehicles, providing a more comprehensive and reliable sensory framework. However, the modality incompleteness in multi-modal…

Deploying Transformer models on edge devices is limited by latency and energy budgets. While INT8 quantization effectively accelerates the primary matrix multiplications, it exposes the softmax as the dominant bottleneck. This stage incurs…

Feature matching is a cornerstone task in computer vision, essential for applications such as image retrieval, stereo matching, 3D reconstruction, and SLAM. This survey comprehensively reviews modality-based feature matching, exploring…

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…

Point cloud foundation models demonstrate strong generalization, yet adapting them to downstream tasks remains challenging in low-data regimes. Full fine-tuning often leads to overfitting and significant drift from pre-trained…

The advent of foundation models have revolutionized various fields, enabling unprecedented task accuracy and flexibility in computational linguistics, computer vision and other domains. Attention mechanism has become an essential component…

The advancement of multi-object tracking (MOT) technologies presents the dual challenge of maintaining high performance while addressing critical security and privacy concerns. In applications such as pedestrian tracking, where sensitive…

This paper presents a compression framework for Reservoir Computing that enables systematic design-space exploration of trade-offs among quantization levels, pruning rates, model accuracy, and hardware efficiency. The proposed approach…

Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…

Multi-head self-attention (MSA) is a key component of Vision Transformers (ViTs), which have achieved great success in various vision tasks. However, their high computational cost and memory footprint hinder their deployment on…

Multi-head attention, a collection of several attention mechanisms that independently attend to different parts of the input, is the key ingredient in the Transformer. Recent work has shown, however, that a large proportion of the heads in…

Transformers usually expose one inference cost per trained model, while deployed systems often need multiple cost-quality operating points. We study Budgeted Attention Allocation, a monotone head-gating mechanism conditioned on a requested…

Multi-head self-attention is a distinctive feature extraction mechanism of vision transformers that computes pairwise relationships among all input patches, contributing significantly to their high performance. However, it is known to incur…