相关论文: SEAT: Stable and Explainable Attention

Pre-trained Transformer-based neural language models, such as BERT, have achieved remarkable results on varieties of NLP tasks. Recent works have shown that attention-based models can benefit from more focused attention over local regions.…

Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optimal ability to learn…

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…

First derived from human intuition, later adapted to machine translation for automatic token alignment, attention mechanism, a simple method that can be used for encoding sequence data based on the importance score each element is assigned,…

Stance detection is crucial for fostering a human-centric Web by analyzing user-generated content to identify biases and harmful narratives that undermine trust. With the development of Large Language Models (LLMs), existing approaches…

BERT-based architectures currently give state-of-the-art performance on many NLP tasks, but little is known about the exact mechanisms that contribute to its success. In the current work, we focus on the interpretation of self-attention,…

The currently dominating artificial intelligence and machine learning technology, neural networks, builds on inductive statistical learning. Neural networks of today are information processing systems void of understanding and reasoning…

Visual perception is the most critical input for driving decisions. In this study, our aim is to understand relationship between saliency and driving decisions. We present a novel attention-based saliency map prediction model for making…

Stance Detection (SD) has become a critical area of interest due to its applications in various contexts leading to increased research within NLP. Yet the subtlety and complexity of texts sourced from online platforms often containing…

Visual attention helps achieve robust perception under noise, corruption, and distribution shifts in human vision, which are areas where modern neural networks still fall short. We present VARS, Visual Attention from Recurrent Sparse…

Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models hard to apply to long sequence tasks. Various improved…

The computational burden of attention in long-context language models has motivated two largely independent lines of work: sparse attention mechanisms that reduce complexity by attending to selected tokens, and gated attention variants that…

Convolutional neural networks have allowed remarkable advances in single image super-resolution (SISR) over the last decade. Among recent advances in SISR, attention mechanisms are crucial for high-performance SR models. However, the…

Explicit Chain-of-Thought improves the reasoning performance of large language models but often incurs high inference cost due to verbose token-level traces. While recent approaches reduce this overhead via concise prompting or step…

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

The attention mechanism is considered the backbone of the widely-used Transformer architecture. It contextualizes the input by computing input-specific attention matrices. We find that this mechanism, while powerful and elegant, is not as…

When predictions support decisions they may influence the outcome they aim to predict. We call such predictions performative; the prediction influences the target. Performativity is a well-studied phenomenon in policy-making that has so far…

Transformers have achieved state-of-the-art results across a range of domains, but their quadratic attention mechanism poses significant challenges for long-sequence modelling. Recent efforts to design linear-time attention mechanisms have…

Most models of visual attention aim at predicting either top-down or bottom-up control, as studied using different visual search and free-viewing tasks. In this paper we propose the Human Attention Transformer (HAT), a single model that…

Active learning is an increasingly important branch of machine learning and a powerful technique for natural language processing. The main advantage of active learning is its potential to reduce the amount of labeled data needed to learn…