相关论文: Quantifying Context Mixing in Transformers

Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to produce scores for…

The lack of contextual information in text data can make the annotation process of text-based emotion classification datasets challenging. As a result, such datasets often contain labels that fail to consider all the relevant emotions in…

Despite increasing instances of machine translation (MT) systems including contextual information, the evidence for translation quality improvement is sparse, especially for discourse phenomena. Popular metrics like BLEU are not expressive…

Current data-driven methodologies for point cloud matching demand extensive training time and computational resources, presenting significant challenges for model deployment and application. In the point cloud matching task, recent…

Modeling semantic information is helpful for scene text recognition. In this work, we propose to model semantic and visual information jointly with a Visual-Semantic Transformer (VST). The VST first explicitly extracts primary semantic…

Dynamic graph learning plays a pivotal role in modeling evolving relationships over time, especially for temporal link prediction tasks in domains such as traffic systems, social networks, and recommendation platforms. While…

Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain. As a result, there is often a performance gap compared to…

Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance…

Blackbox transfer attacks for image classifiers have been extensively studied in recent years. In contrast, little progress has been made on transfer attacks for object detectors. Object detectors take a holistic view of the image and the…

Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on…

Contextual information at inference time, such as demonstrations, retrieved knowledge, or interaction history, can substantially improve large language models (LLMs) without parameter updates, yet its theoretical role remains poorly…

Automated Essay Scoring (AES) has emerged to prominence in response to the growing demand for educational automation. Providing an objective and cost-effective solution, AES standardises the assessment of extended responses. Although…

Video captioning is a popular task that challenges models to describe events in videos using natural language. In this work, we investigate the ability of various visual feature representations derived from state-of-the-art convolutional…

Transformer models have become the dominant backbone for sequence modeling, leveraging self-attention to produce contextualized token representations. These are typically aggregated into fixed-size vectors via pooling operations for…

Transformers are a popular choice for classification tasks and as backbones for object detection tasks. However, their high latency brings challenges in their adaptation to lightweight object detection systems. We present an approximation…

Change Captioning is a task that aims to describe the difference between images with natural language. Most existing methods treat this problem as a difference judgment without the existence of distractors, such as viewpoint changes.…

Subword tokenization is a common method for vocabulary building in Neural Machine Translation (NMT) models. However, increasingly complex tasks have revealed its disadvantages. First, a vocabulary cannot be modified once it is learned,…

The reliability of supervised machine learning systems depends on the accuracy and availability of ground truth labels. However, the process of human annotation, being prone to error, introduces the potential for noisy labels, which can…

Transformers have profoundly influenced AI research, but explaining their decisions remains challenging -- even for relatively simpler tasks such as classification -- which hinders trust and safe deployment in real-world applications.…

Large language models (LLMs) have achieved remarkable success in contextual knowledge understanding. In this paper, we show that these concentrated massive values consistently emerge in specific regions of attention queries (Q) and keys (K)…