相关论文: Visualizing Attention in Transformer-Based Languag…

We present AttentionBender, a tool that manipulates cross-attention in Video Diffusion Transformers to help artists probe the internal mechanics of black-box video generation. While generative outputs are increasingly realistic, prompt-only…

The use of transformer-based models is growing rapidly throughout society. With this growth, it is important to understand how they work, and in particular, how the attention mechanisms represent concepts. Though there are many…

The key to a Transformer model is the self-attention mechanism, which allows the model to analyze an entire sequence in a computationally efficient manner. Recent work has suggested the possibility that general attention mechanisms used by…

Attention is fundamental to cognition, yet it remains a challenge to understand attention in tasks approaching real-world complexity. Here, we approached this problem by modeling gaze patterns of monkeys playing Pac-Man. We first show a…

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

We explore the internal mechanisms of how bias emerges in large language models (LLMs) when provided with ambiguous comparative prompts: inputs that compare or enforce choosing between two or more entities without providing clear context…

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…

Explainability and interpretability are two important concepts, the absence of which can and should impede the application of well-performing neural networks to real-world problems. At the same time, they are difficult to incorporate into…

This chapter reviews recent computational models of visual attention. We begin with models for the bottom-up or stimulus-driven guidance of attention to salient visual items, which we examine in seven different broad categories. We then…

Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed…

Transformer-based language models display impressive reasoning-like behavior, yet remain brittle on tasks that require stable symbolic manipulation. This paper develops a unified perspective on these phenomena by interpreting self-attention…

We investigate the integration of attention maps from a pre-trained Vision Transformer into voxel representations to enhance bimanual robotic manipulation. Specifically, we extract attention maps from DINOv2, a self-supervised ViT model,…

As large language models (LLMs) and visual language models (VLMs) grow in scale and application, attention mechanisms have become a central computational bottleneck due to their high memory and time complexity. While many efficient…

Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats…

Visual interest & affect prediction is a very interesting area of research in the area of computer vision. In this paper, we propose a transfer learning and attention mechanism based neural network model to predict visual interest &…

Transformer has been applied in the field of computer vision due to its excellent performance in natural language processing, surpassing traditional convolutional neural networks and achieving new state-of-the-art. ViT divides an image into…

Transformers have become an indispensable module for text generation models since their great success in machine translation. Previous works attribute the~success of transformers to the query-key-value dot-product attention, which provides…

The Transformer-based models with the multi-head self-attention mechanism are widely used in natural language processing, and provide state-of-the-art results. While the pre-trained language backbones are shown to implicitly capture certain…

Self-supervised Audio Transformers (SAT) enable great success in many downstream speech applications like ASR, but how they work has not been widely explored yet. In this work, we present multiple strategies for the analysis of attention…

Mechanistic interpretability improves the safety, reliability, and robustness of large AI models. This study examined individual attention heads in vision transformers (ViTs) fine tuned on distorted 2D spectrogram images containing non…