相关论文: VISIT: Visualizing and Interpreting the Semantic I…

The transformer is a neural network component that can be used to learn useful representations of sequences or sets of data-points. The transformer has driven recent advances in natural language processing, computer vision, and…

In this work, we introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for…

Advances in GPT-based large language models (LLMs) are revolutionizing natural language processing, exponentially increasing its use across various domains. Incorporating uni-directional attention, these autoregressive LLMs can generate…

Though vision transformers (ViTs) have achieved state-of-the-art performance in a variety of settings, they exhibit surprising failures when performing tasks involving visual relations. This begs the question: how do ViTs attempt to perform…

A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite the remarkable progress of generative AI, existing models…

Planning, as the core module of agents, is crucial in various fields such as embodied agents, web navigation, and tool using. With the development of large language models (LLMs), some researchers treat large language models as intelligent…

Recently, incorporating knowledge from pretrained language models (PLMs) into decision transformers (DTs) has generated significant attention in offline reinforcement learning (RL). These PLMs perform well in RL tasks, raising an intriguing…

Artificial intelligence systems, particularly through generative pre-trained transformers (GPTs), have enabled capability-rich language models, but their operation incurs substantial costs in digital computation, memory, and data movement.…

Large language models (LLMs) demonstrate remarkable ability in cross-lingual tasks. Understanding how LLMs acquire this ability is crucial for their interpretability. To quantify the cross-lingual ability of LLMs accurately, we propose a…

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…

Over the past few decades, the hydrology community has witnessed notable advancements in streamflow prediction, particularly with the introduction of cutting-edge machine-learning algorithms. Recurrent neural networks, especially Long…

Why do large pre-trained transformer-based models perform so well across a wide variety of NLP tasks? Recent research suggests the key may lie in multi-headed attention mechanism's ability to learn and represent linguistic information.…

Transformers are state-of-the-art deep learning models that are composed of stacked attention and point-wise, fully connected layers designed for handling sequential data. Transformers are not only ubiquitous throughout Natural Language…

The paper explores how video models trained for classification tasks represent nuanced, hidden semantic information that may not affect the final outcome, a key challenge for Trustworthy AI models. Through Explainable and Interpretable AI…

Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning (ICL), where models adapt to new tasks through example-based prompts without requiring parameter updates. However, understanding how tasks are…

The Language of Thought Hypothesis suggests that human cognition operates on a structured, language-like system of mental representations. While neural language models can naturally benefit from the compositional structure inherently and…

We investigate how word meanings are represented in the transformer language models. Specifically, we focus on whether transformer models employ something analogous to a lexical store - where each word has an entry that contains semantic…

Narratives drive human behavior and lay at the core of geopolitics, but have eluded quantification that would permit measurement of their overlap and evolution. We present an interpretable model that integrates an established bag-of-words…

Transformer-based pre-trained language models (PLMs) have dramatically improved the state of the art in NLP across many tasks. This has led to substantial interest in analyzing the syntactic knowledge PLMs learn. Previous approaches to this…

Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging. In this paper, we present the design and implementation of a visual analytic framework for assisting researchers in such…