相关论文: Transcoder-based Circuit Analysis for Interpretabl…

Speculative decoding accelerates LLM inference by utilizing otherwise idle computational resources during memory-to-chip data transfer. Current speculative decoding methods typically assume a considerable amount of available computing…

Large Language Models (LLMs) have experienced a rapid rise in AI, changing a wide range of applications with their advanced capabilities. As these models become increasingly integral to decision-making, the need for thorough…

Interactive speech recognition systems must generate words quickly while also producing accurate results. Two-pass models excel at these requirements by employing a first-pass decoder that quickly emits words, and a second-pass decoder that…

Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in…

Understanding the internal activations of Vision Transformers (ViTs) is critical for building interpretable and trustworthy models. While Sparse Autoencoders (SAEs) have been used to extract human-interpretable features, they operate on…

Recent studies in interpretability have explored the inner workings of transformer models trained on tasks across various domains, often discovering that these networks naturally develop highly structured representations. When such…

Transformer models have become state-of-the-art in decoding stimuli and behavior from neural activity, significantly advancing neuroscience research. Yet greater transparency in their decision-making processes would substantially enhance…

Sarcasm detection, with its figurative nature, poses unique challenges for affective systems designed to perform sentiment analysis. While these systems typically perform well at identifying direct expressions of emotion, they struggle with…

Foundation models (FMs), powered by self-supervised learning (SSL), have redefined the capabilities of artificial intelligence, demonstrating exceptional performance in domains like natural language processing and computer vision. These…

Background: Spatial transcriptomics have emerged as a powerful tool in biomedical research because of its ability to capture both the spatial contexts and abundance of the complete RNA transcript profile in organs of interest. However,…

Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split a source sequence with different word segmentors or…

Transformer-based language models exhibit In-Context Learning (ICL), where predictions are made adaptively based on context. While prior work links induction heads to ICL through a sudden jump in accuracy, this can only account for ICL when…

EEG foundation models achieve state-of-the-art clinical performance, yet the internal computations driving their predictions remain opaque: a barrier to clinical trust. We apply TopK Sparse Autoencoders (SAEs) across three architecturally…

Phenotypic drug discovery has attracted widespread attention because of its potential to identify bioactive molecules. Transcriptomic profiling provides a comprehensive reflection of phenotypic changes in cellular responses to external…

The remarkable capabilities of modern large language models are rooted in their vast repositories of knowledge encoded within their parameters, enabling them to perceive the world and engage in reasoning. The inner workings of how these…

Transformer-based encoder-decoder models that generate outputs in a left-to-right fashion have become standard for sequence-to-sequence tasks. In this paper, we propose a framework for decoding that produces sequences from the "outside-in":…

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Understanding the relationships among genes, compounds, and their interactions in living organisms remains limited due to technological constraints and the complexity of biological data. Deep learning has shown promise in exploring these…

Transformers have proven highly effective across various applications, especially in handling sequential data such as natural languages and time series. However, transformer models often lack clear interpretability, and the success of…

Diagnosis-oriented dialogue system queries the patient's health condition and makes predictions about possible diseases through continuous interaction with the patient. A few studies use reinforcement learning (RL) to learn the optimal…