Related papers: Transcoder-based Circuit Analysis for Interpretabl…

Speech foundation models (SFMs) are designed to serve as general-purpose representations for a wide range of speech-processing tasks. The last five years have seen an influx of increasingly successful self-supervised and supervised…

Code pre-trained models (CodePTMs) have recently demonstrated a solid capacity to process various software intelligence tasks, e.g., code clone detection, code translation, and code summarization. The current mainstream method that deploys…

Spoken language models (SLMs) that integrate speech with large language models (LMs) rely on modality adapters (MAs) to map the output of speech encoders to a representation that is understandable to the decoder LM. Yet we know very little…

Underlying mechanisms of memorization in LLMs -- the verbatim reproduction of training data -- remain poorly understood. What exact part of the network decides to retrieve a token that we would consider as start of memorization sequence?…

Sequence-to-Sequence (S2S) neural text generation models, especially the pre-trained ones (e.g., BART and T5), have exhibited compelling performance on various natural language generation tasks. However, the black-box nature of these models…

Protein language models (PLMs) have demonstrated remarkable success in protein modeling and design, yet their internal mechanisms for predicting structure and function remain poorly understood. Here we present a systematic approach to…

The fully convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation. The encoder-decoder architecture utilizes an encoder to capture multilevel feature maps, which are…

Understanding the function of individual neurons within language models is essential for mechanistic interpretability research. We propose $\textbf{Neuron to Graph (N2G)}$, a tool which takes a neuron and its dataset examples, and…

Long Short-Term Memory (LSTM) and Transformers are two popular neural architectures used for natural language processing tasks. Theoretical results show that both are Turing-complete and can represent any context-free language (CFL).In…

The rapid advancements in transformer-based language models have revolutionized natural language processing, yet understanding the internal mechanisms of these models remains a significant challenge. This paper explores the application of…

In this paper, we investigate the manner in which interpretable sub-word speech units emerge within a convolutional neural network model trained to associate raw speech waveforms with semantically related natural image scenes. We show how…

The remarkable performance achieved by Large Language Models (LLM) has driven research efforts to leverage them for a wide range of tasks and input modalities. In speech-to-text (S2T) tasks, the emerging solution consists of projecting the…

Large language models (LLMs) often achieve impressive predictive accuracy, yet correctness alone does not imply genuine understanding. True LLM understanding, analogous to human expertise, requires making consistent, well-founded decisions…

Structural Health Monitoring (SHM) is a critical task for ensuring the safety and reliability of civil infrastructures, typically realized on bridges and viaducts by means of vibration monitoring. In this paper, we propose for the first…

In recent years, numerous Transformer-based models have been applied to long-term time-series forecasting (LTSF) tasks. However, recent studies with linear models have questioned their effectiveness, demonstrating that simple linear layers…

Vision-language models (VLMs) are powerful but remain opaque black boxes. We introduce the first framework for transparent circuit tracing in VLMs to systematically analyze multimodal reasoning. By utilizing transcoders, attribution graphs,…

Single-cell multi-omics data contain huge information of cellular states, and analyzing these data can reveal valuable insights into cellular heterogeneity, diseases, and biological processes. However, as cell differentiation \& development…

Transformers have become the foundational architecture for a broad spectrum of sequence modeling applications, underpinning state-of-the-art systems in natural language processing, vision, and beyond. However, their theoretical limitations…

Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. A crucial part of finding circuits is understanding why each attention head attends where it does. To…

In this paper, we investigate the usage of autoencoders in modeling textual data. Traditional autoencoders suffer from at least two aspects: scalability with the high dimensionality of vocabulary size and dealing with task-irrelevant words.…