相关论文: Exemplar Partitioning for Mechanistic Interpretabi…

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…

Visual Semantic Embedding (VSE) models, which map images into a rich semantic embedding space, have been a milestone in object recognition and zero-shot learning. Current approaches to VSE heavily rely on static word em-bedding techniques.…

Multimodal pre-trained models, such as CLIP, are popular for zero-shot classification due to their open-vocabulary flexibility and high performance. However, vision-language models, which compute similarity scores between images and class…

Large foundation models (LFMs) achieve strong performance through scaling, yet current structural pruning methods derive fixed pruning decisions during inference, overlooking sparsity patterns that emerge in the autoregressive token…

Decoding visual experience from brain signals offers exciting possibilities for neuroscience and interpretable AI. While EEG is accessible and temporally precise, its limitations in spatial detail hinder image reconstruction. Our model…

We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores parameter modifications while maintaining model stability. Inspired by evolutionary optimization…

Sparse autoencoders (SAEs) \citep{bricken2023monosemanticity,gao2024scalingevaluatingsparseautoencoders} rely on dictionary learning to extract interpretable features from neural networks at scale in an unsupervised manner, with…

This article proposes a method to formalise models of cognitive processes grounded in experience, considering experience from the perspective of a living system and not from that of an observer of the living system. The perspective of a…

Sparse autoencoders (SAEs) have proven useful in disentangling the opaque activations of neural networks, primarily large language models, into sets of interpretable features. However, adapting them to domains beyond language, such as…

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior.…

Semantic mapping based on the supervised object detectors is sensitive to image distribution. In real-world environments, the object detection and segmentation performance can lead to a major drop, preventing the use of semantic mapping in…

Sparse autoencoders (SAEs) have received considerable recent attention as tools for mechanistic interpretability, showing success at extracting interpretable features even from very large LLMs. However, this research has been largely…

Enabled by large-scale text corpora with huge parameters, pre-trained language models operate as multi-task experts using a single model architecture. However, recent studies have revealed that certain neurons play disproportionately…

Audio-Visual Video Parsing (AVVP) task aims to detect and temporally locate events within audio and visual modalities. Multiple events can overlap in the timeline, making identification challenging. While traditional methods usually focus…

We introduce the Exemplar-Based Expository Text Generation task, aiming to generate an expository text on a new topic using an exemplar on a similar topic. Current methods fall short due to their reliance on extensive exemplar data,…

We present a new approach for learning compact and intuitive distributed representations with binary encoding. Rather than summing up expert votes as in products of experts, we employ for each variable the opinion of the most reliable…

Sparse Autoencoders (SAEs) have been successfully used to probe Large Language Models (LLMs) and extract interpretable concepts from their internal representations. These concepts are linear combinations of neuron activations that…

Event cameras provide robust visual signals under fast motion and challenging illumination conditions thanks to their microsecond latency and high dynamic range. However, their unique sensing characteristics and limited labeled data make it…

Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning high-level concepts, are valued because of closeness of…

The field of computational pathology has witnessed great advancements since deep neural networks have been widely applied. These networks usually require large numbers of annotated data to train vast parameters. However, it takes…