相关论文: Identifying Functionally Important Features with E…

Whispering is an important mode of human speech, but no end-to-end recognition results for it were reported yet, probably due to the scarcity of available whispered speech data. In this paper, we present several approaches for end-to-end…

We present SAE-BrainMap, a novel framework that directly aligns deep learning visual model representations with voxel-level fMRI responses using sparse autoencoders (SAEs). First, we train layer-wise SAEs on model activations and compute…

Deep learning, particularly with the advancement of Large Language Models, has transformed biomolecular modeling, with protein language models such as ESM inspiring emerging RNA language models such as RiNALMo. Recent work has begun…

Sparse autoencoders (SAEs) trained on large language model activations output thousands of features that enable mapping to human-interpretable concepts. The current practice for analyzing these features primarily relies on inspecting…

Recent interpretability work on large language models (LLMs) has been increasingly dominated by a feature-discovery approach with the help of proxy modules. Then, the quality of features learned by, e.g., sparse auto-encoders (SAEs), is…

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…

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse…

Information in speech signals is not evenly distributed, making it an additional challenge for end-to-end (E2E) speech translation (ST) to learn to focus on informative features. In this paper, we propose adaptive feature selection (AFS)…

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

End-to-end (E2E) systems have played a more and more important role in automatic speech recognition (ASR) and achieved great performance. However, E2E systems recognize output word sequences directly with the input acoustic feature, which…

This paper emphasizes the significance to jointly exploit the problem structure and the parameter structure, in the context of deep modeling. As a specific and interesting example, we describe the deep double sparsity encoder (DDSE), which…

Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based…

A new line of research for feature selection based on neural networks has recently emerged. Despite its superiority to classical methods, it requires many training iterations to converge and detect informative features. The computational…

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

Sparse autoencoders (SAEs) are widely used to extract sparse, interpretable latents from transformer activations. We test whether commonly used SAE quality metrics and automatic explanation pipelines can distinguish trained transformers…

Sparse autoencoders (SAEs) are commonly used to interpret the internal activations of large language models (LLMs) by mapping them to human-interpretable concept representations. While existing evaluations of SAEs focus on metrics such as…

All-neural, end-to-end ASR systems gained rapid interest from the speech recognition community. Such systems convert speech input to text units using a single trainable neural network model. E2E models require large amounts of paired speech…

Sparse autoencoders (SAEs) are now standard tools for decomposing language model activations into interpretable features, and automated interpretability pipelines routinely assign each feature a short natural-language explanation. Existing…

In recent years, all-neural, end-to-end (E2E) ASR systems gained rapid interest in the speech recognition community. They convert speech input to text units in a single trainable Neural Network model. In ASR, many utterances contain rich…

End-to-end (E2E) spoken language understanding (SLU) can infer semantics directly from speech signal without cascading an automatic speech recognizer (ASR) with a natural language understanding (NLU) module. However, paired utterance…