Related papers: Feature Integration Spaces: Joint Training Reveals…
Bi-linear feature learning models, like the gated autoencoder, were proposed as a way to model relationships between frames in a video. By minimizing reconstruction error of one frame, given the previous frame, these models learn "mapping…
Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dictionaries whose features are not directly understandable and…
We propose neural network layers that explicitly combine frequency and image feature representations and show that they can be used as a versatile building block for reconstruction from frequency space data. Our work is motivated by the…
In material research, structural characterization often requires multiple complementary techniques to obtain a holistic morphological view of the synthesized material. Depending on the availability of and accessibility of the different…
Recent deep learning models can efficiently combine inputs from different modalities (e.g., images and text) and learn to align their latent representations, or to translate signals from one domain to another (as in image captioning, or…
We present the discriminative recurrent sparse auto-encoder model, comprising a recurrent encoder of rectified linear units, unrolled for a fixed number of iterations, and connected to two linear decoders that reconstruct the input and…
The point of this paper is to question typical assumptions in deep learning and suggest alternatives. A particular contribution is to prove that even if a Stacked Convolutional Auto-Encoder is good at reconstructing pictures, it is not…
The point of this paper is to question typical assumptions in deep learning and suggest alternatives. A particular contribution is to prove that even if a Stacked Convolutional Auto-Encoder is good at reconstructing pictures, it is not…
Leveraging on the underlying low-dimensional structure of data, low-rank and sparse modeling approaches have achieved great success in a wide range of applications. However, in many applications the data can display structures beyond simply…
The ImageNet hierarchy provides a structured taxonomy of object categories, offering a valuable lens through which to analyze the representations learned by deep vision models. In this work, we conduct a comprehensive analysis of how vision…
Deep neural networks can be trained in reciprocal space, by acting on the eigenvalues and eigenvectors of suitable transfer operators in direct space. Adjusting the eigenvalues, while freezing the eigenvectors, yields a substantial…
We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which show part-based representation of data. The learning algorithm is based on constraining negative…
Existing works are dedicated to untangling atomized numerical components (features) from the hidden states of Large Language Models (LLMs). However, they typically rely on autoencoders constrained by some training-time regularization on…
Traditionally, when generative models of data are developed via deep architectures, greedy layer-wise pre-training is employed. In a well-trained model, the lower layer of the architecture models the data distribution conditional upon the…
Hyperspectral imagery provides rich spectral detail but poses unique challenges because of its high dimensionality in both spatial and spectral domains. We propose \textit{HyperspectralMAE}, a Transformer-based foundation model for…
Sparse autoencoders (SAEs) have emerged as a powerful technique for decomposing language model representations into interpretable features. Current interpretation methods infer feature semantics from activation patterns, but overlook that…
Textual graphs are ubiquitous in real-world applications, featuring rich text information with complex relationships, which enables advanced research across various fields. Textual graph representation learning aims to generate…
Sparse autoencoders (SAEs) decompose polysemantic neural representations, where neurons respond to multiple unrelated concepts, into monosemantic features that capture single, interpretable concepts. However, standard training objectives…
Mixture of Experts (MoE) achieve parameter-efficient scaling through sparse expert routing, yet their internal representations remain poorly understood compared to dense models. We present a systematic comparison of MoE and dense model…
Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different levels of granularity and enable targeted steering of the…