Related papers: SAEdit: Token-level control for continuous image e…

Sparse autoencoders (SAEs) are widely used in mechanistic interpretability research for large language models; however, the state-of-the-art method of using $k$-sparse autoencoders lacks a theoretical grounding for selecting the…

While vision models are highly capable, their internal mechanisms remain poorly understood -- a challenge which sparse autoencoders (SAEs) have helped address in language, but which remains underexplored in vision. We address this gap by…

Deep conditional generative models are excellent tools for creating high-quality images and editing their attributes. However, training modern generative models from scratch is very expensive and requires large computational resources. In…

Scientific archives now contain hundreds of petabytes of data across genomics, ecology, climate, and molecular biology that could reveal undiscovered patterns if systematically analyzed at scale. Large-scale, weakly-supervised datasets in…

Diffusion Transformers (DiTs) have achieved remarkable success in diverse and high-quality text-to-image(T2I) generation. However, how text and image latents individually and jointly contribute to the semantics of generated images, remain…

Text-to-image generative models, specifically those based on diffusion models like Imagen and Stable Diffusion, have made substantial advancements. Recently, there has been a surge of interest in the delicate refinement of text prompts.…

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 image editing provides users with a flexible tool to modify a given image guided by a corresponding segmentation map. In this task, the features of the foreground objects and the backgrounds are quite different. However, all…

Unsupervised text attribute transfer automatically transforms a text to alter a specific attribute (e.g. sentiment) without using any parallel data, while simultaneously preserving its attribute-independent content. The dominant approaches…

Adaptive and flexible image editing is a desirable function of modern generative models. In this work, we present a generative model with auto-encoder architecture for per-region style manipulation. We apply a code consistency loss to…

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

Recent works favored dense signals (e.g., depth, DensePose), as an alternative to sparse signals (e.g., OpenPose), to provide detailed spatial guidance for pose-guided text-to-image generation. However, dense representations raised new…

Stacked Auto-Encoder (SAE) is a kind of deep learning algorithm for unsupervised learning. Which has multi layers that project the vector representation of input data into a lower vector space. These projection vectors are dense…

While large language models provide strong compositional reasoning, existing reasoning segmentation pipelines fail to transparently connect this reasoning to visual perception. Current methods, such as latent query alignment, are end-to-end…

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Sparse Autoencoders (SAEs) have emerged as a promising approach for interpreting neural network representations by learning sparse, human-interpretable features from dense activations. We investigate whether incorporating variational…

Text-to-image (T2I) diffusion models, with their impressive generative capabilities, have been adopted for image editing tasks, demonstrating remarkable efficacy. However, due to attention leakage and collision between the cross-attention…

Balancing fidelity and editability is essential in text-based image editing (TIE), where failures commonly lead to over- or under-editing issues. Existing methods typically rely on attention injections for structure preservation and…

Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic…

Sparse autoencoders (SAEs) aim to disentangle model activations into monosemantic, human-interpretable features. In practice, learned features are often redundant and vary across training runs and sparsity levels, which makes…