Cover Image

SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Stępień, Jakub, Mazur, Marcin, Tabor, Jacek, Spurek, Przemysław
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CEC-MMR: Cross-Entropy Clustering Approach to Multi-Modal Regression
by: Byrski, Krzysztof, et al.
Published: (2025)

Stop Marginalizing My Dreams: Model Inversion via Laplace Kernel for Continual Learning
by: Krukowski, Patryk, et al.
Published: (2026)

GeoGuide: Geometric guidance of diffusion models
by: Poleski, Mateusz, et al.
Published: (2024)

HyperPlanes: Hypernetwork Approach to Rapid NeRF Adaptation
by: Batorski, Paweł, et al.
Published: (2024)

RaySplats: Ray Tracing based Gaussian Splatting
by: Byrski, Krzysztof, et al.
Published: (2025)

Classifier-free Guidance with Adaptive Scaling
by: Malarz, Dawid, et al.
Published: (2025)

MultiPlaneNeRF: Neural Radiance Field with Non-Trainable Representation
by: Zimny, Dominik, et al.
Published: (2023)

PrAViC: Probabilistic Adaptation Framework for Real-Time Video Classification
by: Trędowicz, Magdalena, et al.
Published: (2024)

UnGuide: Learning to Forget with LoRA-Guided Diffusion Models
by: Polowczyk, Agnieszka, et al.
Published: (2025)

Deepfake for the Good: Generating Avatars through Face-Swapping with Implicit Deepfake Generation
by: Stanishevskii, Georgii, et al.
Published: (2024)

ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
by: Borycki, Piotr, et al.
Published: (2026)

GaMeS: Mesh-Based Adapting and Modification of Gaussian Splatting
by: Waczyńska, Joanna, et al.
Published: (2024)

Gaussian Splatting with NeRF-based Color and Opacity
by: Malarz, Dawid, et al.
Published: (2023)

SIDE: Sparse Information Disentanglement for Explainable Artificial Intelligence
by: Dubovik, Viktar, et al.
Published: (2025)

Conceptualizing Embeddings: Sparse Disentanglement for Vision-Language Models
by: Kubaty, Piotr, et al.
Published: (2026)

Interpreting CLIP with Hierarchical Sparse Autoencoders
by: Zaigrajew, Vladimir, et al.
Published: (2025)

Augmentation-aware Self-supervised Learning with Conditioned Projector
by: Przewięźlikowski, Marcin, et al.
Published: (2023)

HyperNeRFGAN: Hypernetwork approach to 3D NeRF GAN
by: Kania, Adam, et al.
Published: (2023)

GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models
by: Nerrise, Favour, et al.
Published: (2026)

DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models
by: Polowczyk, Alicja, et al.
Published: (2026)

EPIC: Explanation of Pretrained Image Classification Networks via Prototype
by: Borycki, Piotr, et al.
Published: (2025)

Bounding Evidence and Estimating Log-Likelihood in VAE
by: Struski, Łukasz, et al.
Published: (2022)

QuantumGS: Quantum Encoding Framework for Gaussian Splatting
by: Wilczyński, Grzegorz, et al.
Published: (2026)

Sparse Autoencoders are Topic Models
by: Girrbach, Leander, et al.
Published: (2025)

ReLAPSe: Reinforcement-Learning-trained Adversarial Prompt Search for Erased concepts in unlearned diffusion models
by: Kolton, Ignacy, et al.
Published: (2026)

GASP: Gaussian Splatting for Physic-Based Simulations
by: Borycki, Piotr, et al.
Published: (2024)

Modeling 3D Surface Manifolds with a Locally Conditioned Atlas
by: Spurek, Przemysław, et al.
Published: (2021)

CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
by: Howil, Kornel, et al.
Published: (2025)

VisTabNet: Adapting Vision Transformers for Tabular Data
by: Wydmański, Witold, et al.
Published: (2024)

Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
by: Kulkarni, Akshay, et al.
Published: (2025)

VeGaS: Video Gaussian Splatting
by: Smolak-Dyżewska, Weronika, et al.
Published: (2024)

SRL-SOA: Self-Representation Learning with Sparse 1D-Operational Autoencoder for Hyperspectral Image Band Selection
by: Ahishali, Mete, et al.
Published: (2022)

Sparse Autoencoders for Interpretable Medical Image Representation Learning
by: Wesp, Philipp, et al.
Published: (2026)

Probing the Representational Power of Sparse Autoencoders in Vision Models
by: Olson, Matthew Lyle, et al.
Published: (2025)

Analyzing Hierarchical Structure in Vision Models with Sparse Autoencoders
by: Olson, Matthew Lyle, et al.
Published: (2025)

LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision
by: Pach, Mateusz, et al.
Published: (2024)

PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models
by: Dziarmaga, Tadeusz, et al.
Published: (2025)

Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment
by: Thasarathan, Harrish, et al.
Published: (2025)

SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning
by: Zhang, Jintao, et al.
Published: (2026)

MeshSplats: Mesh-Based Rendering with Gaussian Splatting Initialization
by: Tobiasz, Rafał, et al.
Published: (2025)