Cover Image

Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kim, Dahye, Ghadiyaram, Deepti
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

$\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models
by: Kim, Dahye, et al.
Published: (2024)

DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers
by: Kim, Dahye, et al.
Published: (2026)

What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
by: Thomas, Xavier, et al.
Published: (2025)

A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning
by: Chen, Tianle, et al.
Published: (2026)

Swift Sampling: Selecting Temporal Surprises via Taylor Series
by: Kim, Dahye, et al.
Published: (2026)

Improving Physical Object State Representation in Text-to-Image Generative Systems
by: Chen, Tianle, et al.
Published: (2025)

Generative Action Tell-Tales: Assessing Human Motion in Synthesized Videos
by: Thomas, Xavier, et al.
Published: (2025)

Semantic Richness or Geometric Reasoning? The Fragility of VLM's Visual Invariance
by: Qiu, Jason, et al.
Published: (2026)

Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models
by: Saichandran, Ketan Suhaas, et al.
Published: (2025)

FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation
by: Ikechukwu, Nicholas, et al.
Published: (2026)

Steerers: A framework for rotation equivariant keypoint descriptors
by: Bökman, Georg, et al.
Published: (2023)

Some Modalities are More Equal Than Others: Decoding and Architecting Multimodal Integration in MLLMs
by: Chen, Tianle, et al.
Published: (2025)

FAGER: Factually Grounded Evaluation and Refinement of Text-to-Image Models
by: Lim, Youngsun, et al.
Published: (2026)

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

Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders
by: Nakka, Krishna Kanth
Published: (2025)

Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs
by: Tasnim, Nazia, et al.
Published: (2025)

Seeing Isn't Orienting: A Cognitively Grounded Benchmark Reveals Systematic Orientation Failures in MLLMs Supplementary
by: Tasnim, Nazia, et al.
Published: (2026)

SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders
by: Cassano, Enrico, et al.
Published: (2025)

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

Transformer with Leveraged Masked Autoencoder for video-based Pain Assessment
by: Nguyen, Minh-Duc, et al.
Published: (2024)

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
by: Li, Qing, et al.
Published: (2025)

Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP
by: Ro, Yusung, et al.
Published: (2026)

DreamSteerer: Enhancing Source Image Conditioned Editability using Personalized Diffusion Models
by: Yu, Zhengyang, et al.
Published: (2024)

GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition
by: Ramaswamy, Vikram V., et al.
Published: (2023)

SPARC: Concept-Aligned Sparse Autoencoders for Cross-Model and Cross-Modal Interpretability
by: Nasiri-Sarvi, Ali, et al.
Published: (2025)

No Concept Left Behind: Test-Time Optimization for Compositional Text-to-Image Generation
by: Sameti, Mohammad Hossein, et al.
Published: (2025)

Causal Interpretation of Sparse Autoencoder Features in Vision
by: Han, Sangyu, et al.
Published: (2025)

SoftSAE: Dynamic Top-K Selection for Adaptive Sparse Autoencoders
by: Stępień, Jakub, et al.
Published: (2026)

Model-Agnostic Gender Bias Control for Text-to-Image Generation via Sparse Autoencoder
by: Wu, Chao, et al.
Published: (2025)

SPG: Sparse-Projected Guides with Sparse Autoencoders for Zero-Shot Anomaly Detection
by: Nanaumi, Tomoyasu, et al.
Published: (2026)

Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation
by: Liu, Jiaming, et al.
Published: (2023)

Interpretable and Testable Vision Features via Sparse Autoencoders
by: Stevens, Samuel, et al.
Published: (2025)

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

Guided Trajectory Optimization with Sparse Scaling for Test-Time Diffusion
by: Dai, Gang, et al.
Published: (2026)

ConceptMaster: Multi-Concept Video Customization on Diffusion Transformer Models Without Test-Time Tuning
by: Huang, Yuzhou, et al.
Published: (2025)

BRIC: Bridging Kinematic Plans and Physical Control at Test Time
by: Lim, Dohun, et al.
Published: (2025)

Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders
by: Stevens, Samuel, et al.
Published: (2025)

Interpretability Transfer from Language to Vision via Sparse Autoencoders
by: Kravets, Alexey, et al.
Published: (2026)

LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer
by: Panda, Raina, et al.
Published: (2025)

Sparse Autoencoders enable Robust and Interpretable Fine-tuning of CLIP models
by: Morelli, Fabian, et al.
Published: (2026)