Cover Image

Interpretability Transfer from Language to Vision via Sparse Autoencoders

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kravets, Alexey, Li, Da, Li, Chuan, Chen, Da, Namboodiri, Vinay P.
Format:	Preprint
Published:	2026
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

Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting
by: Kravets, Alexey, et al.
Published: (2025)

CLIP Adaptation by Intra-modal Overlap Reduction
by: Kravets, Alexey, et al.
Published: (2024)

Zero-Shot Class Unlearning in CLIP with Synthetic Samples
by: Kravets, A., et al.
Published: (2024)

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

Can Unsupervised Segmentation Reduce Annotation Costs for Video Semantic Segmentation?
by: Some, Samik, et al.
Published: (2026)

Trusting Semantic Segmentation Networks
by: Some, Samik, et al.
Published: (2024)

StyleYourSmile: Cross-Domain Face Retargeting Without Paired Multi-Style Data
by: Dey, Avirup, et al.
Published: (2025)

TalkLoRA: Low-Rank Adaptation for Speech-Driven Animation
by: Saunders, Jack, et al.
Published: (2024)

Dubbing for Everyone: Data-Efficient Visual Dubbing using Neural Rendering Priors
by: Saunders, Jack, et al.
Published: (2024)

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

Self-supervised Representation Learning for Cell Event Recognition through Time Arrow Prediction
by: Chen, Cangxiong, et al.
Published: (2024)

EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation
by: Jagpal, Diljeet, et al.
Published: (2025)

MedFocusCLIP : Improving few shot classification in medical datasets using pixel wise attention
by: Arora, Aadya, et al.
Published: (2025)

Determinantal Point Process as an alternative to NMS
by: Some, Samik, et al.
Published: (2020)

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

RISSOLE: Parameter-efficient Diffusion Models via Block-wise Generation and Retrieval-Guidance
by: Mukherjee, Avideep, et al.
Published: (2024)

MERGETUNE: Continued Fine-Tuning of Vision-Language Models
by: Wang, Wenqing, et al.
Published: (2026)

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

RAW: Robust Avatar Watermarking -- Benchmarking and Baseline
by: Parry, Jack, et al.
Published: (2026)

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

Urban Neural Surface Reconstruction from Constrained Sparse Aerial Imagery with 3D SAR Fusion
by: Li, Da, et al.
Published: (2026)

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

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

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)

UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding
by: Zhang, Da, et al.
Published: (2025)

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

ToVE: Efficient Vision-Language Learning via Knowledge Transfer from Vision Experts
by: Wu, Yuanchen, et al.
Published: (2025)

Illumination-Aware Contactless Fingerprint Spoof Detection via Paired Flash-Non-Flash Imaging
by: Sahoo, Roja, et al.
Published: (2026)

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

Long Context Transfer from Language to Vision
by: Zhang, Peiyuan, et al.
Published: (2024)

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

Sparse CLIP: Co-Optimizing Interpretability and Performance in Contrastive Learning
by: Qin, Chuan, et al.
Published: (2026)

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models
by: Pach, Mateusz, et al.
Published: (2025)

Encoding Structural Constraints into Segment Anything Models via Probabilistic Graphical Models
by: Li, Yu, et al.
Published: (2025)

A Vision-Language Foundation Model for Leaf Disease Identification
by: Quoc, Khang Nguyen, et al.
Published: (2025)

Learning without Forgetting for Vision-Language Models
by: Zhou, Da-Wei, et al.
Published: (2023)

Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer
by: Chang, Da, et al.
Published: (2024)

TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation
by: Huang, Victor Shea-Jay, et al.
Published: (2025)

Residualized Temporal Sparse Autoencoders for Interpreting Diffusion Models
by: Yeung, Calvin, et al.
Published: (2026)