Interpretability Transfer from Language to Vision via Sparse Autoencoders

• URL: http://arxiv.org/abs/2605.24946v1
• Date: Sun, 24 May 2026 08:47:36 GMT
• Title: Interpretability Transfer from Language to Vision via Sparse Autoencoders
• Abstract summary: Recent advances in language model interpretability using sparse autoencoders (SAEs) have yet to effectively translate to the visual domain.<n>We introduce Visual Interpretability via SAE Transfer Alignment (VISTA), a framework that transfers interpretability from language to vision in a LLaVA-style vision-language model.
• Score: 24.472985705517
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in language model interpretability using sparse autoencoders (SAEs) have yet to effectively translate to the visual domain, mainly due to the difficulty and ambiguity of labeling visual concepts. In this paper, we introduce Visual Interpretability via SAE Transfer Alignment (VISTA), a framework that transfers interpretability from language to vision in a LLaVA-style vision-language model by constraining a visual projector to map visual tokens into an LLM's pre-existing, labeled textual SAE space. This approach enables visual interpretability without training dedicated vision SAEs. By regularizing the projector using the LLM's SAE reconstruction loss, VISTA achieves a threefold increase in the matching rate, which measures how accurately the most activating textual concepts in the SAE space correspond to semantic elements in the image. Using this framework, we further analyze spatial localization properties of different vision encoders and show that DINOv2 features have stronger localization abilities than other encoders. Leveraging this precision, we validate VISTA's cross-modal alignment through fine-grained, localized concept interventions, where specific objects are removed or replaced in the model's perception while preserving the surrounding scene. This results in improvements of 35% in object removal and 47% in object replacement tasks over vision-only baselines, providing causal evidence that visual tokens inhabit the text SAE manifold. These contributions are validated across multiple LLM architectures.

Related papers

• Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens [54.18057944158818]
  Chain-of-Visual-Thought (COVT) is a framework that enables Vision-Language Models (VLMs) to reason through continuous visual tokens.<n>Within a small budget of roughly 20 tokens, COVT distills knowledge from lightweight vision experts.<n>During training, the VLM with COVT autoregressively predicts visual tokens to reconstruct dense supervision signals.
  arXiv  Detail & Related papers  (2025-11-24T18:55:19Z)
• Attention Guided Alignment in Efficient Vision-Language Models [56.20286899428444]
  Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs)<n>This paper presents a comprehensive analysis of attention patterns in efficient VLMs.<n>We introduce Attention-Guided Efficient Vision-Language Models (AGE-VLM), a novel framework that enhances visual grounding through interleaved cross-attention layers.
  arXiv  Detail & Related papers  (2025-11-21T21:36:48Z)
• VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set [80.50996301430108]
  The alignment of vision-language representations endows current Vision-Language Models with strong multi-modal reasoning capabilities.<n>We propose VL-SAE, a sparse autoencoder that encodes vision-language representations into its hidden activations.<n>For interpretation, the alignment between vision and language representations can be understood by comparing their semantics with concepts.
  arXiv  Detail & Related papers  (2025-10-24T10:29:31Z)
• How Visual Representations Map to Language Feature Space in Multimodal LLMs [9.880509106657009]
  We study the mechanism by which vision-language models (VLMs) achieve alignment of visual and linguistic representations.<n>By keeping the language model frozen, we ensure it maintains its original language representations without adaptation to visual data.<n>We reveal the layer-wise progression through which visual representations gradually align with language feature representations, converging in middle-to-later layers.
  arXiv  Detail & Related papers  (2025-06-13T17:34:05Z)
• Revisit What You See: Disclose Language Prior in Vision Tokens for LVLM Decoding [6.612630497074871]
  Large Vision-Language Models (LVLMs) achieve strong performance across multimodal tasks by integrating visual perception with language understanding.<n>We propose ReVisiT, a training-free decoding method that references vision tokens to guide text generation.
  arXiv  Detail & Related papers  (2025-06-11T08:46:55Z)
• Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection [53.558449071113245]
  Vision-Language Models (VLMs) leverage aligned visual encoders to transform images into visual tokens, allowing them to be processed similarly to text by the backbone large language model (LLM)<n>Recent advancements in vision-language modeling introduce image cropping techniques that feed all encoded sub-images into the model.<n>We propose a lightweight, universal framework that seamlessly integrates with existing VLMs to enhance their ability to process finegrained details.
  arXiv  Detail & Related papers  (2025-03-14T18:33:31Z)
• AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding [79.43306110124875]
  AlignVLM is a vision-text alignment method that maps visual features to a weighted average of text embeddings.<n>Our experiments show that AlignVLM achieves state-of-the-art performance compared to prior alignment methods.
  arXiv  Detail & Related papers  (2025-02-03T13:34:51Z)
• LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models [57.92316645992816]
  Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space.<n>We introduce LayoutVLM, a framework and scene layout representation that exploits the semantic knowledge of Vision-Language Models (VLMs)<n>We demonstrate that fine-tuning VLMs with the proposed scene layout representation extracted from existing scene datasets can improve their reasoning performance.
  arXiv  Detail & Related papers  (2024-12-03T06:15:04Z)
• Towards Interpreting Visual Information Processing in Vision-Language Models [24.51408101801313]
  Vision-Language Models (VLMs) are powerful tools for processing and understanding text and images.<n>We study the processing of visual tokens in the language model component of LLaVA, a prominent VLM.
  arXiv  Detail & Related papers  (2024-10-09T17:55:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.