Cover Image

Scale Alone Does not Improve Mechanistic Interpretability in Vision Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zimmermann, Roland S., Klein, Thomas, Brendel, Wieland
Format:	Preprint
Published:	2023
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

LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models
by: Li, Fanfei, et al.
Published: (2025)

Low-Pass Filtering Improves Behavioral Alignment of Vision Models
by: Wolff, Max, et al.
Published: (2026)

In Search of Forgotten Domain Generalization
by: Mayilvahanan, Prasanna, et al.
Published: (2024)

InfoNCE: Identifying the Gap Between Theory and Practice
by: Rusak, Evgenia, et al.
Published: (2024)

Don't trust your eyes: on the (un)reliability of feature visualizations
by: Geirhos, Robert, et al.
Published: (2023)

Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?
by: Mayilvahanan, Prasanna, et al.
Published: (2023)

Generation is Required for Data-Efficient Perception
by: Brady, Jack, et al.
Published: (2025)

Effective pruning of web-scale datasets based on complexity of concept clusters
by: Abbas, Amro, et al.
Published: (2024)

From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models
by: Kim, Yearim, et al.
Published: (2026)

Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation
by: Li, Qiming, et al.
Published: (2025)

Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality
by: Cedro, Mateusz, et al.
Published: (2026)

Interaction Asymmetry: A General Principle for Learning Composable Abstractions
by: Brady, Jack, et al.
Published: (2024)

Mechanistically Guided LoRA Improves Paraphrase Consistency in Medical Vision-Language Models
by: Sadanandan, Binesh, et al.
Published: (2026)

Capability $\neq$ Interpretability: Human Interpretability of Vision Foundation Models
by: Colin, Julien, et al.
Published: (2026)

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models
by: Che, Liwei, et al.
Published: (2026)

3VL: Using Trees to Improve Vision-Language Models' Interpretability
by: Yellinek, Nir, et al.
Published: (2023)

MentisOculi: Revealing the Limits of Reasoning with Mental Imagery
by: Zeller, Jana, et al.
Published: (2026)

Mechanistic Interpretability of Diffusion Models: Circuit-Level Analysis and Causal Validation
by: Roy, Dip
Published: (2025)

Segmenting Wood Rot using Computer Vision Models
by: Kammerbauer, Roland, et al.
Published: (2024)

LLM-Powered Flood Depth Estimation from Social Media Imagery: A Vision-Language Model Framework with Mechanistic Interpretability for Transportation Resilience
by: Fuad, Nafis, et al.
Published: (2026)

Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System
by: Valentin, Romeo, et al.
Published: (2026)

DINO-QPM: Adapting Visual Foundation Models for Globally Interpretable Image Classification
by: Zimmermann, Robert, et al.
Published: (2026)

LVLM-Interpret: An Interpretability Tool for Large Vision-Language Models
by: Stan, Gabriela Ben Melech, et al.
Published: (2024)

All Eyes, no IMU: Learning Flight Attitude from Vision Alone
by: Hagenaars, Jesse J., et al.
Published: (2025)

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
by: Joseph, Sonia, et al.
Published: (2025)

LHRS-Bot-Nova: Improved Multimodal Large Language Model for Remote Sensing Vision-Language Interpretation
by: Li, Zhenshi, et al.
Published: (2024)

Improving Computer Vision Interpretability: Transparent Two-level Classification for Complex Scenes
by: Scholz, Stefan, et al.
Published: (2024)

[Re] Improving Interpretation Faithfulness for Vision Transformers
by: Kurek, Izabela, et al.
Published: (2025)

Artwork Interpretation with Vision Language Models: A Case Study on Emotions and Emotion Symbols
by: Padó, Sebastian, et al.
Published: (2025)

Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style
by: Limpijankit, Marvin, et al.
Published: (2026)

VGGSounder: Audio-Visual Evaluations for Foundation Models
by: Zverev, Daniil, et al.
Published: (2025)

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability
by: Aravindan, Ashwath Vaithinathan, et al.
Published: (2025)

How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
by: Lee, Seongyun, et al.
Published: (2024)

Interpretability-Aware Vision Transformer
by: Qiang, Yao, et al.
Published: (2023)

Interpreting Low-level Vision Models with Causal Effect Maps
by: Hu, Jinfan, et al.
Published: (2024)

Multi-Modal Interpretability for Enhanced Localization in Vision-Language Models
by: Imran, Muhammad, et al.
Published: (2025)

Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability
by: Shi, Yingdong, et al.
Published: (2025)

Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale
by: Li, Songze, et al.
Published: (2025)

Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales
by: Qi, Shuren, et al.
Published: (2024)

Improving Interpretation Faithfulness for Vision Transformers
by: Hu, Lijie, et al.
Published: (2023)