Cover Image

Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chatzoudis, Gerasimos, Polyzos, Konstantinos D., Li, Zhuowei, Gu, Difei, Moran, Gemma E., Wang, Hao, Metaxas, Dimitris N.
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering
by: Chatzoudis, Gerasimos, et al.
Published: (2025)

LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery
by: Gu, Difei, et al.
Published: (2026)

Anatomy-VLM: A Fine-grained Vision-Language Model for Medical Interpretation
by: Gu, Difei, et al.
Published: (2025)

RadAlign: Advancing Radiology Report Generation with Vision-Language Concept Alignment
by: Gu, Difei, et al.
Published: (2025)

Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
by: Dafnis, Konstantinos M., et al.
Published: (2025)

Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classification
by: Gao, Yunhe, et al.
Published: (2024)

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering
by: Li, Zhuowei, et al.
Published: (2025)

NT-ViT: Neural Transcoding Vision Transformers for EEG-to-fMRI Synthesis
by: Lanzino, Romeo, et al.
Published: (2024)

Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders
by: Harrasse, Abir, et al.
Published: (2025)

MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
by: Dao, Quan, et al.
Published: (2026)

K-Prism: A Knowledge-Guided and Prompt Integrated Universal Medical Image Segmentation Model
by: Guo, Bangwei, et al.
Published: (2025)

Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation
by: Gao, Yunhe, et al.
Published: (2023)

Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
by: Damianos, Dimitrios, et al.
Published: (2026)

Transcoders Beat Sparse Autoencoders for Interpretability
by: Paulo, Gonçalo, et al.
Published: (2025)

Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs
by: Gao, Hang, et al.
Published: (2026)

Prune, Interpret, Evaluate: A Cross-Layer Transcoder-Native Framework for Efficient Circuit Discovery via Feature Attribution
by: Chen, Qinhao, et al.
Published: (2026)

Implicit In-context Learning
by: Li, Zhuowei, et al.
Published: (2024)

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs
by: Draye, Florent, et al.
Published: (2026)

Show and Segment: Universal Medical Image Segmentation via In-Context Learning
by: Gao, Yunhe, et al.
Published: (2025)

Transcoders Find Interpretable LLM Feature Circuits
by: Dunefsky, Jacob, et al.
Published: (2024)

Towards Interpretable Deep Generative Models via Causal Representation Learning
by: Moran, Gemma E., et al.
Published: (2025)

M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark
by: Zhou, Yang, et al.
Published: (2025)

CRaFT: Circuit-Guided Refusal Feature Selection via Cross-Layer Transcoders
by: Kim, Su-Hyeon, et al.
Published: (2026)

Can Sound Replace Vision in LLaVA With Token Substitution?
by: Vosoughi, Ali, et al.
Published: (2025)

A Switching Nonlinear Model Predictive Control Strategy for Safe Collision Handling by an Underwater Vehicle-Manipulator System
by: Polyzos, Ioannis G., et al.
Published: (2026)

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

Can Large Language Models Beat Wall Street? Unveiling the Potential of AI in Stock Selection
by: Fatouros, Georgios, et al.
Published: (2024)

Evidence Over Plans: Online Trajectory Verification for Skill Distillation
by: Zhou, Yang, et al.
Published: (2026)

Protein Circuit Tracing via Cross-layer Transcoders
by: Tsui, Darin, et al.
Published: (2026)

Can Vision Replace Text in Working Memory? Evidence from Spatial n-Back in Vision-Language Models
by: Liang, Sichu, et al.
Published: (2026)

3D Reconstruction in Noisy Agricultural Environments: A Bayesian Optimization Perspective for View Planning
by: Bacharis, Athanasios, et al.
Published: (2023)

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

Transcoder-based Circuit Analysis for Interpretable Single-Cell Foundation Models
by: Hosokawa, Sosuke, et al.
Published: (2025)

LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation
by: Jin, Can, et al.
Published: (2025)

Score-Guided Diffusion for 3D Human Recovery
by: Stathopoulos, Anastasis, et al.
Published: (2024)

Language Recoding and Transcoding
Published: (2026)

Distilling Vision Transformers for Distortion-Robust Representation Learning
by: Alexis, Konstantinos, et al.
Published: (2026)

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

ComFe: An Interpretable Head for Vision Transformers
by: Mannix, Evelyn J., et al.
Published: (2024)

The Missing Point in Vision Transformers for Universal Image Segmentation
by: Shahabodini, Sajjad, et al.
Published: (2025)