Cover Image

A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Zihao, Basu, Samyadeep, Beigi, Mohammad, Manjunatha, Varun, Rossi, Ryan A., Wang, Zichao, Zhou, Yufan, Balasubramanian, Sriram, Zarei, Arman, Rezaei, Keivan, Shen, Ying, Yao, Barry Menglong, Xu, Zhiyang, Liu, Qin, Zhang, Yuxiang, Sun, Yan, Liu, Shilong, Shen, Li, Li, Hongxuan, Feizi, Soheil, Huang, Lifu
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models
by: Balasubramanian, Sriram, et al.
Published: (2025)

Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
by: Balasubramanian, Sriram, et al.
Published: (2024)

Localizing Knowledge in Diffusion Transformers
by: Zarei, Arman, et al.
Published: (2025)

On Mechanistic Knowledge Localization in Text-to-Image Generative Models
by: Basu, Samyadeep, et al.
Published: (2024)

On Mechanistic Circuits for Extractive Question-Answering
by: Basu, Samyadeep, et al.
Published: (2025)

Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings
by: Zarei, Arman, et al.
Published: (2024)

Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models
by: Balasubramanian, Sriram, et al.
Published: (2025)

SliderEdit: Continuous Image Editing with Fine-Grained Instruction Control
by: Zarei, Arman, et al.
Published: (2025)

Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models
by: Moayeri, Mazda, et al.
Published: (2024)

SpecHop: Continuous Speculation for Accelerating Multi-Hop Retrieval Agents
by: Saberi, Mehrdad, et al.
Published: (2026)

Reasoning Under Uncertainty: Exploring Probabilistic Reasoning Capabilities of LLMs
by: Pournemat, Mobina, et al.
Published: (2025)

IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning
by: Ghosal, Soumya Suvra, et al.
Published: (2024)

Revisiting the Past: Data Unlearning with Model State History
by: Rezaei, Keivan, et al.
Published: (2025)

PRIME: Prioritizing Interpretability in Failure Mode Extraction
by: Rezaei, Keivan, et al.
Published: (2023)

Online Advertisements with LLMs: Opportunities and Challenges
by: Feizi, Soheil, et al.
Published: (2023)

RePanda: Pandas-powered Tabular Verification and Reasoning
by: Chegini, Atoosa Malemir, et al.
Published: (2025)

Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP
by: Basu, Samyadeep, et al.
Published: (2023)

Navigating the Dual Facets: A Comprehensive Evaluation of Sequential Memory Editing in Large Language Models
by: Lin, Zihao, et al.
Published: (2024)

AgentComp: From Agentic Reasoning to Compositional Mastery in Text-to-Image Models
by: Zarei, Arman, et al.
Published: (2025)

Understanding Information Storage and Transfer in Multi-modal Large Language Models
by: Basu, Samyadeep, et al.
Published: (2024)

Model-Adaptive Tool Necessity Reveals the Knowing-Doing Gap in LLM Tool Use
by: Cheng, Yize, et al.
Published: (2026)

SpurLens: Automatic Detection of Spurious Cues in Multimodal LLMs
by: Hosseini, Parsa, et al.
Published: (2025)

DREW : Towards Robust Data Provenance by Leveraging Error-Controlled Watermarking
by: Saberi, Mehrdad, et al.
Published: (2024)

RESTOR: Knowledge Recovery in Machine Unlearning
by: Rezaei, Keivan, et al.
Published: (2024)

Can AI-Generated Text be Reliably Detected?
by: Sadasivan, Vinu Sankar, et al.
Published: (2023)

Error-driven Data-efficient Large Multimodal Model Tuning
by: Yao, Barry Menglong, et al.
Published: (2024)

Failing to Explore: Language Models on Interactive Tasks
by: JafariRaviz, Mahdi, et al.
Published: (2026)

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
by: Saberi, Mehrdad, et al.
Published: (2023)

Persona-SQ: A Personalized Suggested Question Generation Framework For Real-world Documents
by: Lin, Zihao, et al.
Published: (2024)

Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories
by: Beigi, Mohammad, et al.
Published: (2025)

AMELI: Enhancing Multimodal Entity Linking with Fine-Grained Attributes
by: Yao, Barry Menglong, et al.
Published: (2023)

Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning
by: Kalibhat, Neha, et al.
Published: (2024)

MULTISCRIPT: Multimodal Script Learning for Supporting Open Domain Everyday Tasks
by: Qi, Jingyuan, et al.
Published: (2023)

Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
by: Chegini, Atoosa, et al.
Published: (2026)

Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing
by: Saha, Shoumik, et al.
Published: (2025)

Tool Preferences in Agentic LLMs are Unreliable
by: Faghih, Kazem, et al.
Published: (2025)

Organophosphorus Layer‐Modified CoFe‐LDH/Co(OH) 2 Electrocatalyst: Green Synthesis and Mechanistic Insights into Enhanced Oxygen Evolution Activity
by: Shuo Liu, et al.
Published: (2025)

Hop, Skip, and Overthink: Diagnosing Why Reasoning Models Fumble during Multi-Hop Analysis
by: Yadav, Anushka, et al.
Published: (2025)

SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models
by: Zhang, Yue, et al.
Published: (2024)

How Do Large Language Models Learn Concepts During Continual Pre-Training?
by: Yao, Barry Menglong, et al.
Published: (2026)