Imagen de Portada

Mechanistically Interpreting Compression in Vision-Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Elluru, Veeraraju, Singh, Arth, Aguero, Roberto, Agarwal, Ajay, Das, Debojyoti, Paul, Hreetam
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Bias-Aware Machine Unlearning: Towards Fairer Vision Models via Controllable Forgetting
por: Aylapuram, Sai Siddhartha Chary, et al.
Publicado: (2025)

Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models
por: Singh, Arth
Publicado: (2026)

EMA Is Not All You Need: Mapping the Boundary Between Structure and Content in Recurrent Context
por: Singh, Arth
Publicado: (2026)

Causally Grounded Mechanistic Interpretability for LLMs with Faithful Natural-Language Explanations
por: Mahale, Ajay Pravin
Publicado: (2026)

Towards Understanding and Improving Refusal in Compressed Models via Mechanistic Interpretability
por: Chhabra, Vishnu Kabir, et al.
Publicado: (2025)

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

Mechanistic Interpretability of Emotion Inference in Large Language Models
por: Tak, Ala N., et al.
Publicado: (2025)

Mechanistic Behavior Editing of Language Models
por: Singh, Joykirat, et al.
Publicado: (2024)

Mechanistic Interpretability of Socio-Political Frames in Language Models
por: Asghari, Hadi, et al.
Publicado: (2025)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
por: Cho, Hakaze, et al.
Publicado: (2025)

Challenges in Mechanistically Interpreting Model Representations
por: Golechha, Satvik, et al.
Publicado: (2024)

Seeing Through Circuits: Faithful Mechanistic Interpretability for Vision Transformers
por: Żukowska, Nina, et al.
Publicado: (2026)

Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design
por: Jacob, Bruno, et al.
Publicado: (2025)

Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models
por: Winninger, Thomas, et al.
Publicado: (2025)

Supernova Event Dataset: Interpreting Large Language Models' Personality through Critical Event Analysis
por: Agarwal, Pranav, et al.
Publicado: (2025)

Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
por: Kim, Geonhee, et al.
Publicado: (2024)

MALCDF: A Distributed Multi-Agent LLM Framework for Real-Time Cyber
por: Bhardwaj, Arth, et al.
Publicado: (2025)

Mechanistic Interpretability of LoRA-Adapted Language Models for Nuclear Reactor Safety Applications
por: Lee, Yoon Pyo
Publicado: (2025)

Mechanistic Interpretability Needs Philosophy
por: Williams, Iwan, et al.
Publicado: (2025)

Mechanistic Interpretability for AI Safety -- A Review
por: Bereska, Leonard, et al.
Publicado: (2024)

A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
por: Rai, Daking, et al.
Publicado: (2024)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
por: Wang, Xu, et al.
Publicado: (2026)

Mechanistic Interpretability with SAEs: Probing Religion, Violence, and Geography in Large Language Models
por: Simbeck, Katharina, et al.
Publicado: (2025)

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

Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability
por: Geiger, Atticus, et al.
Publicado: (2023)

Mechanistic Interpretability of Brain-to-Speech Models Across Speech Modes
por: Maghsoudi, Maryam, et al.
Publicado: (2026)

reward-lens: A Mechanistic Interpretability Library for Reward Models
por: Nadaf, Mohammed Suhail B
Publicado: (2026)

A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models
por: Lin, Zihao, et al.
Publicado: (2025)

Mechanistic Interpretability in the Presence of Architectural Obfuscation
por: Florencio, Marcos, et al.
Publicado: (2025)

Auditing Disability Representation in Vision-Language Models
por: Panda, Srikant, et al.
Publicado: (2026)

Beyond BeautifulSoup: Benchmarking LLM-Powered Web Scraping for Everyday Users
por: Bhardwaj, Arth, et al.
Publicado: (2026)

Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language Models
por: Beniwal, Himanshu, et al.
Publicado: (2026)

The Security Threat of Compressed Projectors in Large Vision-Language Models
por: Zhang, Yudong, et al.
Publicado: (2025)

Mechanistic Interpretability of GPT-like Models on Summarization Tasks
por: Mishra, Anurag
Publicado: (2025)

Interpretable Physics Reasoning and Performance Taxonomy in Vision-Language Models
por: Pawar, Pranav, et al.
Publicado: (2025)

On the Mechanistic Interpretability of Neural Networks for Causality in Bio-statistics
por: Conan, Jean-Baptiste A.
Publicado: (2025)

MINAR: Mechanistic Interpretability for Neural Algorithmic Reasoning
por: He, Jesse, et al.
Publicado: (2026)

RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models
por: Chen, Yuxuan, et al.
Publicado: (2025)

Towards Ethical Multi-Agent Systems of Large Language Models: A Mechanistic Interpretability Perspective
por: Lee, Jae Hee, et al.
Publicado: (2025)

Towards a Systematic Evaluation of Hallucinations in Large-Vision Language Models
por: Seth, Ashish, et al.
Publicado: (2024)