Martina G. Vilas
4 papers · 2023–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Artificial Intelligence
(3)
Core AI · Artificial Intelligence
(3)
Computer Vision
(2)
Machine Learning
(2)
Deep Learning
(1)
Interdisciplinary
(1)
Analysis
(1)
Application Areas
(1)
Architectures
(1)
Cognitive Science
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Optimization & Theory
(1)
Science
(1)
Keywords
mechanistic interpretability
(2)
mechanistic explanation
(2)
self-attention mechanism
(1)
interpretability
(1)
explainable ai
(1)
object localization
(1)
computational complexity
(1)
cognitive neuroscience
(1)
vision-language model
(1)
attention head
(1)
circuit discovery
(1)
fixed-parameter tractability
(1)
neural network
(1)
causal mediation analysis
(1)
class embedding
(1)
class embedding space
(1)
conceptual framework
(1)
inner mechanisms
(1)
image classification
(1)
methodological strategies
(1)
Papers
Mechanisms of Object Localization in Vision-Language Models
CVPR 2026
The Computational Complexity of Circuit Discovery for Inner Interpretability
ICLR 2025
Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience
ICML 2024
Analyzing Vision Transformers for Image Classification in Class Embedding Space
NeurIPS 2023