Fernanda Viégas
5 papers · 2018–2025 · 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
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🐣
Hot Topic Early Bird
🧭
Keyword Pioneer
Venues
Top co-authors
Research topics
Keywords
image classification
(2)
model interpretability
(1)
pretraining
(1)
saliency map
(1)
world model
(1)
sequence model
(1)
attention head
(1)
integrated gradient
(1)
linear representation
(1)
attribution method
(1)
internal representation
(1)
activation steering
(1)
inference-time intervention
(1)
large language model
(1)
neural network
(1)
concept activation vector
(1)
interventional analysis
(1)
testing with cav
(1)
emergent representation
(1)
region-based attribution
(1)
Papers
When Bad Data Leads to Good Models
ICML 2025
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
ICLR 2023
Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
NeurIPS 2023
XRAI: Better Attributions Through Regions
ICCV 2019
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
ICML 2018