Martin Wattenberg
11 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (13)
π
Keyword Champion
(2)
π§
Keyword Pioneer
π
Keyword Trendsetter Combo
(3)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(58)
Venues
Top co-authors
Research topics
Keywords
linear representation
(2)
world model
(2)
representation learning
(1)
embedding space
(1)
interpretability
(1)
self-supervised learning
(1)
knowledge representation
(1)
identifiability
(1)
bert model
(1)
energy minimization
(1)
concept representation
(1)
model interpretability
(1)
pretraining
(1)
linear transformation
(1)
graph topology
(1)
in-context learning
(1)
stability
(1)
convex hull
(1)
language model
(1)
image classification
(1)
Papers
Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models
ICML 2025
ICLR: In-Context Learning of Representations
ICLR 2025
When Bad Data Leads to Good Models
ICML 2025
A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity
ICML 2024
Linearity of Relation Decoding in Transformer Language Models
ICLR 2024
Q-Probe: A Lightweight Approach to Reward Maximization for Language Models
ICML 2024
Emergent Linear Representations in World Models of Self-Supervised Sequence Models
EMNLP 2023
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
Visualizing and Measuring the Geometry of BERT
NeurIPS 2019
Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
ICML 2018