Jack Merullo
11 papers · 2019–2025 · 5 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (18)
💎
Century Club · Bronze
❓
The Questioner
🗃️
Keyword Collector
(50)
Top co-authors
Research topics
Artificial Intelligence
(8)
Machine Learning
(8)
Core AI
(7)
Deep Learning
(5)
Core Methods
(5)
Natural Language Processing
(3)
Architectures
(3)
Learning Types · Machine Learning
(3)
Learning Paradigms
(2)
Learning Types · Deep Learning
(2)
Application Areas
(1)
Generation
(1)
Optimization & Theory
(1)
Resources & Methods
(1)
Understanding
(1)
Keywords
attention head
(3)
mechanistic interpretability
(2)
representation learning
(2)
in-context learning
(2)
vision-language model
(2)
transformer language model
(2)
masked language model
(1)
singular value decomposition
(1)
natural language processing
(1)
predictive modeling
(1)
coreference resolution
(1)
crowdsourcing annotation
(1)
linear projection
(1)
latent representation
(1)
text mining
(1)
in-weights learning
(1)
factual knowledge
(1)
circuit analysis
(1)
feed-forward network
(1)
language model
(1)
Papers
Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
ICLR 2025
On Linear Representations and Pretraining Data Frequency in Language Models
ICLR 2025
Circuit Component Reuse Across Tasks in Transformer Language Models
ICLR 2024
Does CLIP Bind Concepts? Probing Compositionality in Large Image Models
EACL 2024
Language Models Implement Simple Word2Vec-style Vector Arithmetic
NAACL 2024
Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
NeurIPS 2024
Characterizing Mechanisms for Factual Recall in Language Models
EMNLP 2023
ezCoref: Towards Unifying Annotation Guidelines for Coreference Resolution
EACL 2023
Linearly Mapping from Image to Text Space
ICLR 2023
Pretraining on Interactions for Learning Grounded Affordance Representations
NAACL 2022
Investigating Sports Commentator Bias within a Large Corpus of American Football Broadcasts
EMNLP 2019