Follow
Jack Merullo
Title
Cited by
Cited by
Year
Linearly mapping from image to text space
J Merullo, L Castricato, C Eickhoff, E Pavlick
arXiv preprint arXiv:2209.15162, 2022
1012022
Does clip bind concepts? probing compositionality in large image models
M Lewis, NV Nayak, P Yu, Q Yu, J Merullo, SH Bach, E Pavlick
arXiv preprint arXiv:2212.10537, 2022
502022
Circuit component reuse across tasks in transformer language models
J Merullo, C Eickhoff, E Pavlick
arXiv preprint arXiv:2310.08744, 2023
452023
Characterizing mechanisms for factual recall in language models
Q Yu, J Merullo, E Pavlick
arXiv preprint arXiv:2310.15910, 2023
362023
Language models implement simple word2vec-style vector arithmetic
J Merullo, C Eickhoff, E Pavlick
arXiv preprint arXiv:2305.16130, 2023
35*2023
Investigating sports commentator bias within a large corpus of American football broadcasts
J Merullo, L Yeh, A Handler, A Grissom II, B O'Connor, M Iyyer
arXiv preprint arXiv:1909.03343, 2019
222019
Does CLIP Bind Concepts
M Lewis, NV Nayak, P Yu, Q Yu, J Merullo, SH Bach, E Pavlick
Probing Compositionality in Large Image Models, 2023
62023
Talking Heads: Understanding Inter-layer Communication in Transformer Language Models
J Merullo, C Eickhoff, E Pavlick
arXiv preprint arXiv:2406.09519, 2024
52024
ezCoref: Towards unifying annotation guidelines for coreference resolution
A Gupta, M Karpinska, W Zhao, K Krishna, J Merullo, L Yeh, M Iyyer, ...
arXiv preprint arXiv:2210.07188, 2022
52022
Axiomatic causal interventions for reverse engineering relevance computation in neural retrieval models
C Chen, J Merullo, C Eickhoff
Proceedings of the 47th International ACM SIGIR Conference on Research and …, 2024
42024
Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
S Anand, MA Lepori, J Merullo, E Pavlick
arXiv preprint arXiv:2406.00053, 2024
42024
Pretraining on interactions for learning grounded affordance representations
J Merullo, D Ebert, C Eickhoff, E Pavlick
arXiv preprint arXiv:2207.02272, 2022
42022
$100 K or 100 Days: Trade-offs when Pre-Training with Academic Resources
A Khandelwal, T Yun, NV Nayak, J Merullo, SH Bach, C Sun, E Pavlick
arXiv preprint arXiv:2410.23261, 2024
22024
Transformer mechanisms mimic frontostriatal gating operations when trained on human working memory tasks
A Traylor, J Merullo, MJ Frank, E Pavlick
arXiv preprint arXiv:2402.08211, 2024
22024
ACQuA: Arrhythmia Classification with Quasi-Attractors
W Rudman, J Merullo, L Mercurio, C Eickhoff
medRxiv, 2022.08. 31.22279436, 2022
1*2022
On Linear Representations and Pretraining Data Frequency in Language Models
J Merullo, NA Smith, S Wiegreffe, Y Elazar
The Thirteenth International Conference on Learning Representations, 0
The system can't perform the operation now. Try again later.
Articles 1–16