Michael Y. Hu
5 papers · 2024–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (4) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (16) π§ Keyword Pioneer
π
Cross-Pollinator
(13)
Conferences
EMNLP (2)
ACL (1)
CONLL (1)
ICLR (1)
Top co-authors
Keywords
language modeling
(2)
pretrained language model
(2)
cognitive modeling
(1)
question answering
(1)
multimodal learning
(1)
inductive bia
(1)
language model
(1)
scaling law
(1)
downstream task
(1)
data efficiency
(1)
attention head
(1)
formal language
(1)
sample-efficient learning
(1)
model performance
(1)
syntactic generalization
(1)
linguistic generalization
(1)
linguistic bia
(1)
sample-efficient training
(1)
interaction learning
(1)
hierarchical dependency
(1)
Papers
Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases
ACL 2025
Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check
EMNLP 2025
Findings of the Third BabyLM Challenge: Accelerating Language Modeling Research with Cognitively Plausible Data
EMNLP 2025
Aioli: A Unified Optimization Framework for Language Model Data Mixing
ICLR 2025
Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora
CONLL 2024