Lisa Bylinina
7 papers · 2022–2025 · 3 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
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(17)
❓
The Questioner
Top co-authors
Research topics
Natural Language Processing
(4)
Machine Learning
(3)
Artificial Intelligence
(2)
Computer Vision
(2)
Deep Learning
(2)
Interdisciplinary
(2)
Architectures
(2)
Core AI · Artificial Intelligence
(2)
Core Methods
(2)
Resources & Methods
(2)
Understanding
(2)
Application Areas
(1)
Cognitive Science
(1)
Core AI · Computer Vision
(1)
Domain-Specific
(1)
Keywords
language model
(2)
multimodal learning
(2)
visual grounding
(2)
model merging
(1)
semantic representation
(1)
vision-language model
(1)
text embedding
(1)
pre-trained language model
(1)
clip embedding
(1)
word embedding
(1)
paraphrase data
(1)
linguistic analysis
(1)
multimodal embedding
(1)
linguistic phenomenon
(1)
linguistic generalization
(1)
second language learning
(1)
psycholinguistic experiment
(1)
parameter fusion
(1)
text-only model
(1)
baby lm challenge
(1)
Papers
Model Merging to Maintain Language-Only Performance in Developmentally Plausible Multimodal Models
EMNLP 2025
Are BabyLMs Second Language Learners?
CoNLL 2024
Individuation in Neural Models with and without Visual Grounding
EMNLP 2024
Connecting degree and polarity: An artificial language learning study
EMNLP 2023
Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations
ACL 2023
Too Much Information: Keeping Training Simple for BabyLMs
CoNLL 2023
Transformers in the loop: Polarity in neural models of language
ACL 2022