Maggie Mi
8 papers · 2023–2026 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(22)
Top co-authors
Research topics
Natural Language Processing
(7)
Resources & Methods
(6)
Artificial Intelligence
(4)
Machine Learning
(4)
Applications
(3)
Core AI
(3)
Learning Types
(3)
Understanding
(3)
Deep Learning
(2)
Learning Paradigms
(2)
Interdisciplinary
(1)
Core Methods
(1)
Linguistics
(1)
Models
(1)
Optimization & Theory
(1)
Keywords
language model
(2)
large language model
(2)
multimodal learning
(1)
multi-label classification
(1)
semantic representation
(1)
natural language understanding
(1)
model interpretability
(1)
error detection
(1)
language acquisition
(1)
uniform information density
(1)
parameter-efficient fine-tuning
(1)
low-rank adaptation
(1)
next-token prediction
(1)
mixture of expert
(1)
vision-language model
(1)
multimodal representation
(1)
prompt tuning
(1)
zero-shot prompting
(1)
distributional learning
(1)
idiomatic expression
(1)
Papers
Enhancing Linguistic Competence of Language Models through Pre-training with Language Learning Tasks
ACL 2026
Rethinking the Idiomaticity Decomposability Hypothesis: Evidence from Distributional Learning
ACL 2026
From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errors
EMNLP 2025
Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp Context
ACL 2025
SemEval-2025 Task 1: AdMIRe - Advancing Multimodal Idiomaticity Representation
SemEval 2025
ShefCDTeam at SemEval-2024 Task 4: A Text-to-Text Model for Multi-Label Classification
SemEval 2024
Sign of the Times: Evaluating the use of Large Language Models for Idiomaticity Detection
COLING 2024
Mmi01 at The BabyLM Challenge: Linguistically Motivated Curriculum Learning for Pretraining in Low-Resource Settings
CoNLL 2023