Michael Hahn
16 papers · 2013–2026 · 8 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 ↓+5 more ↓ Show less ↑
🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Gold 🗺️ Taxonomy Completionist (29) 🏃 Academic Marathon · Half 🐣 Hot Topic Early Bird
🌈
Renaissance Researcher
(7)
❓
The Questioner
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(85)
Top co-authors
Research topics
Machine Learning
(10)
Deep Learning
(9)
Architectures
(8)
Optimization & Theory · Machine Learning
(8)
Artificial Intelligence
(6)
Core AI
(6)
Optimization & Theory · Deep Learning
(5)
Interdisciplinary
(4)
Linguistics
(4)
Mathematics & Optimization
(3)
Mathematics
(3)
Natural Language Processing
(2)
Resources & Methods
(2)
Computer Science
(1)
Healthcare & Medicine
(1)
Keywords
formal language
(3)
transformer architecture
(2)
hierarchical structure
(2)
recurrent neural network
(2)
chain-of-thought reasoning
(1)
language modeling
(1)
communicative efficiency
(1)
neural network optimization
(1)
attention mechanism
(1)
loss landscape
(1)
computational complexity
(1)
theoretical analysis
(1)
machine learning
(1)
expressive power
(1)
state space model
(1)
corpus linguistics
(1)
expressivity
(1)
hidden state
(1)
communication complexity
(1)
curriculum learning
(1)
Papers
Systematicity between Forms and Meanings across Languages Supports Efficient Communication
ACL 2026
Tug-of-war between idioms’ figurative and literal interpretations in LLMs
EACL 2026
A Formal Framework for Understanding Length Generalization in Transformers
ICLR 2025
Language models can learn implicit multi-hop reasoning, but only if they have lots of training data
EMNLP 2025
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
ICML 2025
One Size Fits None: Rethinking Fairness in Medical AI
ACL 2025
InversionView: A General-Purpose Method for Reading Information from Neural Activations
NeurIPS 2024
Lossy Context Surprisal Predicts Task-Dependent Patterns in Relative Clause Processing
CoNLL 2024
More frequent verbs are associated with more diverse valency frames: Efficient principles at the lexicon-grammar interface
ACL 2024
Separations in the Representational Capabilities of Transformers and Recurrent Architectures
NeurIPS 2024
The Expressive Capacity of State Space Models: A Formal Language Perspective
NeurIPS 2024
Why are Sensitive Functions Hard for Transformers?
ACL 2024
An Information-Theoretic Characterization of Morphological Fusion
EMNLP 2021
RNNs can generate bounded hierarchical languages with optimal memory
EMNLP 2020
Modeling Human Reading with Neural Attention
EMNLP 2016
CoMeT: Integrating different levels of linguistic modeling for meaning assessment
SemEval 2013