Michael Hahn
17 papers · 2013–2026 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
π Academic Marathon (12) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (7) π Cross-Pollinator (13)
πΊοΈ
Taxonomy Completionist
(32)
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π
Keyword Champion
β‘
Prolific Year
(7)
β
The Questioner
π
Century Club
(15)
ποΈ
Keyword Collector
(74)
Conferences
EMNLP (5)
ACL (4)
NIPS (3)
CONLL (1)
EACL (1)
ICLR (1)
ICML (1)
SEMEVAL (1)
Top co-authors
Keywords
formal language
(3)
relative clause
(2)
transformer architecture
(2)
recurrent neural network
(2)
hierarchical structure
(2)
syntactic processing
(2)
memory demand
(2)
lossy context surprisal
(2)
communication complexity
(1)
machine learning
(1)
language modeling
(1)
expressive power
(1)
communicative efficiency
(1)
state space model
(1)
theoretical analysis
(1)
computational complexity
(1)
attention mechanism
(1)
inductive bia
(1)
language model
(1)
memory efficiency
(1)
Papers
Systematicity between Forms and Meanings across Languages Supports Efficient Communication
ACL 2026
Tug-of-war between idiomsβ figurative and literal interpretations in LLMs
EACL 2026
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
ICML 2025
One Size Fits None: Rethinking Fairness in Medical AI
ACL 2025
Language models can learn implicit multi-hop reasoning, but only if they have lots of training data
EMNLP 2025
A Formal Framework for Understanding Length Generalization in Transformers
ICLR 2025
Lossy Context Surprisal Predicts Task-Dependent Patterns in Relative Clause Processing
EMNLP 2024
Separations in the Representational Capabilities of Transformers and Recurrent Architectures
NIPS 2024
The Expressive Capacity of State Space Models: A Formal Language Perspective
NIPS 2024
InversionView: A General-Purpose Method for Reading Information from Neural Activations
NIPS 2024
More frequent verbs are associated with more diverse valency frames: Efficient principles at the lexicon-grammar interface
ACL 2024
Why are Sensitive Functions Hard for Transformers?
ACL 2024
Lossy Context Surprisal Predicts Task-Dependent Patterns in Relative Clause Processing
CONLL 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