Hahn, Michael
- RNNs can generate bounded hierarchical languages with optimal memory
2020/10/15 by Hewitt, John, Hahn, Michael, Ganguli, Surya +2 · 6 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Why are Sensitive Functions Hard for Transformers?
2024/02/15 by Michael Hahn, Mark Rofin, Hahn, Michael +1 · 9 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications
- A Formal Framework for Understanding Length Generalization in Transformers
2024/10/03 by Huang, Xinting, Yang, Andy, Bhattamishra, Satwik +5 · 10 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- A Theory of Emergent In-Context Learning as Implicit Structure Induction
2023/03/14 by Michael G. Hahn, Navin Goyal, Hahn, Michael +1 · 5 citations
Computer Science · Social Sciences · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Language and cultural evolution #Machine Learning (cs.LG) #Speech and dialogue systems #Topic Modeling
- The Expressive Capacity of State Space Models: A Formal Language Perspective
2024/05/27 by Yash Sarrof, Sarrof, Yash, Yana Veitsman +3 · 6 citations
Computer Science · Decision Sciences · #Complex Systems and Decision Making #Computation and Language (cs.CL) #FOS: Computer and information sciences #Formal Languages and Automata Theory (cs.FL) #Machine Learning (cs.LG) #Multi-Agent Systems and Negotiation
- Sensitivity as a Complexity Measure for Sequence Classification Tasks
2021/04/21 by Hahn, Michael, Jurafsky, Dan, Futrell, Richard · 2 citations
#Computation and Language (cs.CL) #Computational Complexity (cs.CC) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
2025/02/04 by Alireza Amiri, Xinting Huang, Amiri, Alireza +5 · 7 citations
Neuroscience · Engineering · Computer Science · #EEG and Brain-Computer Interfaces #Advanced Memory and Neural Computing #Visual Attention and Saliency Detection
- Separations in the Representational Capabilities of Transformers and Recurrent Architectures
2024/06/13 by Satwik Bhattamishra, Michael G. Hahn, Bhattamishra, Satwik +5 · 4 citations
Engineering · #Modular Robots and Swarm Intelligence #Architecture and Computational Design
- Linguistic Structure from a Bottleneck on Sequential Information Processing
2024/05/20 by Richard Futrell, Futrell, Richard, Michael Hahn +1 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Theory (cs.IT) #Natural Language Processing Techniques
- A Cross-Linguistic Pressure for Uniform Information Density in Word Order
2023/06/06 by Clark, Thomas Hikaru, Meister, Clara, Pimentel, Tiago +4 · 2 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences
- Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
2025/05/27 by Jobanputra, Mayank, Veitsman, Yana, Sarrof, Yash +4 · 3 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- InversionView: A General-Purpose Method for Reading Information from Neural Activations
2024/05/27 by Huang, Xinting, Panwar, Madhur, Goyal, Navin +1 · 2 citations
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B
2025/03/31 by Bakalova, Aleksandra, Veitsman, Yana, Huang, Xinting +1 · 3 citations
#Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Tug-of-war between idioms' figurative and literal interpretations in LLMs
2025/06/02 by Soyoung Oh, Oh, Soyoung, Xinting Huang +7 · 1 voice · 1 citation
#cs.CL #cs.AI
- Velocity and Density Fluctuations in the Quiet Sun Corona
2025/03/19 by Hahn, Michael, Fu, Xiangrong, Hofmeister, Stefan J. +3 · 1 citation
#FOS: Physical sciences #Solar and Stellar Astrophysics (astro-ph.SR)