Michael Hahn
~Michael_Hahn1
7
论文总数
3.5
年均投稿
平均评分
接收情况7/7
会议分布
NeurIPS
4
ICML
1
COLM
1
ICLR
1
发表论文 (7 篇)
20254 篇
3
Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
ICML 2025Poster
4
Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B
COLM 2025Poster
4
Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities
NeurIPS 2025Poster
5
A Formal Framework for Understanding Length Generalization in Transformers
ICLR 2025Poster
20243 篇
4
Separations in the Representational Capabilities of Transformers and Recurrent Architectures
NeurIPS 2024Poster
4
The Expressive Capacity of State Space Models: A Formal Language Perspective
NeurIPS 2024Poster
4
InversionView: A General-Purpose Method for Reading Information from Neural Activations
NeurIPS 2024Poster