Gouki Minegishi

According to our database1, Gouki Minegishi authored at least 11 papers between 2023 and 2025.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
Interpreting Multi-Attribute Confounding through Numerical Attributes in Large Language Models.
CoRR, November, 2025

RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs.
CoRR, September, 2025

Mechanism of Task-oriented Information Removal in In-context Learning.
CoRR, September, 2025

Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties.
CoRR, June, 2025

Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of Networks.
Trans. Mach. Learn. Res., 2025

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Towards Empirical Interpretation of Internal Circuits and Properties in Grokked Transformers on Modular Polynomials.
Trans. Mach. Learn. Res., 2024

Interpreting Grokked Transformers in Complex Modular Arithmetic.
CoRR, 2024

ADOPT: Modified Adam Can Converge with Any β<sub>2</sub> with the Optimal Rate.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

2023
Grokking Tickets: Lottery Tickets Accelerate Grokking.
CoRR, 2023


  Loading...