Mao Nishino

According to our database, Mao Nishino authored at least 8 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Numerical Instability and Chaos: Quantifying the Unpredictability of Large Language Models.

Chashi Mahiul Islam, Alan Villarreal, Mao Nishino, Shaeke Salman, Xiuwen Liu

CoRR, April, 2026

2025

A Benamou-Brenier Proximal Splitting Method for Constrained Unbalanced Optimal Transport.

Mao Nishino, Martin Bauer, Tom Needham, Nicolas Charon

CoRR, December, 2025

Universal and Transferable Adversarial Attack on Large Language Models Using Exponentiated Gradient Descent.

Sajib Biswas, Mao Nishino, Samuel Jacob Chacko, Xiuwen Liu

CoRR, August, 2025

Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers.

Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino, Xiuwen Liu

CoRR, February, 2025

The Z-Gromov-Wasserstein Distance.

Martin Bauer, Facundo Mémoli, Tom Needham, Mao Nishino

J. Mach. Learn. Res., 2025

NeuroShield-ViT: Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers.

Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino, Xiuwen Liu

Proceedings of the Advances in Visual Computing - 20th International Symposium, 2025

Unaligning Everything: Or Aligning Any Text to Any Image in Multimodal Models.

Shaeke Salman, Montasir Shams, Mao Nishino, Xiuwen Liu

Proceedings of the International Joint Conference on Neural Networks, 2025

Adversarial Attack on Large Language Models using Exponentiated Gradient Descent.

Sajib Biswas, Mao Nishino, Samuel Jacob Chacko, Xiuwen Liu

Proceedings of the International Joint Conference on Neural Networks, 2025