Teruaki Hayashi

2 accepted papers

2026

SF-Mamba: Rethinking State Space Model for Vision

Masakazu Yoshimura, Teruaki Hayashi, Yuki Hoshino, Wei-Yao Wang, Takeshi Ohashi

ICML 2026poster

The realm of Mamba for vision has been advanced in recent years to strike for the alternatives of Vision Transformers (ViTs) that suffer from the quadratic complexity. While the recurrent scanning mechanism of Mamba offers computational efficiency, it inherently limits non-causal interactions betwee…

Cited by 0 Source ↗Scholar ↗

2025

MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mamba

Masakazu Yoshimura, Teruaki Hayashi, Yota Maeda

ICLR 2025poster

An ecosystem of Transformer-based models has been established by building large models with extensive data. Parameter-efficient fine-tuning (PEFT) is a crucial technology for deploying these models to downstream tasks with minimal cost while achieving effective performance. Recently, Mamba, a State…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗