Yuta Nakashima

6

Papers

35

Total Citations

Papers (6)

Would Deep Generative Models Amplify Bias in Future Models?

SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP

Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown

Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation

Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

Putting People in LLMs’ Shoes: Generating Better Answers via Question Rewriter