Profiles2022-2026
Hiroshi Kera
Chiba University
11Papers
1Last author
11Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers11
- Adversarially Pretrained Transformers May Be Universally Robust In-Context LearnersAuthor 2 of 3ICLR 2026 · 2 citations
- Explaining Object Detectors via Collective Contribution of PixelsAuthor 2 of 3CVPR 2026
- Zero-Shot Textual Explanations via Translating Decision-Critical FeaturesAuthor 2 of 3CVPR Findings 2026
- Computational Algebra with Attention: Transformer Oracles for Border Basis AlgorithmsAuthor 1 of 5NeurIPS 2025 · 8 citations
- Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental LearningAuthor 2 of 3CVPR 2025
- Learning to compute Gröbner basesAuthor 1 of 5NeurIPS 2024 · 9 citations
- Theoretical Understanding of Learning from Adversarial PerturbationsAuthor 2 of 3ICLR 2024 · 4 citations
- Wide Two-Layer Networks can Learn from Adversarial PerturbationsAuthor 2 of 3NeurIPS 2024 · 2 citations
- Identifying Important Group of Pixels using InteractionsAuthor 3 of 3CVPR 2024
- Adversarial Training from Mean Field PerspectiveAuthor 2 of 3NeurIPS 2023 · 2 citations
- Adversarial Bone Length Attack on Action RecognitionAuthor 2 of 3AAAI 2022 · 18 citations
