近期论文11
- Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners第 2 位,共 3 位作者ICLR 2026 · 2 次引用
- Explaining Object Detectors via Collective Contribution of Pixels第 2 位,共 3 位作者CVPR 2026
- Zero-Shot Textual Explanations via Translating Decision-Critical Features第 2 位,共 3 位作者CVPR Findings 2026
- Computational Algebra with Attention: Transformer Oracles for Border Basis Algorithms第 1 位,共 5 位作者NeurIPS 2025 · 8 次引用
- Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning第 2 位,共 3 位作者CVPR 2025
- Learning to compute Gröbner bases第 1 位,共 5 位作者NeurIPS 2024 · 9 次引用
- Theoretical Understanding of Learning from Adversarial Perturbations第 2 位,共 3 位作者ICLR 2024 · 4 次引用
- Wide Two-Layer Networks can Learn from Adversarial Perturbations第 2 位,共 3 位作者NeurIPS 2024 · 2 次引用
- Identifying Important Group of Pixels using Interactions第 3 位,共 3 位作者CVPR 2024
- Adversarial Training from Mean Field Perspective第 2 位,共 3 位作者NeurIPS 2023 · 2 次引用
- Adversarial Bone Length Attack on Action Recognition第 2 位,共 3 位作者AAAI 2022 · 18 次引用
