Loading the SOTA2 catalog…
SOTA2 Research · papers
Find papers, implementations, and the benchmark evidence behind state-of-the-art AI systems.
| Improving robustness to corruptions with multiplicative weight perturbations |
|---|
| Trung Trinh, Markus Heinonen, Luigi Acerbi |
| 2024 |
| arxiv 2406.16540 |
| Utilization of Neighbor Information for Image Classification with Different Levels of Supervision | Gihan Jayatilaka, Abhinav Shrivastava, Matthew Gwilliam | 2025 | arxiv 2503.14500 |
|---|
| Cross-attention for State-based model RWKV-7 | Liu Xiao, Li Zhiyuan, Lin Yueyu | 2025 | arxiv 2504.14260 |
|---|
| Continual Learning: Less Forgetting, More OOD Generalization via Adaptive Contrastive Replay | Hossein Rezaei, Mohammad Sabokrou | 2024 | arxiv 2410.07110 |
|---|
| Keep It Light! Simplifying Image Clustering Via Text-Free Adapters | Yicen Li, Haitz Sáez de Ocáriz Borde, Anastasis Kratsios | 2025 | arxiv 2502.04226 |
|---|
| Exploring Deep-to-Shallow Transformable Neural Networks for Intelligent Embedded Systems | Xiangzhong Luo, Weichen Liu | 2025 | arxiv 2512.19731 |
|---|
| Bridging Explainability and Embeddings: BEE Aware of Spuriousness | Cristian Daniel Păduraru, Antonio Bărbălau, Radu Filipescu | 2024 | arxiv 2410.18970 |
|---|
| Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP | Lorenz Hufe, Constantin Venhoff, Erblina Purelku | 2025 | arxiv 2508.20570 |
|---|
| TriLite: Efficient Weakly Supervised Object Localization with Universal Visual Features and Tri-Region Disentanglement | Arian Sabaghi, José Oramas | 2026 | arxiv 2602.23120 |
|---|
| Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization | Ben Isselmann, Dilara Göksu, Heinz Neumann | 2026 | arxiv 2604.10970 |
|---|