안녕하세요! 이곳은 제가 읽은 논문들을 리뷰하고 정리하는 공간입니다.
각 논문에 대한 핵심 아이디어와 주요 기여점을 간결하게 요약하여 공유합니다.
| 논문 제목 | 출판년도 | 학회/저널 | 작성일 |
|---|---|---|---|
| InstructPix2Pix: Learning to Follow Image Editing Instructions | 2023 | CVPR 2023 | 2025-07-02 |
| Denoising Diffusion Bridge Models | 2023 | ICLR 2024 | 2025-07-01 |
| Interpreting the Second-Order Effects of Neurons in CLIP | 2025 | ICLR 2025 | 2025-06-27 |
| Scaling and evaluating sparse autoencoders | 2024 | ICLR 2025 | 2025-06-19 |
| Label-Free Concept Bottleneck Models | 2023 | ICLR 2023 | 2025-06-18 |
| Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery | 2024 | ECCV 2024 | 2025-06-17 |
| Steering CLIP's vision transformer with sparse autoencoders | 2025 | CVPR 2025 Workshop | 2025-06-16 |
| Sparse Autoencoders for Scientifically Rigorous Interpretation of Vision Models | 2025 | Arxiv | 2025-06-13 |
| Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models | 2024 | ICLR 2025 | 2025-06-13 |
| Causality Inspired Representation Learning for Domain Generalization | 2022 | CVPR 2022 | 2025-06-11 |