Two papers accepted at ICML 2025.

카테고리 없음

KDST 2025. 5. 18. 12:24

7월에 캐나다 밴쿠버에서 열리는 ICML 2025에 다음 2편의 논문을 발표하게 되었습니다.

"When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class"

"ELITE: Enhanced Language-Image Toxicity Evaluation for Safety"

KDST

KDST는 딥러닝을 포함한 데이터와 지능에 관련된 여러 주제에 대해서 연구하는 팀입니다.

domain shift, Sharpness-Aware Minimization, robustness, 강화학습, representation leanring, autoencoder, anomaly detection, Reinforcement Learning, Singulairty, domain generalization, bearing fault detection, Diffusion Model, point-based image editing #dragdiffusion #dragondiffusion, gan, bearing fault diagnosis, pruning, ICCV, cnn, Knowledge Distillation, DQN,

KDST