🏢 Chinese Academy of Sciences

AcFormer, a novel vision-language connector for MLLMs, leverages ‘visual anchors’ to reduce computation cost by ~66% while improving accuracy.

PamaCF, a novel personalized adversarial collaborative filtering technique, significantly improves recommendation robustness and accuracy against poisoning attacks by dynamically adjusting perturbatio…

Boosting 3D point cloud recognition robustness, Frequency Adversarial Training (FAT) leverages frequency-domain adversarial examples to improve model resilience against corruptions, achieving state-of…

Hallo3D: a tuning-free method resolving 3D generation hallucinations via multi-modal inconsistency detection and mitigation for consistent 3D content.

Unlocking deep learning’s generalization mystery, this research pioneers a theoretical understanding of memorization neural network generalizability, revealing critical network structural requirements…

MolPeg, a novel molecular data pruning framework, enhances model generalization in transfer learning by using a source-free approach and consistently outperforming other methods, even surpassing full-…