2 papers
cs.CL2026
MIPIC: Matryoshka Representation Learning via Self-Distilled Intra-Relational and Progressive Information Chaining
Phung Gia Huy, Hai An Vu, Minh-Phuc Truong +4
Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Representation Learning (MRL) of…
cs.LG2025
WSS-CL: Weight Saliency Soft-Guided Contrastive Learning for Efficient Machine Unlearning Image Classification
Thang Duc Tran, Thai Hoang Le
Machine unlearning, the efficient deletion of the impact of specific data in a trained model, remains a challenging problem. Current machine unlearning approaches that focus primar…