3 papers
cs.LG2026
Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem
Amit Peleg, Naman Deep Singh, Naama Pearl +2
Machine unlearning in LLMs is the targeted removal of specific knowledge while preserving all other capabilities, critical for privacy and safety. Yet existing benchmarks measure i…
cs.LG2025
Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
Amit Peleg, Naman Deep Singh, Matthias Hein
Vision-language models like CLIP have demonstrated remarkable zero-shot capabilities in classification and retrieval. However, these models often struggle with compositional reason…
cs.LG2025
Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
Amit Peleg, Matthias Hein
Neural networks typically generalize well when fitting the data perfectly, even though they are heavily overparameterized. Many factors have been pointed out as the reason for this…