254 citations · 1.3k across the 50 of their papers we have counts for
7 papers · 1 filter
From Memorization to Parameter Interference: How Overtraining Experts Harms Model Merging
Stefan Horoi, Guy Wolf, Eugene Belilovsky +1
Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets. This has led to a proliferation of ex…
Continual Learning in Vision-Language Models via Aligned Model Merging
Ghada Sokar, Gintare Karolina Dziugaite, Anurag Arnab +3
Continual learning is conventionally tackled through sequential fine-tuning, a process that, while enabling adaptation, inherently favors plasticity over the stability needed to re…
Leveraging Per-Instance Privacy for Machine Unlearning
Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik +5
We present a principled, per-instance approach to quantifying the difficulty of unlearning via fine-tuning. We begin by sharpening an analysis of noisy gradient descent for unlearn…
From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization
Shoaib Ahmed Siddiqui, Adrian Weller, David Krueger +3
Recent unlearning methods for LLMs are vulnerable to relearning attacks: knowledge believed-to-be-unlearned re-emerges by fine-tuning on a small set of (even seemingly-unrelated) e…
On Traceability in Stochastic Convex Optimization
Sasha Voitovych, Mahdi Haghifam, Idan Attias +3
In this paper, we investigate the necessity of traceability for accurate learning in stochastic convex optimization (SCO) under geometries. Informally, we say a learning a…
Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives
Anat Kleiman, Gintare Karolina Dziugaite, Jonathan Frankle +2
Have we made mitigating catastrophic forgetting more complicated than it needs to be? Continual adaptation often degrades performance on earlier tasks, motivating rehearsal buffers…