activity
20242026
collaborators

14 papers

cs.LG2026

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…

cs.AI2026

Position: agentic AI orchestration should be Bayes-consistent

Theodore Papamarkou, Pierre Alquier, Matthias Bauer +27

LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to co…

cs.LG2026

Detoxifying LLMs via Representation Erasure-Based Preference Optimization

Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle +3

Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and simila…

cs.LG2026

SSFL: Discovering Sparse Unified Subnetworks at Initialization for Efficient Federated Learning

Riyasat Ohib, Bishal Thapaliya, Gintare Karolina Dziugaite +3

In this work, we propose Salient Sparse Federated Learning (SSFL), a streamlined approach for sparse federated learning with efficient communication. SSFL identifies a sparse subne…

cs.LG2026

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…

cs.CV2025

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…