collaborators

5 papers

cs.LG2026

Overcoming Rank Collapse in Feedback Alignment

Gauthier Boeshertz, Razvan Pascanu, Claudia Clopath

Backpropagation (BP) is widely viewed as biologically implausible, in part because it requires feedback weights to be the transpose of forward weights for error propagation. Intere…

cs.LG2026

Navigating Potholes with Geometry-Aware Sharpness Minimization

Simon Dufort-Labbé, Mehrab Hamidi, Razvan Pascanu +3

Sharpness-aware minimization (SAM) encourages flat minima by perturbing parameters along directions of high loss curvature, but treats all parameter directions uniformly, ignoring…

cs.LG2026

Revisiting Adam for Streaming Reinforcement Learning

Florin Gogianu, Adrian Catalin Lutu, Razvan Pascanu

Learning from a sequence of interactions, as soon as observations are perceived and acted upon, without explicitly storing them, holds the promise of simpler, more efficient and ad…

cs.LG2026

Layerwise LQR for Geometry-Aware Optimization of Deep Networks

Simon Dufort-Labbé, Pierre-Luc Bacon, Razvan Pascanu +2

Geometry-aware optimizers such as Newton and natural gradient can improve conditioning in deep learning, but scalable variants such as K-FAC, Shampoo, and related preconditioners u…

cs.CL2026

TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models

Jinho Choo, JunSeung Lee, Jimyeong Kim +3

Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language, exhibiting a phenomenon known…