6 papers · 1 filter
Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision-Language Models
Jonas Ngnawé, Yann Pequignot, Sabyasachi Sahoo +3
Large vision-language models (LVLMs) inherit massive activations from their text-only bases: spikes where a few fixed hidden channels receive values thousands of times above the ty…
SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
Kaustubh Mani, Yann Pequignot, Vincent Mai +1
Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains. In this paper, we approach safe exploration through the lens of epis…
A Guide to Robust Generalization: The Impact of Architecture, Pre-training, and Optimization Strategy
Maxime Heuillet, Rishika Bhagwatkar, Jonas Ngnawé +6
Deep learning models operating in the image domain are vulnerable to small input perturbations. For years, robustness to such perturbations was pursued by training models from scra…
Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
Jonas Ngnawé, Sabyasachi Sahoo, Yann Pequignot +2
Despite extensive research on adversarial training strategies to improve robustness, the decisions of even the most robust deep learning models can still be quite sensitive to impe…
A Layer Selection Approach to Test Time Adaptation
Sabyasachi Sahoo, Mostafa ElAraby, Jonas Ngnawe +3
Test Time Adaptation (TTA) addresses the problem of distribution shift by adapting a pretrained model to a new domain during inference. When faced with challenging shifts, most met…
Out-of-distribution detection for regression tasks: parameter versus predictor entropy
Yann Pequignot, Mathieu Alain, Patrick Dallaire +4
It is crucial to detect when an instance lies downright too far from the training samples for the machine learning model to be trusted, a challenge known as out-of-distribution (OO…