Portrait de Simon Roy

Simon Roy

Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e
Giovanni Beltrame
Co-supervisor
Jana Pavlasek
Sujets de recherche
Apprentissage multimodal
Apprentissage par renforcement
Navigation robotique autonome
Robotique
Site web
GitHub

Publications

To Select or not to Select, that is the Question: Distilling Robot Skill Prediction into a Small Ensemble
Haechan Mark Bong
Simon Roy
Euhid Aman
Giovanni Beltrame
As robot fleets become more heterogeneous, including humanoids, rovers, quadrupeds, and drones, selecting the right robot for a task becomes… (voir plus) a core systems problem. We study robot skill prediction: mapping a natural-language task description to the physical capabilities required to execute it, such as fly, wheels, legs, surface water, under water and hands. Since labelled data that maps natural-language task descriptions to robot's physical capabilities does not exist, we construct a synthetic task-to-skill dataset using LLM-assisted generation and targeted label auditing. Trained on this data, a ~133M-parameter ensemble of two fine-tuned sentence encoders (mpnet + MiniLM) reaches 83.5% task-to-skill matching on a stratified 200 task dataset, outperforming Kimi K2 (1T MoE) at 72.0%, GPT-OSS-120B at 71.5%, and Llama-4-Scout-17B at 69.0% under the same zero-shot prompt. These results suggest that, for fixed robot skill taxonomies, small specialized models trained on synthetic data can outperform much larger general-purpose LLMs for fleet-level task routing.
2026-05-19
arXiv (prépublication)
doi.org
arxiv.org
Revisiting the Learning Objectives of Vision-Language Reward Models
Simon Roy
Samuel Barbeau
Giovanni Beltrame
Christian Desrosiers
Nicolas Thome
Learning generalizable reward functions is a core challenge in embodied intelligence. Recent work leverages contrastive vision language mode… (voir plus)ls (VLMs) to obtain dense, domain-agnostic rewards without human supervision. These methods adapt VLMs into reward models through increasingly complex learning objectives, yet meaningful comparison remains difficult due to differences in training data, architectures, and evaluation settings. In this work, we isolate the impact of the learning objective by evaluating recent VLM-based reward models under a unified framework with identical backbones, finetuning data, and evaluation environments. Using Meta-World tasks, we assess modeling accuracy by measuring consistency with ground truth reward and correlation with expert progress. Remarkably, we show that a simple triplet loss outperforms state-of-the-art methods, suggesting that much of the improvements in recent approaches could be attributed to differences in data and architectures.
2025-12-19
ArXiv (prépublication)
doi.org
arxiv.org