Portrait of Nicolas Thome

Nicolas Thome

thome.nicolas@gmail.com
Collaborating researcher - Sorbonne Université
Supervisor
Pablo Piantanida
Research Topics
AI Safety
Computer Vision
Deep Learning
Machine Learning for Physical Sciences
Medical Machine Learning
Multimodal Learning
Robotics
Website
Google Scholar

Publications

Latent Goal Prediction from Language for Model-Based Planning
Samuel Barbeau
Simon Roy
Giovanni Beltrame
Christian Desrosiers
Nicolas Thome
Planning with world models is bottlenecked by compounding prediction errors and the difficulty of defining optimizable goals. Visual targets… (see more) provide precise local gradients but poor distant guidance, while language is flexible yet limited by noisy cross-modal alignment or dependence on large generative models unsuited for the high-sampling nature of model-based planning. To address these challenges, we introduce Latent Goal Prediction from Language (LAGO), a framework that predicts both sequences of intermediate goal states from language instructions and action-conditioned rollouts, all within the same latent space. Rather than optimizing toward a single global objective, LAGO dynamically decomposes instructions into explicitly predicted, locally tractable latent subgoals. By updating these subgoals online and using a soft minimum trajectory cost during planning, LAGO enables an agent to follow coherent latent trajectories over long horizons. Evaluation across multiple environments planning horizons shows that LAGO avoids the sharp degradation of prior methods. By achieving robust and precise long-horizon planning purely from language, LAGO bridges the precision of visual goals with the flexibility of text-guided control.
2026-05-25
arXiv (preprint)
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… (see more)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 (preprint)
doi.org
arxiv.org