3 citations · 4 across the 6 of their papers we have counts for
8 papers
SPLICE: Sparse Physics Library Identification and Compositional Expansion
Lucas Thil, Jesse Read, Guillaume Doquet +1
Neural operator splitting composes a library of neural operators, one per physical mechanism, into zero-shot simulators of new equations. Existing approaches, however, require thes…
RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
Mohamed Dhouib, Clement Elliker, Alexi Canesse +6
Tool-using language-model agents are vulnerable to indirect prompt injection because they must act on untrusted external content. Existing training-time defenses can reduce attack…
Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World Models
Lucas Thil, Jesse Read, Rim Kaddah +1
World models used for planning learn to predict how a scene evolves, yet they rarely hold a global view of how far a task has progressed. We argue that such a view should be part o…
STEP: Learning STructured Embeddings for Progressive Time Series
Lucas Thil, Jesse Read, Rim Kaddah +1
We present a novel method for learning interpretable representations of progressive time series, that is, data capturing irreversible state transitions such as degradation or task…
A Machine Learning Framework for Turbofan Health Estimation via Inverse Problem Formulation
Milad Leyli-Abadi, Lucas Thil, Sebastien Razakarivony +2
Estimating the health state of turbofan engines is a challenging ill-posed inverse problem, hindered by sparse sensing and complex nonlinear thermodynamics. Research in this area r…
I-GLIDE: Input Groups for Latent Health Indicators in Degradation Estimation
Lucas Thil, Jesse Read, Rim Kaddah +1
Accurate remaining useful life (RUL) prediction hinges on the quality of health indicators (HIs), yet existing methods often fail to disentangle complex degradation mechanisms in m…
Uncertainty Quantification as a Complementary Latent Health Indicator for Remaining Useful Life Prediction on Turbofan Engines
Lucas Thil, Jesse Read, Rim Kaddah +1
Health Indicators (HIs) are essential for predicting system failures in predictive maintenance. While methods like RaPP (Reconstruction along Projected Pathways) improve traditiona…
Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement Learning
Lucas-Andreï Thil, Mirela Popa, Gerasimos Spanakis
Recent advancements in language models have demonstrated remarkable improvements in various natural language processing (NLP) tasks such as web navigation. Supervised learning (SL)…