7 papers
CIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents
Maxime Heuillet, Sharadind Peddiraju
Enterprise data science and analytics spans closed-ended information extraction with verifiable answers and open-ended insight discovery. Agents are evaluated on one or the other,…
Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data
Baptiste Bonin, Maxime Heuillet, Audrey Durand
Slate recommender systems (RecSys) present users with ordered sets of interacting items (e.g., playlists). We investigate whether large language models (LLMs) can articulate pairwi…
Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling
Jonas Ngnawé, Maxime Heuillet, Sabyasachi Sahoo +5
Fine-tuning pretrained models is a standard and effective workflow in modern machine learning. However, robust fine-tuning (RFT), which aims to simultaneously achieve adaptation to…
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…
Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts
Maxime Heuillet, Yufei Cui, Boxing Chen +2
Advanced reasoning in LLMs on challenging domains like mathematical reasoning can be tackled using verifiable rewards based reinforced fine-tuning (ReFT). In standard ReFT framewor…
Neural Active Learning Meets the Partial Monitoring Framework
Maxime Heuillet, Ola Ahmad, Audrey Durand
We focus on the online-based active learning (OAL) setting where an agent operates over a stream of observations and trades-off between the costly acquisition of information (label…
Randomized Confidence Bounds for Stochastic Partial Monitoring
Maxime Heuillet, Ola Ahmad, Audrey Durand
The partial monitoring (PM) framework provides a theoretical formulation of sequential learning problems with incomplete feedback. On each round, a learning agent plays an action w…