← Search

Alexandre Fréchette

2 accepted papers

2025

Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models

NeurIPS 2025poster

We propose a new algorithm for fine-tuning large language models using reinforcement learning. Tapered Off-Policy REINFORCE (TOPR) uses an asymmetric, tapered variant of importance sampling to speed up learning while maintaining stable learning dynamics, even without the use of KL regularization. TO…

Cited by 0SourceScholar
2023

Perception Test: A Diagnostic Benchmark for Multimodal Video Models

NeurIPS 2023poster

We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e.g. Flamingo, BEiT-3, or GPT-4). Compared to existing benchmarks that focus on computational tasks (e.g. classification, detection or tracking), th…