1 code implementation • 13 Mar 2024 • Samir Yitzhak Gadre, Georgios Smyrnis, Vaishaal Shankar, Suchin Gururangan, Mitchell Wortsman, Rulin Shao, Jean Mercat, Alex Fang, Jeffrey Li, Sedrick Keh, Rui Xin, Marianna Nezhurina, Igor Vasiljevic, Jenia Jitsev, Alexandros G. Dimakis, Gabriel Ilharco, Shuran Song, Thomas Kollar, Yair Carmon, Achal Dave, Reinhard Heckel, Niklas Muennighoff, Ludwig Schmidt
We fit scaling laws that extrapolate in both the number of model parameters and the ratio of training tokens to parameters.
no code implementations • NeurIPS 2023 • Chenran Li, Chen Tang, Haruki Nishimura, Jean Mercat, Masayoshi Tomizuka, Wei Zhan
Specifically, we formulate the customization problem as a Markov Decision Process (MDP) with a reward function that combines 1) the inherent reward of the demonstration; and 2) the add-on reward specified by the downstream task.
1 code implementation • 4 Oct 2022 • Haruki Nishimura, Jean Mercat, Blake Wulfe, Rowan Mcallister, Adrien Gaidon
Robust planning in interactive scenarios requires predicting the uncertain future to make risk-aware decisions.
no code implementations • 28 Apr 2022 • Rowan Mcallister, Blake Wulfe, Jean Mercat, Logan Ellis, Sergey Levine, Adrien Gaidon
Autonomous vehicle software is typically structured as a modular pipeline of individual components (e. g., perception, prediction, and planning) to help separate concerns into interpretable sub-tasks.
no code implementations • ICLR 2022 • Blake Wulfe, Ashwin Balakrishna, Logan Ellis, Jean Mercat, Rowan Mcallister, Adrien Gaidon
The ability to learn reward functions plays an important role in enabling the deployment of intelligent agents in the real world.
no code implementations • 28 Oct 2020 • Jean Mercat
Following up on the linear transformer part of the article from Katharopoulos et al., that takes this idea from Shen et al., the trick that produces a linear complexity for the attention mechanism is re-used and extended to a second-order approximation of the softmax normalization.
no code implementations • 27 Nov 2019 • Edouard Leurent, Jean Mercat
We study the design of learning architectures for behavioural planning in a dense traffic setting.
no code implementations • 8 Oct 2019 • Jean Mercat, Thomas Gilles, Nicole El Zoghby, Guillaume Sandou, Dominique Beauvois, Guillermo Pita Gil
This paper presents a novel vehicle motion forecasting method based on multi-head attention.
2 code implementations • 29 Aug 2019 • Jean Mercat, Nicole El Zoghby, Guillaume Sandou, Dominique Beauvois, Guillermo Pita Gil
This article is meant to be used along with the published code to establish baselines for further work.