User profiles for Jean Mercat
![]() | Jean MercatResearch scientist at Toyota Research Institute Verified email at tri.global Cited by 432 |
Multi-head attention for multi-modal joint vehicle motion forecasting
This paper presents a novel vehicle motion forecasting method based on multi-head
attention. It produces joint forecasts for all vehicles on a road scene as sequences of multi-modal …
attention. It produces joint forecasts for all vehicles on a road scene as sequences of multi-modal …
Kinematic single vehicle trajectory prediction baselines and applications with the NGSIM dataset
In the recent vehicle trajectory prediction literature, the most common baselines are briefly
introduced without the necessary information to reproduce it. In this article we produce …
introduced without the necessary information to reproduce it. In this article we produce …
Social attention for autonomous decision-making in dense traffic
We study the design of learning architectures for behavioural planning in a dense traffic setting.
Such architectures should deal with a varying number of nearby vehicles, be invariant to …
Such architectures should deal with a varying number of nearby vehicles, be invariant to …
Control-aware prediction objectives for autonomous driving
Autonomous vehicle software is typically structured as a modular pipeline of individual
components (eg, perception, prediction, and planning) to help separate concerns into …
components (eg, perception, prediction, and planning) to help separate concerns into …
Language models scale reliably with over-training and on downstream tasks
Scaling laws are useful guides for developing language models, but there are still gaps between
current scaling studies and how language models are ultimately trained and evaluated. …
current scaling studies and how language models are ultimately trained and evaluated. …
Droid: A large-scale in-the-wild robot manipulation dataset
The creation of large, diverse, high-quality robot manipulation datasets is an important
stepping stone on the path toward more capable and robust robotic manipulation policies. …
stepping stone on the path toward more capable and robust robotic manipulation policies. …
Rap: Risk-aware prediction for robust planning
Robust planning in interactive scenarios requires predicting the uncertain future to make risk-aware
decisions. Unfortunately, due to long-tail safety-critical events, the risk is often under-…
decisions. Unfortunately, due to long-tail safety-critical events, the risk is often under-…
Residual q-learning: Offline and online policy customization without value
Imitation Learning (IL) is a widely used framework for learning imitative behavior from
demonstrations. It is especially appealing for solving complex real-world tasks where handcrafting …
demonstrations. It is especially appealing for solving complex real-world tasks where handcrafting …
Linearizing Large Language Models
Linear transformers have emerged as a subquadratic-time alternative to softmax attention
and have garnered significant interest due to their fixed-size recurrent state that lowers …
and have garnered significant interest due to their fixed-size recurrent state that lowers …
Dynamics-aware comparison of learned reward functions
The ability to learn reward functions plays an important role in enabling the deployment of
intelligent agents in the real world. However, comparing reward functions, for example as a …
intelligent agents in the real world. However, comparing reward functions, for example as a …