Thomas Gilles

6 papers · 2022–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15)

Venues

CVPR (3) ECCV (1) ICLR (1) WACV (1)

Top co-authors

Raquel Urtasun (4) Sergio Casas (4) Ben Agro (3) Quinlan Sykora (2) Bogdan Stanciulescu (2) Dzmitry Tsishkou (2) Jiageng Mao (1) Christopher Diehl (1) Arnaud de La Fortelle (1) Arthur Moreau (1)

Research topics

Computer Vision (5) Domain-Specific (5) Artificial Intelligence (4) Analysis (4) Core AI (4) Deep Learning (3) Machine Learning (3) Architectures (2) Learning Types · Machine Learning (2) Core Methods (1) Learning Types · Deep Learning (1) Techniques (1)

Keywords

world model (2) lidar point cloud (2) autonomous driving (1) trajectory prediction (1) motion forecasting (1) visual localization (1) object tracking (1) sensor fusion (1) trajectory forecasting (1) 3d object detection (1) latent representation (1) temporal data (1) memory augmentation (1) sensor modality (1) object proposal (1) scene decomposition (1) occupancy forecasting (1) multi-agent system (1) refinement transformer (1) trajectory forecast (1)

Papers

DIO: Decomposable Implicit 4D Occupancy-Flow World Model CVPR 2025 MAD: Memory-Augmented Detection of 3D Objects CVPR 2025 DeTra: A Unified Model for Object Detection and Trajectory Forecasting ECCV 2024 UnO: Unsupervised Occupancy Fields for Perception and Forecasting CVPR 2024 ImPosing: Implicit Pose Encoding for Efficient Visual Localization WACV 2023 THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling ICLR 2022