INTACT Probing Suite Collection A probing suite for the generalization boundaries of VLA models. This collection holds the model checkpoints and more. https://ai4ce.github.io/INT-ACT • 4 items • Updated Jun 15 • 1
From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models Paper • 2506.09930 • Published Jun 11 • 8
CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos Paper • 2411.17820 • Published Nov 26, 2024 • 2
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion Paper • 2302.12251 • Published Feb 23, 2023
NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences Paper • 2110.09004 • Published Oct 18, 2021
Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset Paper • 2406.09383 • Published Jun 13, 2024