Search papers, labs, and topics across Lattice.
Tongji University
7
0
7
Ditch the clunky text-based reasoning: LaST-VLA achieves new benchmarks in autonomous driving by thinking in a physically-grounded, latent spatio-temporal space.
Mimicking human intuition, this autonomous driving system anticipates hidden pedestrian behavior by actively maintaining and updating beliefs about their intentions, leading to safer and more explainable navigation.
Diffusion models can achieve a 10x performance boost in real-world autonomous driving when optimized for trajectory representation, loss space, and augmented with reinforcement learning.
Keypoint detectors can now be trained with RL to directly optimize for long-term trackability across image sequences, leading to significant improvements in downstream 3D vision tasks.
Forget quadratic complexity: UFO reconstructs 16-second driving scenes in half a second by unifying feed-forward and optimization-based methods.
Ditch the discrete anchors: MeanFuser achieves state-of-the-art autonomous driving trajectory generation by using a continuous Gaussian Mixture Noise representation and a mean-flow formulation for faster, more robust planning.
