Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
36
This work proposes OPTED (on-policy fine-tuning for end-to-end driving) which decouples reinforcement learning from the post-training of the end-to-end policy: a privileged teacher is trained using RL on vectorized inputs (HD-map and bounding boxes) which provides supervision to the pre-trained student during closed-loop post-training.
Generating missing multi-view data from diverse driving videos boosts closed-loop driving robustness in edge cases by over 30%.
Cosmos 3 sets a new benchmark for omnimodal models, outperforming existing state-of-the-art in both Text-to-Image and Image-to-Video tasks.
By structuring diffusion-based driving models around a "scaffold" of frozen structural tokens, Fast-dDrive achieves a 12x speedup over autoregressive baselines while improving trajectory accuracy.
