Search papers, labs, and topics across Lattice.
5
0
8
9
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.
Steering imaginations in video world models can reveal critical failure points in robotic actions that traditional methods might overlook.
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.
Guaranteeing safety in human-robot collaboration is now possible with vision, thanks to a new framework that provides high-confidence motion predictions with conformal prediction sets.
Forget scaling laws: this humanoid robot model crushes benchmarks using 10x less data by cleverly pre-training on human videos and then fine-tuning on robot-specific movements.
