Search papers, labs, and topics across Lattice.
3
1
5
7
LingBot-VA 2.0 achieves few-shot generalization in complex robot manipulation tasks, outperforming traditional video generative models.
LingBot-Video bridges the gap between digital creativity and physical actuation, achieving unprecedented efficiency in video pretraining for embodied intelligence.
LLM agents struggle to maintain performance in multi-day collaborative tasks, dropping significantly after just one environmental update, revealing a critical gap in adaptation to evolving real-world conditions.
