Search papers, labs, and topics across Lattice.
3
0
6
11
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.
Grounding boosts spatial reasoning in VLMs: explicitly linking language to 2D and 3D scene elements lets models decompose complex spatial problems and improve performance even on non-grounded tasks.
Forget brittle visual-history buffers: LoHo-Manip uses a VLM task manager with visual trace prompts to achieve robust long-horizon robotic manipulation through implicit closed-loop replanning.
