Search papers, labs, and topics across Lattice.
University of California , San Diego
6
0
6
5
Failures in robotic manipulation are transformed into learnable, reusable capabilities, dramatically boosting task success and minimizing human intervention.
A single generalist model outperforms specialized systems, achieving over 35% improvement in real-world robotic task success.
SR-REAL's dual-path reasoning framework allows spatial VLMs to excel in both linguistic deduction and 3D geometric inference, significantly enhancing performance on complex spatial reasoning tasks.
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.
