Search papers, labs, and topics across Lattice.
6
0
8
MLLMs can significantly reduce hallucinations and improve reasoning by shifting focus from linguistic shortcuts to causal visual grounding through VIGIL.
Flash-WAM achieves real-time inference for world-action models by reducing latency from 8.1 seconds to 348 milliseconds without sacrificing performance.
Teaching VLMs to "look back" and "look ahead" with lightweight spatial reasoning tasks unlocks surprisingly strong navigation performance.
Bridging the gap between human manipulation and robotic control, JoyAI-RA unlocks enhanced cross-embodiment behavior learning through multi-source pretraining.
Image-goal navigation gets a boost from hierarchical reasoning, using vision-language models for high-level planning and online RL for low-level execution, significantly reducing wandering and improving success in complex environments.
Unlock accurate predictions of complex nonlinear system dynamics from just one shot, slashing data needs for MEMS characterization.
