Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
0
StateTrace reveals that enhancing memory structures in VLMs can drastically improve reasoning about invisible objects, achieving a remarkable 24.6-point performance increase on hidden-state tasks.
Reward hacking can be effectively mitigated by a novel agentic reward framework that enhances exploration in RL, leading to substantial accuracy gains in embodied world models.
Kairos achieves top-tier performance in Physical AI while ensuring efficient state management over extended time horizons, setting a new standard for operational world models.
