Track synthesis, materials and catalysis as it is published.
Search papers, labs, and topics across Lattice.
4
0
9
13
Large-scale rewards can unfairly suppress learning signals from smaller rewards in multi-objective RL; CorrGRPO fixes this by normalizing reward covariances.
A groundbreaking pipeline has generated over 8,000 hours of action-conditioned video, overcoming the limitations of real-world data collection.
Bridging the action-sufficiency gap in robotic manipulation, GIFT achieves up to 12.6 points improvement over existing models by integrating structured intermediate features.
A dedicated guard agent, trained via reasoning-intensive methods, can effectively neutralize prompt injection attacks in web-navigating agents without sacrificing performance.