Search papers, labs, and topics across Lattice.
5
0
10
1
ActionSplice is introduced, an inference framework that formulates this problem as Counterfactual State Transport (CST), a lightweight corrector that transports the interrupted backbone-native representation toward the matched state induced by the revised action at the same solver step.
DKL boosts RAG accuracy by over 25 points in retrieval failure cases without the need for costly instruction fine-tuning.
SparsePR cuts attention-reconstruction error while speeding up video generation by over 2.5x without sacrificing quality.
Closing the sim-to-real gap for LiDAR in adverse weather is now possible: physics-informed GANs generate synthetic data that allows models to perform as well as if trained on real-world data.
Decoupling reasoning from action generation in autonomous driving VLMs lets you beat larger end-to-end models while slashing training costs.
