Search papers, labs, and topics across Lattice.
3
0
5
2
Qantara achieves a remarkable 91.2 SR on the LeWM control suite, redefining the capabilities of JEPA world models to operate across multiple inference paradigms without retraining.
Correlation-structured supervision from video-derived ordinal signals can replace traditional reward mechanisms, achieving robust policy learning across diverse tasks.
Ditch the decoder: Directly predicting future latent embeddings with a temporal transformer yields state-of-the-art MBRL performance, especially in complex, partially observable environments.
