Search papers, labs, and topics across Lattice.
3
0
5
SV-WAM achieves high-performance autonomous driving planning without the computational burden of generating future videos during inference.
Hard-assigned predictors in MoP-JEPA enable accurate planning in stochastic environments, achieving up to 42 times better performance than traditional methods.
Forget blindly aligning layers in audio Flow Matching: AG-REPA reveals that targeting the *causally dominant* layers driving the velocity field, not just representationally rich ones, unlocks superior generation.
