Search papers, labs, and topics across Lattice.
4
0
6
5
Current action-conditioned world models fail to reliably follow diverse off-expert actions, risking the effectiveness of policy learning in real-world applications.
Achieving high perceptual quality in video compression at bitrates below 0.005 bpp could redefine the limits of efficient video transmission.
Achieving a 76.2% relative gain in multi-step reasoning success rates, HDR redefines the capabilities of video models in real-time applications.
Forget static imitation learning: LaST-R1 unlocks near-perfect robotic manipulation (99.8% success) by adaptively reasoning about physical dynamics *before* acting, then refining with RL.
