Search papers, labs, and topics across Lattice.
Address:
5
0
7
Eternal geometric flows now bridge any Clifford hypersurface to equatorial spheres in $S^{n+1}$, resolving a long-standing problem in minimal surface theory.
Visual token pruning often degrades robotic control because it ignores language conditioning; steering token cache reuse via text-vision entropy differentials cuts VLA compute by 2.45x while boosting task success by up to 14.5%.
PhysCaP enables robots to actively infer hidden physical properties, achieving superior manipulation efficiency without additional sensors.
3D-PLOT-LLM achieves part-level reasoning in 3D MLLMs without the hefty parameter costs of traditional methods, outperforming competitors on key benchmarks.
Multi-iteration experience learning in LLMs can lead to capability collapse, but strategic adjustments in experience granularity and injection patterns can stabilize and enhance performance.