Search papers, labs, and topics across Lattice.
4
0
8
Achieve 34x compression of 3D Gaussian Splatting models *without* sacrificing rendering quality, and sometimes even improving it.
Discrete diffusion policies, typically used for image generation, turn out to be surprisingly effective and efficient asynchronous executors for robots acting in dynamic environments, outperforming traditional continuous control methods.
Forget monolithic updates: HiEdit's hierarchical RL finds that editing specific knowledge in LLMs is best done by surgically perturbing only the relevant layers, boosting performance and cutting compute by half.
LLMs can be actively trained to master specific knowledge domains with 50% less data and computation by focusing on what they *don't* know, not what they already do.
