Search papers, labs, and topics across Lattice.
4
0
8
0
Lngram v2 achieves substantial memory efficiency gains while preserving semantic integrity, allowing for scalable transformer architectures without the typical parameter bloat.
Adaptive weighting in model merging can drastically improve multilingual reasoning performance, outperforming traditional methods across 21 languages.
PTL-Diffusion achieves superior manifold-level distributional matching by embedding phase structure directly into the diffusion process, outperforming traditional models.
Forget hand-crafted rewards: VLLR leverages LLMs and VLMs to automatically generate dense rewards, boosting robotic task success rates by up to 56% on long-horizon tasks.
