Search papers, labs, and topics across Lattice.
4
0
5
5
CoDeR achieves up to a 23.53 point reduction in V@2 scores, revolutionizing how we handle constraint-sensitive queries in information retrieval.
A unified framework reveals how different 3D data representations and learning paradigms interact, paving the way for more efficient and effective applications in 3D vision.
Stop bloating your agent's context window: a dependency-aware skill graph slashes token costs by 37% and boosts reward by 43% compared to naive skill loading.
VLMs can now self-evolve from *zero* data, thanks to a multi-agent RL framework that synthesizes its own visual concepts and reasoning tasks.
