Search papers, labs, and topics across Lattice.
5
0
7
4
Coverage-driven token pruning can significantly enhance the efficiency of 3D VLMs without sacrificing reasoning capabilities.
Achieving 10x faster decoding and 10x higher compactness, MSVS-VAE redefines the standards for high-fidelity 3D reconstruction.
VLM agents exhibit vastly different skill evolution patterns, revealing that initial performance scores can be misleading without considering improvement dynamics.
Standard RL rollouts can effectively provide world modeling supervision, leading to significant performance gains in language agents.
Autoregressive Transformers can now generate modular 3D assets from text, opening new avenues for UGC and professional 3D content creation.
