Search papers, labs, and topics across Lattice.
Affiliation:
3
0
7
Current leading models fail to achieve over 60% success in constructing 3D worlds from user prompts, but VibeWorlder models leverage RL training to outperform them significantly.
EditVerse3D achieves high-fidelity 3D object edits using only coarse region specifications, outperforming traditional methods that require precise inputs.
Stop comparing apples to oranges: HRBench offers the first unified benchmark to fairly evaluate thinking-mode switch strategies in hybrid-reasoning LLMs.
