Search papers, labs, and topics across Lattice.
3
0
7
4
A small LLM can be trained to detect hallucinations as effectively as larger models through an innovative self-play framework that evolves its own training data.
Forget object-centric prompts: Function2Scene designs 3D indoor scenes directly from natural language descriptions of *how* the space will be used, not just *what* furniture to put there.
Current VLM spatial reasoning benchmarks are misleading, as they often penalize models for "incorrect" answers that are actually correct given the limited visual information the models receive.
