Search papers, labs, and topics across Lattice.
2
0
4
4
Visual transition reasoning, not just diverse data, unlocks significant multimodal LLM improvements, with just 2,000 examples boosting 22 benchmarks.
VLMs confidently hallucinate answers to spatial reasoning questions even when visual evidence is occluded or misleading, achieving near-random performance in identifying viewpoints that could resolve the ambiguity.
