Search papers, labs, and topics across Lattice.
University of North Carolina at
3
0
5
HiViG outperforms existing critics by integrating historical context and visual grounding, achieving up to 9% higher success rates in complex GUI tasks.
Current video generation models are far from ready to teach, stumbling on basic knowledge, skills, and attitudes needed for effective education.
Even the best search-augmented agents, like Gemini Deep Research, are easily distracted by noisy web content, leading to surprisingly poor performance (40% accuracy) on a new multimodal reasoning benchmark.
