Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University
3
0
4
Multi-frame temporal reasoning is crucial for video-text understanding, and ViTexQA reveals that existing datasets fall short, leaving a significant gap in multimodal comprehension.
LightSTAR slashes retrieval latency while maintaining top-tier accuracy by cleverly bypassing heavy MLLM processing on every document page.
Forget real-world video datasets: training VLMs on just 7.7K synthetic videos with temporal primitives beats 165K real-world examples, unlocking surprisingly effective transfer learning for video reasoning.
