Author

Xiaomeng Li

h-index 8 View on Semantic Scholar

We have 1 of 14 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Beyond Frame Selection: Generative Latent Evidence Aggregation for Long-Video Understanding

GenEvA uses a query-conditioned evidence distribution to focus aggregation on relevant frames, forming compact cross-frame latent evidence from their frame-specific information from their frame-specific information.

Bowen Liu, Shu-Ning Wang, Xinpeng Ding et al. · arXiv.org · 2 citations