Preprint
Aug 2026
ChronoVision: Temporal Reasoning via Latent State Reconstruction
This work proposes ChronoVision, a multimodal framework designed to align visual logic with latent imagery, and introduces Vbvr-VQA, a novel dataset that evaluates temporal tracking by reformulating video reasoning into a strict image-ordering task.
Yifan Shen, Jian Xu, Boyi Li et al.
· 1 citation