Reproduce “TAM: Task-Aware Memory Distillation for Efficient Spatiotemporal Prediction” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yuqi Li, Xiaoqin Feng, Fan Xu, Weilun Feng, Chuanguang Yang, Yingli Tian, Hao Wu
TAM adds task-specific teacher history to distillation for spatiotemporal prediction, retrieving references according to the task while leaving student inference architecture unchanged. On KittiCaltech, it lowers MSE from 6.983 to 6.853 and improves SSIM and LPIPS over matched output-distillation training. TaxiBJ favors TAM over global-residual memory, though retrieval and horizon grouping change together.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.