Tag
TrackEverything introduces a 3D point tracker that overcomes the trade-off between sparse long-horizon and dense short-horizon tracking by representing videos as persistent 3D scene tracks with voxelization-based de-duplication, achieving state-of-the-art performance on TAPVid-3D and handling videos over 1000 frames within 40GB GPU memory.
A writeup of a multi-stage LLM pipeline that fetches newsletter articles, summarizes, de-duplicates, scores importance and urgency, and publishes a digest, with robust prompt-injection defenses and self-validation.