4 papers
Déjà Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates
Haofan Cao, Zhichao You, Yunkai Yang +3
Tracking links observations of the same object through visual change, yet cannot by itself determine when the object is empty or filled, intact or cut. We formulate identity-condit…
Versioned Late Materialization for Ultra-Long Sequence Training in Recommendation Systems at Scale
Liang Guo, Ge Song, Litao Deng +9
Modern Deep Learning Recommendation Models (DLRMs) follow scaling laws with sequence length, driving the frontier toward ultra-long User Interaction History (UIH). However, the ind…
PaCo-VLA: Passivity-Shielded Compliance Prior for Contact-Rich Vision-Language-Action Manipulation
Haofan Cao, Zhaoyang Li, Zhichao You +2
Contact-rich manipulation demands both high-level semantic reasoning and the safe regulation of high-frequency contact dynamics. While Vision-Language-Action (VLA) models provide u…
PAS3R: Pose-Adaptive Streaming 3D Reconstruction for Long Video Sequences
Lanbo Xu, Liang Guo, Caigui Jiang +1
Online monocular 3D reconstruction enables dense scene recovery from streaming video but remains fundamentally limited by the stability-adaptation dilemma: the reconstruction model…