technique
masked-token modeling
techniqueactive
masked-token-modeling-82414eff·1 events·first seen 27d agoAliases: masked-token modeling
Co-occurring entities
More like this (12)
embedding modelsMasked Diffusion ModelsMask2FormerKnowledge Editing in Masked Diffusion Language ModelsEvent-Partitioned Maskingunsupervised language modelingmasked autoencodingmodel-native harnessMAML (Model-Agnostic Meta-Learning)generative language modelingUnified Multimodal Models (UMMs)Language Modeling Loss
Recent events (1)
TrajTok: Adaptive Spatial Tokenization for Trajectory Representation Learning
TrajTok is a trajectory encoder that learns transferable GPS trace representations via multi-resolution hexagonal spatial tokenization and masked-token pretraining. It uses a factorized transformer with per-modality self-attention, cross-attention fusion, and spatiotemporal rotary position embeddings (ST-RoPE) to jointly encode geometry and kinematics. A single frozen TrajTok encoder with lightweight adapters outperforms task-specific methods on trajectory similarity search, classification, ETA, and travel-time regression on the Porto dataset. The work positions learned spatial tokenization plus masked pretraining as a viable path toward general-purpose trajectory foundation models.