FlowWM applies flow matching directly in pretrained feature space with a one-step projection mechanism, improving perception accuracy, mode coverage, and horizon robustness on synthetic and real-world benchmarks.
arXiv preprint arXiv:2507.13162 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A representation- and geometry-guided discrete tokenizer for driving scenes improves token quality for world models and planning on NAVSIM.
citing papers explorer
-
Flow Matching in Feature Space for Stochastic World Modeling
FlowWM applies flow matching directly in pretrained feature space with a one-step projection mechanism, improving perception accuracy, mode coverage, and horizon robustness on synthetic and real-world benchmarks.
-
Unified Driving Tokens: Representation- and Geometry-Guided Discrete Tokenizer for Driving World Models and Planning
A representation- and geometry-guided discrete tokenizer for driving scenes improves token quality for world models and planning on NAVSIM.