Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Self-Consistent Generative Paths via Admissible Random Variational Transport
Lei Luo, Yingzhen Zhang, Jian Yang
Modern generative models often define an entire probability path from a simple prior to the data law, rather than only an endpoint map. Diffusion models follow stochastic denoising…
cs.LG2026
Conditional Random Ordered Transport Spaces
Lei Luo, Jian Yang
A small Wasserstein distance does not certify that a transformation is admissible. In evidence-constrained, semantic, causal, physical, monotone, or risk-sensitive learning, one mu…