A latent flow-matching model with asynchronous, per-event noise schedules jointly generates inter-event times and event types, improving RMSE and long-horizon optimal-transport distance on five TPP benchmarks.
In other words: Eϵ∼N (0,I)[ps(xs|ϵ) ps(xs) us(xs|ϵ)] = us(xs)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ADiff4TPP: Asynchronous Diffusion Models for Temporal Point Processes
A latent flow-matching model with asynchronous, per-event noise schedules jointly generates inter-event times and event types, improving RMSE and long-horizon optimal-transport distance on five TPP benchmarks.