U2Diffine augments diffusion denoising with negative log-likelihood loss and first-order uncertainty propagation to jointly perform trajectory completion and provide per-state heteroscedastic uncertainty for multi-agent paths.
Collaborative uncertainty benefits multi-agent multi- modal trajectory forecasting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Heteroscedastic Diffusion for Multi-Agent Trajectory Modeling
U2Diffine augments diffusion denoising with negative log-likelihood loss and first-order uncertainty propagation to jointly perform trajectory completion and provide per-state heteroscedastic uncertainty for multi-agent paths.