A decoder-only Transformer with an overprediction auxiliary loss reaches state-of-the-art non-ensemble accuracy on Argoverse 2 motion forecasting.
Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DONUT: A Decoder-Only Model for Trajectory Prediction
A decoder-only Transformer with an overprediction auxiliary loss reaches state-of-the-art non-ensemble accuracy on Argoverse 2 motion forecasting.