DA-WAM: Decision-Aligned Future Latents for Driving World Models
Anticipating how scenes evolve under ego actions is fundamental to safe autonomous driving, yet the full potential of world models for decision-making remains unrealized. The critical challenge lies in ensuring that future modeling is not merely predictive, but decision-informative: the predicted future must directly shape which trajectory is selected. Existing approaches decouple future representation learning from planning optimization, or share predicted states across trajectory candidates, thereby diluting the action-specific consequences that ought to guide selection. To bridge this gap,
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 56%Physics-informed deep learning for robust trajectory prediction in automated driving - Nature →
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- LinkedLinked via arxiv author · 85%Ruiguo Zhong →
“DA-WAM: Decision-Aligned Future Latents for Driving World Models”
- LinkedLinked via arxiv author · 85%Benshan Ma →
“DA-WAM: Decision-Aligned Future Latents for Driving World Models”
- LinkedLinked via arxiv author · 85%Xiaolong Chen →
“DA-WAM: Decision-Aligned Future Latents for Driving World Models”
- LinkedLinked via arxiv author · 85%Lang Zhang →
“DA-WAM: Decision-Aligned Future Latents for Driving World Models”
- LinkedLinked via arxiv author · 85%Mingyue Feng →
“DA-WAM: Decision-Aligned Future Latents for Driving World Models”
- LinkedLinked via arxiv author · 85%Yaonong Wang →
“DA-WAM: Decision-Aligned Future Latents for Driving World Models”