Machine Learning for Autonomous Driving

Submissions

Submission deadlines: 19th October 2023 and 16th November 2023, at 23:59 Anywhere on Earth
Submission website: https://cmt3.research.microsoft.com/ML4AD2023
Submission format: either extended abstracts (4 pages) or full papers (up to 9 pages) anonymously using:
 •  neurips_2023_ml4ad.tex -- LaTeX template
 •  neurips_2023_ml4ad.sty -- style file for LaTeX 2e
 •  neurips_2023_ml4ad.pdf -- example PDF output
Authors may submit to either submission round and reviewers will treat both rounds equally. Some authors may prefer the earlier notification date of the first round (27 Oct) while other authors might prefer a later submission deadline (16 Nov). References and appendix should be appended into the same (single) PDF document, and do not count towards the page count.

We invite submissions on machine learning applied to autonomous driving, including (but not limited to):
 •  Foundational Driving Models
 •  Prediction and Planning for AV with LLMs
 •  Mapless Autonomous Driving
 •  Scaling Laws for Autonomous Driving
 •  Diffusion modeling for prediction, planning
 •  Closed loop training and evaluation
 •  Causal/counterfactual analysis of interactive multi-agent scenarios
 •  Human driver in the loop for interaction modeling
 •  Coordination with vehicles (V2V) or infrastructure (V2I)
 •  Uncertainty propagation through AV software pipelines
 •  Imitation learning, Reinforcement learning for AV
 •  Transfer learning (Sim2Real) and domain adaptation for autonomous driving
 •  Off-road autonomous driving
 •  Real-time inference and prediction
 •  Adaptive driving styles based on user preferences
 •  Metrics/benchmarks for autonomous driving

FAQ

Q: Are dual submissions OK?
A: Yes.

Q: Will there be archival proceedings?
A: No. Submissions will be indexed nor have archival proceedings.

Q: Should submitted papers be anonymized?
A: Yes. If accepted, we will ask for a de-anonymized version to link on the website.

Q: My papers contains ABC, but not XYZ, is this good enough for a submission?
A: Submissions will be evaluated based on these reviewer questions.