Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
UniMotion: A Unified Motion Framework for Simulation, Prediction and Planning
Authors: Nan Song, Junzhe Jiang, jingyu li, Xiatian Zhu, Li Zhang
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on the Waymo Open Motion Dataset demonstrate that joint training leads to robust generalization and effective task integration. With further fine-tuning, Uni Motion achieves state-of-the-art performance across a range of motion tasks, establishing it as a versatile and scalable solution for autonomous driving. |
| Researcher Affiliation | Academia | Nan Song1 Junzhe Jiang1 Jingyu Li1,2 Xiatian Zhu3 Li Zhang1,2 1School of Data Science, Fudan University 2Shanghai Innovation Institute 3University of Surrey Li Zhang (EMAIL) is the corresponding author. |
| Pseudocode | No | The paper describes the methodology and architecture but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | https://github.com/Logos Robotics Group/Uni Motion |
| Open Datasets | Yes | Extensive experiments on the Waymo Open Motion Dataset (WOMD) demonstrate that joint training leads to robust generalization and effective task integration. |
| Dataset Splits | Yes | To evaluate the performance of our method, we conduct extensive experiments on the Waymo Open Motion Dataset, comprising 486,995 training scenarios, 44,097 validation scenarios and 44,920 testing scenarios. |
| Hardware Specification | Yes | We train our models using the Adam W [41] optimizer with a total batch size of 48 on 8 NVIDIA A6000 GPUs for 30 epochs, with the weight decay set to 0.01. |
| Software Dependencies | No | The paper mentions using the Adam W optimizer and Transformer architecture, but does not provide specific version numbers for software libraries or programming languages. |
| Experiment Setup | Yes | We train our models using the Adam W [41] optimizer with a total batch size of 48 on 8 NVIDIA A6000 GPUs for 30 epochs, with the weight decay set to 0.01. We initialize the learning rate of 5 10 4 , which is then decayed following a cosine annealing schedule. Regarding the fine-tuning stage, we employ the same learning rate for prediction, while a lower learning rate of 5 10 5 for simulation and planning. Beside, we also fine-tune these tasks with the same epochs. |