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..
Flow Field Reconstruction with Sensor Placement Policy Learning
Authors: Ruoyan Li, Frank Wan, Zijie Huang, Zixiao Liu, Haixin Wang, Xiao Luo, Wei Wang, Yizhou Sun
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct comprehensive experiments under realistic assumptions to benchmark the performance of our reconstruction model and sensor placement policy. Together, they achieve significant improvements over existing methods. 5 Experiment |
| Researcher Affiliation | Academia | Ruoyan Li1, Guancheng Wan1, Zijie Huang1, Zixiao Liu1, Haixin Wang1, Xiao Luo1, Wei Wang1, Yizhou Sun1 1University of California, Los Angeles |
| Pseudocode | Yes | Algorithm 1 Two Step Constrained PPO |
| Open Source Code | Yes | Code and datasets are available at Github. |
| Open Datasets | Yes | Code and datasets are available at Github. We evaluate our reconstruction model on NOAA OISST V2 weekly mean sea surface temperature dataset recorded from December 31, 1989 through January 29, 2023 (Reynolds et al., 2008) |
| Dataset Splits | Yes | We train on 80% of the data, use 10% for validation and the remaining 10% for testing. |
| Hardware Specification | Yes | We implement all models in Py Torch. All experiments are run on servers/workstations with the following configuration: 80 CPUs, 503G Mem, 8 x NVIDIA V100 GPUs. 48 CPUs, 220G Mem, 8 x NVIDIA TITAN Xp GPUs. 96 CPUs, 1.0T Mem, 8 x NVIDIA A100 GPUs. 64 CPUs, 1.0T Mem, 8 x NVIDIA RTX A6000 GPUs. 224 CPUs, 1.5T Mem, 8 x NVIDIA L40S GPUs. |
| Software Dependencies | No | We implement all models in Py Torch. (No specific version number for PyTorch or any other software library is provided.) |
| Experiment Setup | Yes | The hidden dimension is set to 64. We add a separate MLP in the encoder to encode the binary mask indicating sensor placement. The mask encoder latent dimension is set to 16. The number of attention blocks is set to 2. The models are trained with batch size 16 for 300 epochs. We use a cosine annealing learning rate with a starting learning rate at 1e-4 to an end learning rate at 1e-5. (This is an example from OFormer; similar details are provided for other models and in Appendix F for optimal sensor placement.) |