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..
Seeing the Wind from a Falling Leaf
Authors: Zhiyuan Gao, Jiageng Mao, Hong-Xing "Koven" Yu, HAOZHE LOU, Emily Jia, Jernej Barbic, Jiajun Wu, Yue Wang
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we conduct comprehensive experiments to investigate the following key questions: Can our method successfully recover forces from both synthetic and real-world videos? (Section 4.2) How do the proposed components, i.e., force representation and loss function affect the final performance, and how robust is the proposed VLM framework to variations in object physical properties?(Section 4.3) How can our method be applied to physics-based video generation and editing? (Section 4.4)... For numerical comparisons in synthetic scenarios, we adopt image reconstruction metrics, i.e., PSNR, SSIM [64], and LPIPS [65], to compare the re-simulated videos with the recovered forces and the original input videos, to demonstrate the accuracy of recovered forces in simulation. Moreover, we compare the recovered forces with the ground truth forces using two metrics: average magnitude error (reported as percentages) and direction error (measured in degrees). |
| Researcher Affiliation | Academia | Zhiyuan Gao1 Jiageng Mao1 Hong-Xing Yu2 Haozhe Lou1 Emily Yue-Ting Jia1 Jernej Barbic1 Jiajun Wu2 Yue Wang1 1University of Southern California 2Stanford University |
| Pseudocode | No | The paper describes the methodology in prose and mathematical equations (e.g., Section 3.1, 3.2, 3.3, 3.4) but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The code is not included for now. A demonstration code will be released upon acceptance. |
| Open Datasets | Yes | For synthetic data, we use synthetic objects in [63, 18] to evaluate the numerical accuracy of recovered forces. |
| Dataset Splits | No | The paper mentions conducting experiments on 'synthetic objects in [63, 18]' and 'Internet videos' but does not specify any explicit training, validation, or test dataset splits, such as percentages or sample counts. |
| Hardware Specification | No | The paper states in the NeurIPS Paper Checklist (Question 8) that it provides sufficient information on computer resources for experiments, but these details (specific GPU/CPU models, memory) are not present in the main body of the provided paper text. |
| Software Dependencies | No | The paper mentions the use of a differentiable physics simulator using the Material Point Method (MPM) [2], vision-language models [53], and grounded segmentation models [54], but it does not specify specific version numbers for these software components or any other key libraries. The NeurIPS checklist states 'implementation details' are included, but these are not present in the provided text. |
| Experiment Setup | No | The paper states in the NeurIPS Paper Checklist (Question 6) that it includes 'implementation details', which would typically contain experimental setup information, but these specific details (hyperparameters, optimizer settings, etc.) are not present in the main body of the provided paper text. |