Research map / Video / Video generation
Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals
Nate Gillman, Yinghua Zhou, Zitian Tang, Evan Luo, Arjan Chakravarthy, Daksh Aggarwal, Michael Freeman, Chen Sun
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add explicit goal-force control signal vs text-only zero-shot Wan2.2 | Goal Force · Two Object Collision human study | goal force adherence preference: 73.4% preference | Improved |
| add explicit goal-force control signal vs text-only fine-tuned ControlNet (ablation) | Goal Force · Tool Object Interaction human study | goal force adherence preference: 60.3% preference | Improved |
| add goal force control signal | Goal Force · Human Object Interaction human study | realistic motion and visual quality: 47.5% and 48.9% preference vs zero-shot | Hurt |
| random masking of causal information (goal vs direct force) during training | Goal Force · Domino diversity | diversity score: 0.3900 -> 0.6577 | Improved |
| provide mass channel in control signal | Goal Force · ball collision speed | projectile speed relations satisfied: all four in-distribution, three of four out-of-distribution | Mixed |
Closest papers by meaning
- Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals (NeurIPS 2025 · similarity 0.92)
- PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation (NeurIPS 2025 · similarity 0.89)
- RoboDreamer: Learning Compositional World Models for Robot Imagination (ICML 2024 · similarity 0.87)
- How Far Is Video Generation from World Model: A Physical Law Perspective (ICML 2025 · similarity 0.87)
- RoboScape: Physics-informed Embodied World Model (NeurIPS 2025 · similarity 0.87)
- VideoVLA: Video Generators Can Be Generalizable Robot Manipulators (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
