# Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals

arXiv: https://arxiv.org/abs/2601.05848 · HTML: https://mlsanity.com/paper/2601.05848/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 33 of its 67 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)

## Builds on (most cited first, 30 of 33)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory](https://mlsanity.com/paper/2308.08089/) (2023)
- [Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning](https://mlsanity.com/paper/2311.10709/) (2023)
- [RoboDreamer: Learning Compositional World Models for Robot Imagination](https://mlsanity.com/paper/2404.12377/) (2024)
- [Motion Prompting: Controlling Video Generation with Motion Trajectories](https://mlsanity.com/paper/2412.02700/) (2024)
- [DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion](https://mlsanity.com/paper/2411.04928/) (2024)
- [GameGen-X: Interactive Open-world Game Video Generation](https://mlsanity.com/paper/2411.00769/) (2024)
- [CamI2V: Camera-Controlled Image-to-Video Diffusion Model](https://mlsanity.com/paper/2410.15957/) (2024)
- [Motion-Conditioned Diffusion Model for Controllable Video Synthesis](https://mlsanity.com/paper/2304.14404/) (2023)
- [MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model](https://mlsanity.com/paper/2405.20222/) (2024)
- [Dreamitate: Real-World Visuomotor Policy Learning via Video Generation](https://mlsanity.com/paper/2406.16862/) (2024)
- [Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion](https://mlsanity.com/paper/2406.04338/) (2024)
- [SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation](https://mlsanity.com/paper/2411.04989/) (2024)
- [Image Conductor: Precision Control for Interactive Video Synthesis](https://mlsanity.com/paper/2406.15339/) (2024)
- [Diffusion Reward: Learning Rewards via Conditional Video Diffusion](https://mlsanity.com/paper/2312.14134/) (2023)
- [Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals](https://mlsanity.com/paper/2505.19386/) (2025)
- [PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop](https://mlsanity.com/paper/2503.09595/) (2025)
- [MotionCraft: Physics-based Zero-Shot Video Generation](https://mlsanity.com/paper/2405.13557/) (2024)
- [PhysMotion: Physics-Grounded Dynamics From a Single Image](https://mlsanity.com/paper/2411.17189/) (2024)
- [WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions](https://mlsanity.com/paper/2505.18151/) (2025)
- [DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors](https://mlsanity.com/paper/2406.01476/) (2024)

## Built on by (most cited first, 9 of 9)

- [Masked Visual Actions for Unified World Modeling](https://mlsanity.com/paper/2607.19343/) (2026)
- [LaMo: Self-Supervised Latent Motion Priors for Physical Realism in Video Generation](https://mlsanity.com/paper/2605.23878/) (2026)
- [DeformMaster: An Interactive Physics-Neural World Model for Deformable Objects from Videos](https://mlsanity.com/paper/2605.09586/) (2026)
- [PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation](https://mlsanity.com/paper/2607.16355/) (2026)
- [PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control](https://mlsanity.com/paper/2609.17521/) (2026)
- [Seeking Physics in Diffusion Noise](https://mlsanity.com/paper/2603.14294/) (2026)
- [MotiMotion: Motion-Controlled Video Generation with Visual Reasoning](https://mlsanity.com/paper/2605.22818/) (2026)
- [VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation](https://mlsanity.com/paper/2607.23472/) (2026)
- [CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation](https://mlsanity.com/paper/2609.21455/) (2026)

## Abstract (arXiv)

Recent advancements in video generation have enabled the development of ``world models'' capable of simulating potential futures for robotics and planning. However, specifying precise goals for these models remains a challenge; text instructions are often too abstract to capture physical nuances, while target images are frequently infeasible to specify for dynamic tasks. To address this, we introduce Goal Force, a novel framework that allows users to define goals via explicit force vectors and intermediate dynamics, mirroring how humans conceptualize physical tasks. We train a video generation model on a curated dataset of synthetic causal primitives-such as elastic collisions and falling dominos-teaching it to propagate forces through time and space. Despite being trained on simple physics data, our model exhibits remarkable zero-shot generalization to complex, real-world scenarios, including tool manipulation and multi-object causal chains. Our results suggest that by grounding video generation in fundamental physical interactions, models can emerge as implicit neural physics simulators, enabling precise, physics-aware planning without reliance on external engines. We release all datasets, code, model weights, and interactive video demos at our project page.