# PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLM

arXiv: https://arxiv.org/abs/2505.16456 · HTML: https://mlsanity.com/paper/2505.16456/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 35 of its 42 references that are in the map.
- First posted on arXiv 22 May 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 35)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [Learning to Simulate Complex Physics with Graph Networks](https://mlsanity.com/paper/2002.09405/) (2020)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics](https://mlsanity.com/paper/2311.12198/) (2023)
- [SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion](https://mlsanity.com/paper/2403.12008/) (2024)
- [Text-to-3D using Gaussian Splatting](https://mlsanity.com/paper/2309.16585/) (2023)
- [Neural Radiance Flow for 4D View Synthesis and Video Processing](https://mlsanity.com/paper/2012.09790/) (2020)
- [PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation](https://mlsanity.com/paper/2404.13026/) (2024)
- [PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation](https://mlsanity.com/paper/2409.18964/) (2024)
- [Open-Sora 2.0: Training a Commercial-Level Video Generation Model in 200k](https://mlsanity.com/paper/2503.09642/) (2025)
- [L4GM: Large 4D Gaussian Reconstruction Model](https://mlsanity.com/paper/2406.10324/) (2024)
- [Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians](https://mlsanity.com/paper/2403.09434/) (2024)
- [Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion](https://mlsanity.com/paper/2406.04338/) (2024)
- [Learning Signed Distance Field for Multi-view Surface Reconstruction](https://mlsanity.com/paper/2108.09964/) (2021)
- [OmniPhysGS: 3D Constitutive Gaussians for General Physics-Based Dynamics Generation](https://mlsanity.com/paper/2501.18982/) (2025)
- [A Compact Dynamic 3D Gaussian Representation for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2311.12897/) (2023)
- [DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation](https://mlsanity.com/paper/2410.06756/) (2024)
- [GIC: Gaussian-Informed Continuum for Physical Property Identification and Simulation](https://mlsanity.com/paper/2406.14927/) (2024)
- [Differentiable Physics Simulation of Dynamics-Augmented Neural Objects](https://mlsanity.com/paper/2210.09420/) (2022)
- [PhysMotion: Physics-Grounded Dynamics From a Single Image](https://mlsanity.com/paper/2411.17189/) (2024)
- [Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling](https://mlsanity.com/paper/2410.18912/) (2024)
- [PhysFlow: Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation](https://mlsanity.com/paper/2411.14423/) (2024)
- [Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics](https://mlsanity.com/paper/2410.08257/) (2024)
- [Exploring the Evolution of Physics Cognition in Video Generation: A Survey](https://mlsanity.com/paper/2503.21765/) (2025)
- [ParticleNeRF: A Particle-Based Encoding for Online Neural Radiance Fields](https://mlsanity.com/paper/2211.04041/) (2022)

## Built on by (most cited first, 5 of 5)

- [When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Video Generation](https://mlsanity.com/paper/2607.16947/) (2026)
- [MonoSR: Open-Vocabulary Spatial Reasoning from Monocular Images](https://mlsanity.com/paper/2511.19119/) (2025)
- [Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering](https://mlsanity.com/paper/2608.21450/) (2026)
- [PhysForge: Material-Controllable 3D Reconstruction with Separable Components](https://mlsanity.com/paper/2610.13681/) (2026)
- [PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA](https://mlsanity.com/paper/2610.19823/) (2026)

## Abstract (arXiv)

Recent advances in 3D content generation have amplified demand for dynamic models that are both visually realistic and physically consistent. However, state-of-the-art video diffusion models frequently produce implausible results such as momentum violations and object interpenetrations. Existing physics-aware approaches often rely on task-specific fine-tuning or supervised data, which limits their scalability and applicability. To address the challenge, we present PhyMAGIC, a training-free framework that generates physically consistent motion from a single image. PhyMAGIC integrates a pre-trained image-to-video diffusion model, confidence-guided reasoning via LLMs, and a differentiable physics simulator to produce 3D assets ready for downstream physical simulation without fine-tuning or manual supervision. By iteratively refining motion prompts using LLM-derived confidence scores and leveraging simulation feedback, PhyMAGIC steers generation toward physically consistent dynamics. Comprehensive experiments demonstrate that PhyMAGIC outperforms state-of-the-art video generators and physics-aware baselines, enhancing physical property inference and motion-text alignment while maintaining visual fidelity.