# PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation

arXiv: https://arxiv.org/abs/2412.00596 · HTML: https://mlsanity.com/paper/2412.00596/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 34 of its 63 references that are in the map.
- First posted on arXiv 30 Nov 2024.

## Placed in

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

## Builds on (most cited first, 30 of 34)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models](https://mlsanity.com/paper/2309.15103/) (2023)
- [Photorealistic Video Generation with Diffusion Models](https://mlsanity.com/paper/2312.06662/) (2023)
- [LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://mlsanity.com/paper/2305.13655/) (2023)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://mlsanity.com/paper/2401.11708/) (2024)
- [Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters](https://mlsanity.com/paper/2212.10001/) (2022)
- [PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation](https://mlsanity.com/paper/2409.18964/) (2024)
- [Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation](https://mlsanity.com/paper/2410.05363/) (2024)
- [VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://mlsanity.com/paper/2309.15091/) (2023)
- [Tarsier: Recipes for Training and Evaluating Large Video Description Models](https://mlsanity.com/paper/2407.00634/) (2024)
- [Self-correcting LLM-controlled Diffusion Models](https://mlsanity.com/paper/2311.16090/) (2023)
- [In-Context Learning Unlocked for Diffusion Models](https://mlsanity.com/paper/2305.01115/) (2023)
- [Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answering](https://mlsanity.com/paper/2308.13259/) (2023)
- [WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens](https://mlsanity.com/paper/2401.09985/) (2024)
- [LLM-grounded Video Diffusion Models](https://mlsanity.com/paper/2309.17444/) (2023)
- [CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects](https://mlsanity.com/paper/2401.09962/) (2024)
- [GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning](https://mlsanity.com/paper/2311.12631/) (2023)
- [UnrealCV: Connecting Computer Vision to Unreal Engine](https://mlsanity.com/paper/1609.01326/) (2016)
- [A Survey on Long Video Generation: Challenges, Methods, and Prospects](https://mlsanity.com/paper/2403.16407/) (2024)
- [Compositional 3D-aware Video Generation with LLM Director](https://mlsanity.com/paper/2409.00558/) (2024)
- [WorldGPT: A Sora-Inspired Video AI Agent as Rich World Models from Text and Image Inputs](https://mlsanity.com/paper/2403.07944/) (2024)

## Built on by (most cited first, 30 of 80)

- [VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models](https://mlsanity.com/paper/2505.23656/) (2025)
- [WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation](https://mlsanity.com/paper/2503.08153/) (2025)
- [Uni-cot: Towards Unified Chain-of-Thought Reasoning Across Text and Vision](https://mlsanity.com/paper/2508.05606/) (2025)
- [VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior](https://mlsanity.com/paper/2503.23368/) (2025)
- [NewtonGen: Physics-Consistent and Controllable Text-to-Video Generation via Neural Newtonian Dynamics](https://mlsanity.com/paper/2509.21309/) (2025)
- [Inference-time Physics Alignment of Video Generative Models with Latent World Models](https://mlsanity.com/paper/2601.10553/) (2026)
- [Exploring the Evolution of Physics Cognition in Video Generation: A Survey](https://mlsanity.com/paper/2503.21765/) (2025)
- [What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards](https://mlsanity.com/paper/2512.00425/) (2025)
- [Generative Physical AI in Vision: A Survey](https://mlsanity.com/paper/2501.10928/) (2025)
- [PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation](https://mlsanity.com/paper/2512.24551/) (2025)
- [PresentAgent: Multimodal Agent for Presentation Video Generation](https://mlsanity.com/paper/2507.04036/) (2025)
- [Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation](https://mlsanity.com/paper/2508.10858/) (2025)
- [AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation](https://mlsanity.com/paper/2604.08540/) (2026)
- [T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation](https://mlsanity.com/paper/2507.18107/) (2025)
- [TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models](https://mlsanity.com/paper/2511.13704/) (2025)
- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning](https://mlsanity.com/paper/2504.15932/) (2025)
- [PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models](https://mlsanity.com/paper/2601.11087/) (2026)
- [Think Before You Diffuse: Infusing Physical Rules into Video Diffusion](https://mlsanity.com/paper/2505.21653/) (2025)
- [MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models](https://mlsanity.com/paper/2510.19022/) (2025)
- [Synthetic Video Enhances Physical Fidelity in Video Synthesis](https://mlsanity.com/paper/2503.20822/) (2025)
- [Simulating the Visual World with Artificial Intelligence: A Roadmap](https://mlsanity.com/paper/2511.08585/) (2025)
- [Physical Simulator In-the-Loop Video Generation](https://mlsanity.com/paper/2603.06408/) (2026)
- [Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility](https://mlsanity.com/paper/2509.24702/) (2025)
- [Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations](https://mlsanity.com/paper/2510.05571/) (2025)
- [RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence](https://mlsanity.com/paper/2512.02622/) (2025)
- [Grounding Creativity in Physics: A Brief Survey of Physical Priors in AIGC](https://mlsanity.com/paper/2502.07007/) (2025)
- [PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning](https://mlsanity.com/paper/2510.13809/) (2025)
- [Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics](https://mlsanity.com/paper/2604.08503/) (2026)
- [NEWTON: Agentic Planning for Physically Grounded Video Generation](https://mlsanity.com/paper/2605.18396/) (2026)

## Abstract (arXiv)

Text-to-video (T2V) generation has been recently enabled by transformer-based diffusion models, but current T2V models lack capabilities in adhering to the real-world common knowledge and physical rules, due to their limited understanding of physical realism and deficiency in temporal modeling. Existing solutions are either data-driven or require extra model inputs, but cannot be generalizable to out-of-distribution domains. In this paper, we present PhyT2V, a new data-independent T2V technique that expands the current T2V model's capability of video generation to out-of-distribution domains, by enabling chain-of-thought and step-back reasoning in T2V prompting. Our experiments show that PhyT2V improves existing T2V models' adherence to real-world physical rules by 2.3x, and achieves 35% improvement compared to T2V prompt enhancers. The source codes are available at: https://github.com/pittisl/PhyT2V.