# Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning

arXiv: https://arxiv.org/abs/2504.15932 · HTML: https://mlsanity.com/paper/2504.15932/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 58 references that are in the map.
- First posted on arXiv 22 Apr 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 29 of 29)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Vector-quantized Image Modeling with Improved VQGAN](https://mlsanity.com/paper/2110.04627/) (2021)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [How Far is Video Generation from World Model: A Physical Law Perspective](https://mlsanity.com/paper/2411.02385/) (2024)
- [MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance](https://mlsanity.com/paper/2406.19680/) (2024)
- [Do generative video models understand physical principles?](https://mlsanity.com/paper/2501.09038/) (2025)
- [VideoDPO: Omni-Preference Alignment for Video Diffusion Generation](https://mlsanity.com/paper/2412.14167/) (2024)
- [PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation](https://mlsanity.com/paper/2412.00596/) (2024)
- [OnlineVPO: Align Video Diffusion Model with Online Video-Centric Preference Optimization](https://mlsanity.com/paper/2412.15159/) (2024)
- [Auto-Encoding Morph-Tokens for Multimodal LLM](https://mlsanity.com/paper/2405.01926/) (2024)
- [AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding](https://mlsanity.com/paper/2409.09039/) (2024)
- [Generative Physical AI in Vision: A Survey](https://mlsanity.com/paper/2501.10928/) (2025)
- [Non-confusing Generation of Customized Concepts in Diffusion Models](https://mlsanity.com/paper/2405.06914/) (2024)
- [Towards Transformer-Based Aligned Generation with Self-Coherence Guidance](https://mlsanity.com/paper/2503.17675/) (2025)
- [Embedding Self-Correction as an Inherent Ability in Large Language Models for Enhanced Mathematical Reasoning](https://mlsanity.com/paper/2410.10735/) (2024)
- [Efficient Prompting for Continual Adaptation to Missing Modalities](https://mlsanity.com/paper/2503.00528/) (2025)
- [Latent Knowledge-Guided Video Diffusion for Scientific Phenomena Generation from a Single Initial Frame](https://mlsanity.com/paper/2411.11343/) (2024)
- [The Power of Next-Frame Prediction for Learning Physical Laws](https://mlsanity.com/paper/2405.17450/) (2024)

## Built on by (most cited first, 18 of 18)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning](https://mlsanity.com/paper/2505.07538/) (2025)
- [MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models](https://mlsanity.com/paper/2510.19022/) (2025)
- [Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility](https://mlsanity.com/paper/2509.24702/) (2025)
- [Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances](https://mlsanity.com/paper/2508.10316/) (2025)
- [Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models](https://mlsanity.com/paper/2605.18601/) (2026)
- [Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning](https://mlsanity.com/paper/2506.01480/) (2025)
- [Reinforcement Learning for Large Model: A Survey](https://mlsanity.com/paper/2508.08189/) (2025)
- [Planning with Sketch-Guided Verification for Physics-Aware Video Generation](https://mlsanity.com/paper/2511.17450/) (2025)
- [WorldEdit: Towards Open-World Image Editing with a Knowledge-Informed Benchmark](https://mlsanity.com/paper/2602.07095/) (2026)
- [Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation](https://mlsanity.com/paper/2606.25306/) (2026)
- [From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models](https://mlsanity.com/paper/2511.12861/) (2025)
- [Physics-Informed Video Diffusion For Shallow Water Equations](https://mlsanity.com/paper/2603.15627/) (2026)
- [Distilling Physical Priors into Streaming World Models](https://mlsanity.com/paper/2608.07981/) (2026)
- [PhySe-RPO: Physics and Semantics Guided Relative Policy Optimization for Diffusion-Based Surgical Smoke Removal](https://mlsanity.com/paper/2603.22844/) (2026)
- [Learning How the World Evolves: Extrapolative Video World Models via Latent Dynamics Reasoning](https://mlsanity.com/paper/2608.09926/) (2026)
- [Video Generation Models: A Survey of Post-Training and Alignment](https://mlsanity.com/paper/2610.00812/) (2026)

## Abstract (arXiv)

Despite recent progress in video generation, producing videos that adhere to physical laws remains a significant challenge. Traditional diffusion-based methods struggle to extrapolate to unseen physical conditions (eg, velocity) due to their reliance on data-driven approximations. To address this, we propose to integrate symbolic reasoning and reinforcement learning to enforce physical consistency in video generation. We first introduce the Diffusion Timestep Tokenizer (DDT), which learns discrete, recursive visual tokens by recovering visual attributes lost during the diffusion process. The recursive visual tokens enable symbolic reasoning by a large language model. Based on it, we propose the Phys-AR framework, which consists of two stages: The first stage uses supervised fine-tuning to transfer symbolic knowledge, while the second stage applies reinforcement learning to optimize the model's reasoning abilities through reward functions based on physical conditions. Our approach allows the model to dynamically adjust and improve the physical properties of generated videos, ensuring adherence to physical laws. Experimental results demonstrate that PhysAR can generate videos that are physically consistent.