PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

• URL: http://arxiv.org/abs/2601.11087v1
• Date: Fri, 16 Jan 2026 08:40:10 GMT
• Title: PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models
• Authors: Qiyuan Zhang, Biao Gong, Shuai Tan, Zheng Zhang, Yujun Shen, Xing Zhu, Yuyuan Li, Kelu Yao, Chunhua Shen, Changqing Zou,
• Abstract summary: Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation.<n>We introduce a physics-aware reinforcement learning paradigm for video generation models that enforces physical collision rules directly in high-dimensional spaces.<n>We extend this paradigm to a unified framework, termed Mimicry-Discovery Cycle (MDcycle), which allows substantial fine-tuning.
• Score: 100.65199317765608
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Physical principles are fundamental to realistic visual simulation, but remain a significant oversight in transformer-based video generation. This gap highlights a critical limitation in rendering rigid body motion, a core tenet of classical mechanics. While computer graphics and physics-based simulators can easily model such collisions using Newton formulas, modern pretrain-finetune paradigms discard the concept of object rigidity during pixel-level global denoising. Even perfectly correct mathematical constraints are treated as suboptimal solutions (i.e., conditions) during model optimization in post-training, fundamentally limiting the physical realism of generated videos. Motivated by these considerations, we introduce, for the first time, a physics-aware reinforcement learning paradigm for video generation models that enforces physical collision rules directly in high-dimensional spaces, ensuring the physics knowledge is strictly applied rather than treated as conditions. Subsequently, we extend this paradigm to a unified framework, termed Mimicry-Discovery Cycle (MDcycle), which allows substantial fine-tuning while fully preserving the model's ability to leverage physics-grounded feedback. To validate our approach, we construct new benchmark PhysRVGBench and perform extensive qualitative and quantitative experiments to thoroughly assess its effectiveness.

Related papers

• PhysicsMind: Sim and Real Mechanics Benchmarking for Physical Reasoning and Prediction in Foundational VLMs and World Models [40.16417939211015]
  Modern foundational Multimodal Large Language Models (MLLMs) and video world models have advanced significantly in mathematical, common-sense, and visual reasoning.<n>Existing benchmarks attempting to measure this matter rely on synthetic, Visual Question Answer templates or focus on perceptual video quality that is tangential to measuring how well the video abides by physical laws.<n>We introduce PhysicsMind, a unified benchmark that evaluates law-consistent reasoning and generation over three canonical principles: Center of Mass, Lever Equilibrium, and Newton's First Law.
  arXiv  Detail & Related papers  (2026-01-22T14:33:01Z)
• Inference-time Physics Alignment of Video Generative Models with Latent World Models [28.62446995107834]
  We introduce WMReward and treat improving physics plausibility of video generation as an inference-time alignment problem.<n>In particular, we leverage the strong physics prior to a latent world model as a reward to search and steer multiple candidate denoising trajectories.<n> Empirically, our approach substantially improves physics plausibility across image-conditioned, multiframe-conditioned, and text-conditioned generation settings.
  arXiv  Detail & Related papers  (2026-01-15T16:18:00Z)
• ProPhy: Progressive Physical Alignment for Dynamic World Simulation [55.456455952212416]
  ProPhy is a Progressive Physical Alignment Framework that enables explicit physics-aware conditioning and anisotropic generation.<n>We show that ProPhy produces more realistic, dynamic, and physically coherent results than existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-05T09:39:26Z)
• PhysCorr: Dual-Reward DPO for Physics-Constrained Text-to-Video Generation with Automated Preference Selection [10.498184571108995]
  We propose PhysCorr, a unified framework for modeling, evaluating, and optimizing physical consistency in video generation.<n>Specifically, we introduce PhysicsRM, the first dual-dimensional reward model that quantifies both intra-object stability and inter-object interactions.<n>Our approach is model-agnostic and scalable, enabling seamless integration into a wide range of video diffusion and transformer-based backbones.
  arXiv  Detail & Related papers  (2025-11-06T02:40:57Z)
• LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference [57.086932851733145]
  We introduce LikePhys, a training-free method that evaluates intuitive physics in video diffusion models.<n>We benchmark intuitive physics understanding in current video diffusion models.<n> Empirical results show that, despite current models struggling with complex and chaotic dynamics, there is a clear trend of improvement in physics understanding as model capacity and inference settings scale.
  arXiv  Detail & Related papers  (2025-10-13T15:19:07Z)
• PhysHMR: Learning Humanoid Control Policies from Vision for Physically Plausible Human Motion Reconstruction [52.44375492811009]
  We present PhysHMR, a unified framework that learns a visual-to-action policy for humanoid control in a physics-based simulator.<n>A key component of our approach is the pixel-as-ray strategy, which lifts 2D keypoints into 3D spatial rays and transforms them into global space.<n>PhysHMR produces high-fidelity, physically plausible motion across diverse scenarios, outperforming prior approaches in both visual accuracy and physical realism.
  arXiv  Detail & Related papers  (2025-10-02T21:01:11Z)
• Physics-Grounded Motion Forecasting via Equation Discovery for Trajectory-Guided Image-to-Video Generation [54.42523027597904]
  We introduce a novel framework that integrates symbolic regression and trajectory-guided image-to-video (I2V) models for physics-grounded video forecasting.<n>Our approach extracts motion trajectories from input videos, uses a retrieval-based pre-training mechanism to enhance symbolic regression, and discovers equations of motion to forecast physically accurate future trajectories.
  arXiv  Detail & Related papers  (2025-07-09T13:28:42Z)
• PhyMAGIC: Physical Motion-Aware Generative Inference with Confidence-guided LLM [17.554471769834453]
  We present PhyMAGIC, a training-free framework that generates physically consistent motion from a single image.<n>PhyMAGIC integrates a pre-trained image-to-video diffusion model, confidence-guided reasoning via LLMs, and a differentiable physics simulator.<n> Comprehensive experiments demonstrate that PhyMAGIC outperforms state-of-the-art video generators and physics-aware baselines.
  arXiv  Detail & Related papers  (2025-05-22T09:40:34Z)
• PhysMotion: Physics-Grounded Dynamics From a Single Image [24.096925413047217]
  We introduce PhysMotion, a novel framework that leverages principled physics-based simulations to guide intermediate 3D representations generated from a single image and input conditions.<n>Our approach addresses the limitations of traditional data-driven generative models and result in more consistent physically plausible motions.
  arXiv  Detail & Related papers  (2024-11-26T07:59:11Z)
• Physics-Integrated Variational Autoencoders for Robust and Interpretable Generative Modeling [86.9726984929758]
  We focus on the integration of incomplete physics models into deep generative models. We propose a VAE architecture in which a part of the latent space is grounded by physics. We demonstrate generative performance improvements over a set of synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2021-02-25T20:28:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.