Chain of Event-Centric Causal Thought for Physically Plausible Video Generation

• URL: http://arxiv.org/abs/2603.09094v1
• Date: Tue, 10 Mar 2026 02:13:51 GMT
• Title: Chain of Event-Centric Causal Thought for Physically Plausible Video Generation
• Abstract summary: Physically Plausible Video Generation (PPVG) has emerged as a promising avenue for modeling real-world physical phenomena.<n>Current approaches leverage commonsense reasoning capability of large language models to embed physical concepts into prompts.<n>In this paper, we view PPVG as generating a sequence of causally connected and dynamically evolving events.
• Score: 41.53933387975629
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Physically Plausible Video Generation (PPVG) has emerged as a promising avenue for modeling real-world physical phenomena. PPVG requires an understanding of commonsense knowledge, which remains a challenge for video diffusion models. Current approaches leverage commonsense reasoning capability of large language models to embed physical concepts into prompts. However, generation models often render physical phenomena as a single moment defined by prompts, due to the lack of conditioning mechanisms for modeling causal progression. In this paper, we view PPVG as generating a sequence of causally connected and dynamically evolving events. To realize this paradigm, we design two key modules: (1) Physics-driven Event Chain Reasoning. This module decomposes the physical phenomena described in prompts into multiple elementary event units, leveraging chain-of-thought reasoning. To mitigate causal ambiguity, we embed physical formulas as constraints to impose deterministic causal dependencies during reasoning. (2) Transition-aware Cross-modal Prompting (TCP). To maintain continuity between events, this module transforms causal event units into temporally aligned vision-language prompts. It summarizes discrete event descriptions to obtain causally consistent narratives, while progressively synthesizing visual keyframes of individual events by interactive editing. Comprehensive experiments on PhyGenBench and VideoPhy benchmarks demonstrate that our framework achieves superior performance in generating physically plausible videos across diverse physical domains. Our code will be released soon.

Related papers

• Physically Plausible Video Generation via Visual-Semantic Chain-of-Events Conditioning [48.21630532401797]
  We reformulate PPVG as event-centric generation by representing physical evolution as a chain of causally connected and physically constrained events.<n>Our framework generates videos with superior physical plausibility across diverse domains.
  arXiv  Detail & Related papers  (2026-09-01T03:35:02Z)
• CausalMotion: Structured Physical Reasoning as Keyframe and Trajectory Guidance for Training-Free Video Generation [31.482087672315895]
  textbfCausalMotion injects explicit physical reasoning into video generation through structured intermediate representations.<n>Our method consistently improves physical plausibility and temporal coherence, particularly in dynamics-intensive scenarios.
  arXiv  Detail & Related papers  (2026-06-12T09:57:01Z)
• RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation [31.320456668679554]
  RealDiffusion is a framework designed to reconcile narrative dynamism with narrative coherence.<n>Heat diffusion serves as a dissipative prior that averages neighboring features along the sequence.<n>A region-aware process removes perturbations that explore nearby modes and prevent collapse so the story maintains pose change and scene evolution.
  arXiv  Detail & Related papers  (2026-05-12T10:39:45Z)
• PhyRPR: Training-Free Physics-Constrained Video Generation [12.488633253476111]
  We propose a training-free three-stage pipeline for video generation.<n>textitPhyRPR:textitPhyulineReason--textitPhyulinePlan--textitPhyulineRefine.<n>textitPhyReason uses a large multimodal model for physical state reasoning and an image generator for synthesis.<n>textitPhyPlan deterministically synthesizes a controllable coarse motion scaffold.<n>textit
  arXiv  Detail & Related papers  (2026-01-14T07:41:56Z)
• Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions [70.87254264798341]
  PCI is a training-free and model-agnostic framework for analyzing concept dynamics through diffusion time.<n>It reveals diverse temporal behaviors across diffusion models, in which certain phases of the trajectory are more favorable to specific concepts even within the same concept type.
  arXiv  Detail & Related papers  (2025-12-09T11:05:08Z)
• Think Before You Diffuse: Infusing Physical Rules into Video Diffusion [55.046699347579455]
  The complexity of real-world motions, interactions, and dynamics introduce great difficulties when learning physics from data.<n>We propose DiffPhy, a generic framework that enables physically-correct and photo-realistic video generation by fine-tuning a pre-trained video diffusion model.
  arXiv  Detail & Related papers  (2025-05-27T18:26:43Z)
• Reasoning Physical Video Generation with Diffusion Timestep Tokens via Reinforcement Learning [53.33388279933842]
  We propose to integrate symbolic reasoning and reinforcement learning to enforce physical consistency in video generation.<n>Based on it, we propose the Phys-AR framework, which consists of two stages: The first uses supervised fine-tuning to transfer symbolic knowledge, while the second stage applies reinforcement learning to optimize the model's reasoning abilities.<n>Our approach allows the model to dynamically adjust and improve the physical properties of generated videos, ensuring adherence to physical laws.
  arXiv  Detail & Related papers  (2025-04-22T14:20:59Z)
• ContPhy: Continuum Physical Concept Learning and Reasoning from Videos [86.63174804149216]
  ContPhy is a novel benchmark for assessing machine physical commonsense. We evaluated a range of AI models and found that they still struggle to achieve satisfactory performance on ContPhy. We also introduce an oracle model (ContPRO) that marries the particle-based physical dynamic models with the recent large language models.
  arXiv  Detail & Related papers  (2024-02-09T01:09:21Z)

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.