Physis-Lang: Self-Evolving Language as a Physical Representation for Video World Model

arXiv:2609.40358 · cs.CV · Submitted 2026-09-30 · Read on arXiv

cs.CV

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/kandinskylab/kandinsky-wm

Terminology

• Benchmark — 44× in this paper · explained in 2 episodes
• World Model — 43× in this paper · explained in 7 episodes
• Agentic Loop — 9× in this paper · explained in 1 episode
• Alignment — 9× in this paper · explained in 1 episode
• F1 Score — 8× in this paper · explained in 3 episodes
• Fine-Tuning — 8× in this paper · explained in 5 episodes
• Generative Model — 7× in this paper · explained in 2 episodes
• Generative Models — 5× in this paper · explained in 2 episodes
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Activation Checkpointing — 4× in this paper · explained in 1 episode
• Consistency — 4× in this paper · explained in 3 episodes
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Embeddings — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Self-Evolving Agents — 2× in this paper · explained in 2 episodes
• Steering — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Latent World Models — 1× in this paper · explained in 2 episodes
• Momentum transfer — 1× in this paper · explained in 2 episodes
• Physical Constraints — 1× in this paper · explained in 7 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Temporal consistency — 1× in this paper · explained in 2 episodes

Sources

• Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility
• CausalMotion: Structured Physical Reasoning as Keyframe and Trajectory Guidance for Training-Free Video Generation
• PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance
• MMPhysVideo: Physically Plausible Video Generation Through Joint RGB-Perception Modeling
• Learning Plug-and-play Memory for Guiding Video Diffusion Models
• Seeking Physics in Diffusion Noise
• Think Before You Diffuse: Infusing Physical Rules into Video Diffusion
• Bootstrapping Physics-Grounded Video Generation through VLM-Guided Iterative Self-Refinement
• NEWTON: Agentic Planning for Physically Grounded Video Generation
• PhiZero: A World Model Built Around Physical Language
• PhysCorr: Dual-Reward DPO for Physics-Constrained Text-to-Video Generation with Automated Preference Selection
• PhyWorld: Physics-Faithful World Model for Video Generation
• Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers
• When Physical Preferences Meet Semantic Constraints: Physical and Semantic Direct Preference Optimization for Text-to-Video Generation
• PhyPrompt: RL-based Prompt Refinement for Physically Plausible Text-to-Video Generation
• Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning
• DiReCT: Disentangled Regularization of Contrastive Trajectories for Physics-Refined Video Generation
• STANCE: Motion Coherent Video Generation Via Sparse-to-Dense Anchored Encoding
• PH-Dreamer: A Physics-Driven World Model via Port-Hamiltonian Generative Dynamics
• Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamics

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models