PhysEditWorld is a new dataset of over 60 million frames from 12 UE5 cinematic scenes with synchronized multimodal signals and explicit gravity labels, built via replay to support physics-editable world models.
Physctrl: Generative physics for controllable and physics-grounded video generation
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 13roles
background 2polarities
background 2representative citing papers
PQSG is a hierarchical question-graph pipeline for fine-grained physical plausibility evaluation in text-to-video generation that achieves higher correlation with human judgments than prior methods on the FinePhyEval dataset.
PhysAgent is a simulator-in-the-loop multi-agent system that automates physically grounded 4D synthesis from multimodal prompts by using trajectory feedback from vision models and LLM reasoning to optimize force fields.
A self-supervised framework learns implicit 3D physics by lifting V-JEPA features into voxels and performing volumetric feature advection conditioned on actions.
NEXUS introduces a graph-based neural energy-field model that derives forces from scalar energy and dissipation terms to achieve physically consistent contact-rich 3D dynamics.
StreamForce presents a unified causal model for force-controllable streaming video generation using a new force representation and distillation pipeline, claiming SOTA force adherence and 16.6 FPS performance.
DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and JailBreakV while preserving general capabilities.
LiVER conditions video diffusion models on renderer-derived 3D control signals for disentangled, editable control over object layout, lighting, and camera trajectory.
Next-scale autoregressive modeling with cross-scale and in-scale refinements produces SOTA text-to-motion generation by enforcing coarse-to-fine causal hierarchy.
A fine-tuned video diffusion model becomes a fast, differentiable CFD surrogate for urban wind, enabling gradient-based building-layout optimization confirmed by ground-truth simulations.
PhysRAG curates 7K videos from WISA-80K, builds a physical video database, and injects knowledge via learnable queries into a diffusion model to reach SOTA visual quality and physical compliance on PhyGenBench and VBench.
A new pipeline for occlusion-robust multi-object 3D reconstruction from sparse views supports physics-based robotic interaction.
The paper's stated CA-World counterfactual claim is absent from the body, which instead describes the SAM3D-Phys pipeline for multi-object interactive reconstruction and simulation.
citing papers explorer
-
PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models
PhysEditWorld is a new dataset of over 60 million frames from 12 UE5 cinematic scenes with synchronized multimodal signals and explicit gravity labels, built via replay to support physics-editable world models.
-
Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation
PQSG is a hierarchical question-graph pipeline for fine-grained physical plausibility evaluation in text-to-video generation that achieves higher correlation with human judgments than prior methods on the FinePhyEval dataset.
-
PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback
PhysAgent is a simulator-in-the-loop multi-agent system that automates physically grounded 4D synthesis from multimodal prompts by using trajectory feedback from vision models and LLM reasoning to optimize force fields.
-
Neural Voxel Dynamics: Learning Implicit 3D Physics via Volumetric Feature Advection
A self-supervised framework learns implicit 3D physics by lifting V-JEPA features into voxels and performing volumetric feature advection conditioned on actions.
-
NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics
NEXUS introduces a graph-based neural energy-field model that derives forces from scalar energy and dissipation terms to achieve physically consistent contact-rich 3D dynamics.
-
Streaming Video Generation with Streaming Force Control
StreamForce presents a unified causal model for force-controllable streaming video generation using a new force representation and distillation pipeline, claiming SOTA force adherence and 16.6 FPS performance.
-
Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and JailBreakV while preserving general capabilities.
-
Lighting-grounded Video Generation with Renderer-based Agent Reasoning
LiVER conditions video diffusion models on renderer-derived 3D control signals for disentangled, editable control over object layout, lighting, and camera trajectory.
-
Next-Scale Autoregressive Models for Text-to-Motion Generation
Next-scale autoregressive modeling with cross-scale and in-scale refinements produces SOTA text-to-motion generation by enforcing coarse-to-fine causal hierarchy.
-
Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows
A fine-tuned video diffusion model becomes a fast, differentiable CFD surrogate for urban wind, enabling gradient-based building-layout optimization confirmed by ground-truth simulations.
-
PhysRAG: Enhancing Physics-Awareness in Video Generation via Retrieval-Augmented Generation
PhysRAG curates 7K videos from WISA-80K, builds a physical video database, and injects knowledge via learnable queries into a diffusion model to reach SOTA visual quality and physical compliance on PhyGenBench and VBench.
-
Occlusion-Robust Multi-Object Decoupling for Physics-Based Robotic Interaction
A new pipeline for occlusion-robust multi-object 3D reconstruction from sparse views supports physics-based robotic interaction.
-
CA-World: Multi-Object Counterfactual Alignment for Efficient Interactive-Ready Reconstruction
The paper's stated CA-World counterfactual claim is absent from the body, which instead describes the SAM3D-Phys pipeline for multi-object interactive reconstruction and simulation.