Text2Sim: Agentic Physics-Based Simulation Generation with Distilled Expertise
cs.GR, cs.AI
Submitted: 2026-09-29
Updated: 2026-09-30
Code: https://github.com/Genesis-Embodied-AI/genesis-world
Project page: https://phys-sim-book.github.io
Sources
- Seedance 1.0: Exploring the Boundaries of Video Generation Models
- Video Diffusion Models
- InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
- Training and Benchmarking Code Generation for Physics-Inspired Animations
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
- GS-Agent: Creating 4D Physical Worlds With Generative Simulation
Related papers
- SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control
- CADReasoner: Iterative Program Editing for CAD Reverse Engineering
- QuadLink: Autoregressive Quad-Dominant Mesh Generation via Point-Relation Learning
- DrawVideo: Grounded and Faithful Multi-Shot Video Generation from Storyboard Keyframe Sketches
- MotionPersona: Real-Time Locomotion Control across Personas, Bodies, and Styles
- GaussianBench: Physics-Fidelity Evaluation for Gaussian Scene Representations