Lists (8)
Stars
G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training" official implementation.
This is a public version of LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision
[NeurIPS 2025] SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations
Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
Code implementation of the paper "World-in-World: World Models in a Closed-Loop World"
[NeurIPS 2025] PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation
Feed-forward model for predicting 3D physics with 3DGS + NeRF
Code for A Neural Material Point Method for Particle-based Emulation
[ICCV 2025 Highlight] DIMO: Diverse 3D Motion Generation for Arbitrary Objects
[CVPR 2025] Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
[ECCV 2024] DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
[CVPR 2024 Highlight] Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields
Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.
Just wanna see what type and how many GPUs/TPUs are used in CVPR 2025 oral papers. Fun vibe coding with LLMs.
MAGI-1: Autoregressive Video Generation at Scale
This is the repository that contains source code for the PhysGen3D.
[ICCV 2025, Oral] TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
Original implementation of "Radiant Foam: Real-Time Differentiable Ray Tracing"
DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image (ICLR 2025)
Self-reimplemented version of Long-LRM.
DELTA: Dense Efficient Long-range 3D Tracking for Any video (ICLR 2025)