Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors
cs.CV, cs.RO
Submitted: 2026-10-13
Updated: 2026-10-13
Comments: 31 pages, 17 figures. Project page: https://research.nvidia.com/labs/sil/projects/lidarverse
Project page: https://research.nvidia.com/labs/sil/projects/lidarverse
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- LaGen: Towards Autoregressive LiDAR Scene Generation
- RangeLDM: Fast Realistic LiDAR Point Cloud Generation
- Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models
- LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields
- STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes
- GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction
- GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors
- GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting
- Wan: Open and Advanced Large-Scale Video Generative Models
- World Simulation with Video Foundation Models for Physical AI
- Qwen2.5-VL Technical Report
- Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
- Efficient Streaming Language Models with Attention Sinks
- Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
- Long-Context Autoregressive Video Modeling with Next-Frame Prediction
- Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization
- Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention
- Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation
- Addressable Memory for Video World Models
- Cosmos World Foundation Model Platform for Physical AI
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