worldbench repositories

awesome-event-camera-vision

Public

🌐 Event Camera Vision in the Era of Large Models: A Survey

perception low-latency object-detection reconstruction neuromorphic semantic-segmentation 3d vlm high-dynamic-range scene-understanding

Apache License 2.0

•2•6•0•0•Updated

Apr 20, 2026

worldbench.github.io

Public

HTML

•

MIT License

•1•0•0•0•Updated

Apr 16, 2026

awesome-vla-for-ad

Public

🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

awesome-list autonomous-driving multi-modal

awesome-list autonomous-driving multi-modal 3d vla self-driving vlm vision-language embodied-ai large-language-models

HTML

•

MIT License

•36•384•0•0•Updated

Apr 12, 2026

awesome-3d-4d-world-models

Public

🌐 3D and 4D World Modeling: A Survey

awesome-list autonomous-driving 3d

awesome-list autonomous-driving 3d 4d 3d-generation video-generation world-models embodied-ai 4d-generation lidar-generation

HTML

•

Apache License 2.0

•53•886•2•0•Updated

Apr 12, 2026

awesome-ai-auto-research

Public

🔥 A Survey on AI Auto-Research

agent ai multi-agent-system

agent ai multi-agent-system ai-research rag large-language-models llm agentic-ai ai-scientist auto-research

MIT License

•0•7•0•0•Updated

Apr 9, 2026

awesome-spatial-intelligence

Public

🌐 Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systems

planning lidar awesome-list

planning lidar awesome-list pretrained-models autonomous-driving 3d 4d vlm occupancy lidar-point-cloud

HTML

•

MIT License

•12•147•0•0•Updated

Apr 4, 2026

VideoLucy

Public

[NeurIPS 2025] Deep Memory Backtracking for Long Video Understanding

gpt video-understanding vlm

gpt video-understanding vlm multimodal egocentric-vision llm chatgpt mllm multimodal-large-language-models qwen

Python

•

Apache License 2.0

•1•66•1•0•Updated

Feb 10, 2026

Talk2Event

Public

[NeurIPS 2025 Spotlight] Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras

low-latency visual-grounding object-grounding

low-latency visual-grounding object-grounding event-camera llms vlms event-sensor vision-language-models talk2event

Python

•

Other

•0•15•4•0•Updated

Feb 1, 2026

WorldLens

Public

[CVPR 2026 Oral] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World

lidar generation reconstruction

lidar generation reconstruction autonomous-driving 3d 4d occupancy video-generation scene-understanding aigc

Python

•

Apache License 2.0

•16•208•6•0•Updated

Jan 18, 2026

3EED

Public

[NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D

gpt 3d vlm

gpt 3d vlm multi-modality llm 3d-visual-grounding mllm qwen spatial-intelligence vlm-for-3d

Python

•

Apache License 2.0

•13•209•0•0•Updated

Dec 26, 2025

Pi3DET

Public

[ICCV 2025] Perspective-Invariant 3D Object Detection

drone robotics autonomous-driving

drone robotics autonomous-driving lidar-point-cloud multimodal 3d-object-detection quadruped-robot embodied-ai 3d-scene-understanding spatial-intelligence

Python

•

MIT License

•14•174•2•0•Updated

Dec 22, 2025

U4D

Public

[CVPR 2026 Highlight] U4D: Uncertainty-Aware 4D World Modeling from LiDAR Sequences

lidar autonomous-driving 3d

lidar autonomous-driving 3d 4d lidar-point-cloud 3d-generation world-models aigc generative-ai 4d-generation

Python

•

Apache License 2.0

•1•18•0•0•Updated

Dec 20, 2025

awesome-3d-in-the-wild

Public

🌐 A Roadmap for 3D Scene Understanding in the Wild

robotics awesome-list autonomous-driving

robotics awesome-list autonomous-driving semantic-segmentation 3d 4d occupancy-prediction lidar-point-cloud panoptic-segmentation semantic-scene-completion

HTML

•

MIT License

•3•31•0•0•Updated

Dec 19, 2025

LiDARCrafter

Public

[AAAI 2026 Oral] LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences

lidar autonomous-driving 3d-generation

lidar autonomous-driving 3d-generation scene-understanding 3d-object-detection world-models aigc generative-ai 4d-generation lidar-generation

Python

•

MIT License

•13•194•4•0•Updated

Dec 12, 2025

DriveBench

Public

[ICCV 2025] Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives

autonomous-driving chatgpt vision-language-models

autonomous-driving chatgpt vision-language-models phi-3 internvl qwen2-vl driving-with-language

Python

•

Apache License 2.0

•15•236•10•0•Updated

Dec 12, 2025

Calib3D

Public

[WACV 2025 Oral] Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding

autonomous-driving uncertainty-estimation 3d-semantic-segmentation

autonomous-driving uncertainty-estimation 3d-semantic-segmentation temperature-scaling network-calibration

Python

•

Apache License 2.0

•4•72•1•0•Updated

Dec 6, 2025

RoboDepth

Public

[NeurIPS 2023] RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

autonomous-driving depth-estimation robustness

autonomous-driving depth-estimation robustness ood-detection

Python

•33•295•4•0•Updated

Dec 6, 2025

LaserMix

Public

[CVPR 2023 Highlight] LaserMix for Semi-Supervised LiDAR Semantic Segmentation

lidar semi-supervised-learning segmentation

lidar semi-supervised-learning segmentation autonomous-driving

Python

•

Apache License 2.0

•21•318•7•0•Updated

Dec 6, 2025

Robo3D

Public

[ICCV 2023] Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

autonomous-driving 3d-object-detection lidar-segmentation

autonomous-driving 3d-object-detection lidar-segmentation ood-robustness

Python

•31•371•9•0•Updated

Dec 6, 2025

RoboBEV

Public

[TPAMI 2025] Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving

autonomous-driving 3d-detection bird-eye-view

autonomous-driving 3d-detection bird-eye-view ood-generalization

Python

•37•420•6•0•Updated

Dec 6, 2025

SuperFlow

Public

[ECCV 2024] 4D Contrastive Superflows are Dense 3D Representation Learners

Python

•

Apache License 2.0

•2•52•1•0•Updated

Dec 4, 2025

.github

Public

MIT License

•1•0•0•0•Updated

Dec 2, 2025

SPIRAL

Public

[NeurIPS 2025] SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

point-cloud lidar autonomous-driving

point-cloud lidar autonomous-driving semantic-segmentation 3d aigc lidar-generation spatial-intelligence aigc3d 3d-gen

Python

•

MIT License

•3•43•1•0•Updated

Nov 30, 2025

github-profile-views-counter

Public

It counts how many times your GitHub profile has been viewed. Free cloud micro-service.

PHP

•

MIT License

•417•0•0•0•Updated

Jun 21, 2025

evalkit

Public

🌐 A curated evaluation toolkit and benchmark for state-of-the-art 3D and 4D world models

3d-generation video-generation world-models

3d-generation video-generation world-models embodied-ai aigc 4d-generation lidar-generation spatial-intelligence aigc3d occupancy-generation

Apache License 2.0

•1•2•0•0•Updated

Jun 21, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

worldbench

All

All

25 repositories

awesome-event-camera-vision

worldbench.github.io

awesome-vla-for-ad

awesome-3d-4d-world-models

awesome-ai-auto-research

awesome-spatial-intelligence

VideoLucy

Talk2Event

WorldLens

3EED

Pi3DET

U4D

awesome-3d-in-the-wild

LiDARCrafter

DriveBench

Calib3D

RoboDepth

LaserMix

Robo3D

RoboBEV

SuperFlow

.github

SPIRAL

github-profile-views-counter

evalkit

All

All

Repositories list

25 repositories