Wang-Xiaodong1899/Long-DWM
🌟[AAAI 2026] The official repo for "LongDWM: Cross-Granularity Distillation for Building a Long-Term Driving World Model"
This project helps researchers and developers in autonomous driving build models that can predict how a self-driving car will behave and what its surroundings will look like far into the future. It takes in existing driving data and model architectures, and outputs a more efficient model capable of making long-term predictions for actions and video frames. Autonomous vehicle engineers and AI researchers focused on predictive control or simulation for self-driving systems would use this.
No commits in the last 6 months.
Use this if you are developing or researching advanced autonomous driving systems and need to create world models that can reliably predict future driving scenarios and actions over an extended period.
Not ideal if you are looking for an off-the-shelf, ready-to-deploy solution for immediate use in a production self-driving car.
Stars
11
Forks
—
Language
—
License
—
Category
Last pushed
Jun 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Wang-Xiaodong1899/Long-DWM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators