zachytong

diffusion-forcing

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

ml-4m

4M: Massively Multimodal Masked Modeling

Forge_VFM4AD

A comprehensive survey of forging vision foundation models for autonomous driving, including challenges, methodologies, and opportunities.

LCSim

LCSim: A Large-Scale Controllable Traffic Simulator

CAT-DM

CAT-DM: Controllable Accelerated Virtual Try-on with Diffusion Model

MOFA-Video

[ECCV 2024] MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model.

The_Prompt_Report

DiffSynth-Studio

Enjoy the magic of Diffusion models!

awesome-end-to-end-autonomous-driving

A curated list of awesome End-to-End Autonomous Driving resources (continually updated)

Decouple-Traj

Official Code for "Fully Decoupling Trajectory and Scene Encoding for Lightweight Heatmap-oriented Trajectory Prediction"

LLM101n

LLM101n: Let's build a Storyteller

plant

[CoRL'22] PlanT: Explainable Planning Transformers via Object-Level Representations

SMART

[NeurIPS 2024] SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction

ml-stable-diffusion

Stable Diffusion with Core ML on Apple Silicon

map4d

Photo-realistic mapping of dynamic urban areas

Hydra-MDP

ctrl-sim

Official repository for "CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning"

SimGen

Simulator-conditioned Driving Scene Generation

TrafficBotsV1.5

TrafficBots V1.5: TrafficBots + HPTR. 3rd place solution for Waymo Open Sim Agent Challenge 2024.

Hydra-MDP

The official repository of Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation

LAW

Enhancing End-to-End Autonomous Driving with Latent World Model

StreamSpeech

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

scepter

SCEPTER is an open-source framework used for training, fine-tuning, and inference with generative models.

SparseDrive

SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation

RAG-Driver

A Multi-Modal Large Language Model with Retrieval-augmented In-context Learning capacity designed for generalisable and explainable end-to-end driving

AD-H

streamv2v

Official Pytorch implementation of StreamV2V.

P-MapNet

Received by RAL

3D-GCL

CASD

Official Implementation for "Cross Attention Based Style Distribution for Controllable Person Image Synthesis" (ECCV2022))