Wang-Xiaodong1899

OpenVoice

Instant voice cloning by MyShell.

trl

Train transformer language models with reinforcement learning.

waymo-open-dataset

Waymo Open Dataset

ShareGPT4Video

An official implementation of ShareGPT4Video: Improving Video Understanding and Generation with Better Captions

Bunny

A family of lightweight multimodal models.

Samba

Official implementation of "Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling"

LLaMA-VID

Official Implementation for LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

SimPO

SimPO: Simple Preference Optimization with a Reference-Free Reward

OccWorld

[ECCV 2024] 3D World Model for Autonomous Driving

LLaVA-RLHF

Aligning LMMs with Factually Augmented RLHF

4DGen

"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency", Yuyang Yin*, Dejia Xu*, Zhangyang Wang, Yao Zhao, Yunchao Wei

NVS_Solver

Source code of paper "NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer"

OmniTokenizer

OmniTokenizer: one model and one weight for image-video joint tokenization.

EthicalTrajectoryPlanning

An Ethical Trajectory Planning Algorithm for Autonomous Vehicles

Diffusion4D

"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models", Hanwen Liang*, Yuyang Yin*, Dejia Xu, Hanxue Liang, Zhangyang Wang, Konstantinos N. Plataniotis, Yao Zhao, Yunchao Wei

titok-pytorch

Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"

RLAIF-V

RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness

VQASynth

Compose multimodal datasets 🎹

Recap-DataComp-1B

This is the official repository of our paper "What If We Recaption Billions of Web Images with LLaMA-3 ?"

richhf-18k

RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with the file name of the associated labeled images (no urls or images are included in this dataset).

VLFeedback

LAW

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

HA-DPO

Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

Learning-Naturalistic-Driving-Environment

This repo contains the code for paper "Learning naturalistic driving environment with statistical realism"

CSR

[Arxiv] Calibrated Self-Rewarding Vision Language Models

MEFT

LLMBind

LLMBind: A Unified Modality-Task Integration Framework

TI2V-Zero

Text-conditioned image-to-video generation based on diffusion models.

LLMmed

Large Language Models Streamline Automated Machine Learning for Clinical Studies

visiPAM

Code for the paper 'Zero-shot visual reasoning through probabilistic analogical mapping'