A suite of image and video neural tokenizers

Standard Open Arm 100

[EMNLP 2018] PyTorch code for TVQA: Localized, Compositional Video Question Answering

本项目提供了基于910B的huggingface LLM模型的Tensor Parallel(TP)部署教程，同时也可以作为一份极简的TP学习代码。

Official implementation of "ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis"

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

DUSt3R: Geometric 3D Vision Made Easy

Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"

PS4 emulator for Windows,Linux,MacOS

[NeurIPS'24 Spotlight] EVE: Encoder-Free Vision-Language Models

Must-read Papers on LLM Agents.

SEED-Story: Multimodal Long Story Generation with Large Language Model

DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception

Mixture of Attention Heads

AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目

Multicultural Avatar Generator in JavaScript

Avatar generation package for Python

[ECCV 2024] TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes

Code of SIGGRAPH 2023 Conference paper: StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video

[CVPR 2024 & NeurIPS 2024] EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI