你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

Make any agent harness multimodal-native.

A curated list of papers, models, datasets, and benchmarks for unified multi-modal embedding models.

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

This repo contains the code for "VLM2Vec / MMEB" [ICLR 2025], "VLM2Vec-V2 / MMEB-V2" [TMLR 2026], and "MMEB-V3" [COLM 2026]

Official implementation of the paper: [EMNLP 2025] RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction

[SIGGRAPH 2025] SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations

[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

DeepEP: an efficient expert-parallel communication library

The ultimate training toolkit for finetuning diffusion models

Concise, consistent, and legible badges in SVG and raster format

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

a family of versatile and state-of-the-art video tokenizers.

[ICLR'25] SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

Official code for paper Semantic-aware Permutation Training

[NeurIPS 2024]OmniTokenizer: one model and one weight for image-video joint tokenization.

Writing AI Conference Papers: A Handbook for Beginners

Generative Models by Stability AI

[ICLR'24] Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.

[CSUR] A Survey on Video Diffusion Models

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". A…

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

🎓 Academic portfolio that boosts citations. AI generates pages, you own as Markdown. BibTeX auto-import, Jupyter, LaTeX, slides, visual block editor — free to host forever. 学术主页，AI 生成，Markdown 拥有 👇

[NAACL 2024] LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-text Generation?