AI Agent Skills

🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and…

Real-time and accurate open-vocabulary end-to-end object detection

[EMNLP-2024] Build multimodal language agents for fast prototype and production

[NeurIPS '25] Knowledge Graph Generation from Any Text

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation

Tai-e assignments for static program analysis

MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025

Official Repo for "TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem Understanding" [ACL 2025 oral]

[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other…

Generate, edit, or batch-create SEO, marketing, social, and document images with Gemini or OpenAI through the repository-owned Growth Lab image client. Use when a page o…

小红书内容增长闭环 —— 从调研找 idea、锚定爆款骨架、填入真实产品内容、生图与合规检查，到回收 24h/48h/7d 发布结果并完成复盘。用户要求出稿、复刻、月度复盘、查看发布数据或修订内容规律时使用。

🐟 🍣 🍱 Highly-accurate & wicked fast transcript-level quantification from RNA-seq reads using selective alignment

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR 2025]