Autonomous AI development loop for Claude Code with intelligent exit detection

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code and OpenCode.

The code will be released publicly upon publication.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

[MICCAI'25] A training-free solver for few-shot adaptation of medical VLMs. Addressing imbalanced and validation-free realistic scenarios.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

A generative world for general-purpose robotics & embodied AI learning.

A python library for self-supervised learning on images.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

This repo contains the official implementation of ICLR 2024 paper "Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video""

PyTorch Implementation of Learning to Prompt (L2P) for Continual Learning @ CVPR22

Kyung Hee University Vision and Learning Reading Group

Code for Video Pose Distillation