lmm

Eagle: Frontier Vision-Language Models with Data-Centric Strategies

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

LLaVA-Interactive-Demo

Official code for Paper "Mantis: Multi-Image Instruction Tuning" [TMLR 2024 Best Paper]

😎 curated list of awesome LMM hallucinations papers, methods & resources.

An Interactive Game-based Vision Planning benchmark