AstraQ-VL is a minimal, efficient astronomy Vision-Language Model following the LLaVA architecture. Stage 1 trains only a lightweight MLP connector to align frozen CLIP vision features with a frozen LLM. Stage 2 then warm-starts that connector and fine-tunes the LLM with LoRA adapters on instruction (QA) data.
astronomy transformers pytorch remote-sensing image-captioning lora clip earth-observation visual-question-answering peft faiss huggingface medical-vqa instruction-tuning vision-language-model llava retrieval-augmented-generation qwen multimodal-ai vrsbench
-
Updated
Aug 13, 2026 - Python