qwen-vl 5 llava 2 multimodal 2 vision-language-model 2 awesome 1 large-multimodal-models 1 llava-next 1 multimodal-large-language-models 1 vision-language 1 visual-instruction-tuning 1 claude 1 computer-use 1 computer-using-agent 1 cua 1 gemini 1 gpt4o 1 gpt4v 1 llms 1 operator 1 playwright 1 prompt 1 prompt-engineering 1 set-of-mark 1 som 1 autodistill 1 zero-shot-object-detection 1 awesome-list 1 blip 1 clip 1 cogvlm 1 image-encoder 1 internlm 1 kosmos 1 text-encoder 1 vlm 1 deepseek 1 deepspeed 1 fine-tuning 1 llama 1 megatron-lm 1 npu 1 pretrain 1 qwen 1 finetuning 1 foundation-models 1 instruction-tuning 1 large-language-model 1