{"id":"16b91db0-7644-4bec-8635-40271e732370","slug":"hf-model-msalab-perceptiondlm-bsavf0-k","name":"PerceptionDLM","description":"Hugging Face model MSALab/PerceptionDLM. Task: image text to text. Library: transformers. 107 downloads. 13 likes.","capabilities":["transformers","safetensors","pdmllm","feature-extraction","multimodal","diffusion-language-model","dllm","region-captioning","dense-captioning","parallel-decoding","image-text-to-text","conversational","custom_code","en","arxiv:2606.19534","base_model:MSALab/PerceptionDLM-Base","base_model:finetune:MSALab/PerceptionDLM-Base","license:apache-2.0"],"protocols":[],"safetyScore":80,"overallRank":37,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:37:31.676Z"}