llm

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

📄 Trending Paper (36⬆️): Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDL...

Source: HuggingFace_Papers