Post
3423
🚀 Introducing PerceptionDLM — the first multimodal diffusion LLM for parallel region perception!
Most MLLMs are autoregressive, so captioning N regions costs N sequential passes. PerceptionDLM instead describes ALL masked regions in a single denoising process. 🧩
✨ Highlights
• ⚡ Up to 3.4× faster on dense multi-region captioning, with stable per-image latency
• 🏆 PerceptionDLM-Base beats LLaDA-V on 15/16 multimodal benchmarks (new SOTA among open diffusion VLMs)
• 📊 New benchmark: ParaDLC-Bench — jointly evaluates caption quality AND inference efficiency
• 🔓 Code, models & benchmark all open-sourced
🤖 Models
MSALab/PerceptionDLM-Base
MSALab/PerceptionDLM
📊 Benchmark
MSALab/ParaDLC-Bench
📄 Paper: PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models (2606.19534)
💻 Code: https://github.com/MSALab-PKU/PerceptionDLM
Diffusion LLMs aren't just for text — they unlock efficient, parallel visual perception. 👁️✨
#multimodal #diffusion #VLM #perception
Most MLLMs are autoregressive, so captioning N regions costs N sequential passes. PerceptionDLM instead describes ALL masked regions in a single denoising process. 🧩
✨ Highlights
• ⚡ Up to 3.4× faster on dense multi-region captioning, with stable per-image latency
• 🏆 PerceptionDLM-Base beats LLaDA-V on 15/16 multimodal benchmarks (new SOTA among open diffusion VLMs)
• 📊 New benchmark: ParaDLC-Bench — jointly evaluates caption quality AND inference efficiency
• 🔓 Code, models & benchmark all open-sourced
🤖 Models
MSALab/PerceptionDLM-Base
MSALab/PerceptionDLM
📊 Benchmark
MSALab/ParaDLC-Bench
📄 Paper: PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models (2606.19534)
💻 Code: https://github.com/MSALab-PKU/PerceptionDLM
Diffusion LLMs aren't just for text — they unlock efficient, parallel visual perception. 👁️✨
#multimodal #diffusion #VLM #perception