#mllm
3 briefs tagged #mllm.
Research
PaDoc proposes parallel decoding for document parsing
The arXiv paper describes a layout-grounded MLLM parser that decodes document regions concurrently.
arXiv cs.AI+1 outlet·Aug 7
Research
LoT improves KB-VQA accuracy without model training
The framework highlights image regions and text evidence before answer generation.
arXiv cs.AI+1 outlet·Aug 7
Research
Researchers propose STAMPlus for MLLM segmentation
Structured All-Mask Prediction aims to preserve dialogue ability while speeding dense mask output.
HF Daily Papers·Aug 3