task · first seen 8 Oct 2026
multimodal large language model perception
Also: MLLM perception
Using multimodal language models to output localization results such as bounding boxes and masks.
Mentions per week
PapersCodeDiscussion
Earliest sources
- DVD: Dynamic Vector Decoding for Efficient MLLM-based PerceptionPapers · 8 Oct 2026 · Jinghua Hou, Zhe Liu, Hengshuang Zhao
Latest sources
- DVD: Dynamic Vector Decoding for Efficient MLLM-based PerceptionPapers · 8 Oct 2026 · Jinghua Hou, Zhe Liu, Hengshuang Zhao