DVD: Dynamic Vector Decoding for Efficient MLLM-based Perception
arXiv:2610.12266v1 Announce Type: cross Abstract: Multimodal large language models have made remarkable progress in bridging vision and language, facilitating various perception tasks essential for human-machine interaction, robotics, and autonomous driving. However, existing MLLM-based perception methods predominantly rely on text-based coordinate representation, which suffers from excessive token overhead, or fixed-range quantization, which suffers from range and precision constraints, especi…