VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making
This work addresses a fundamental bottleneck in multimodal and multitask learning for applications like autonomous driving, enabling more efficient parallel processing, though it is incremental as it builds upon existing large pretrained models.
The paper tackles the limitation of multi-input single-output (MISO) models in multi-input multi-output (MIMO) scenarios, where parallel task execution is hindered by mutual exclusion effects, and introduces MIMO-VLA (VLASCD), a unified training framework that enables concurrent multi-task outputs, such as simultaneous dialogue generation and decision-making, and demonstrates substantial performance improvements over state-of-the-art models on the CARLA autonomous driving platform.
Recent large pretrained models such as LLMs (e.g., GPT series) and VLAs (e.g., OpenVLA) have achieved notable progress on multimodal tasks, yet they are built upon a multi-input single-output (MISO) paradigm. We show that this paradigm fundamentally limits performance in multi-input multi-output (MIMO) scenarios, where parallel task execution is required. In MISO architectures, tasks compete for a shared output channel, creating mutual exclusion effects that cause unbalanced optimization and degraded performance. To address this gap, we introduce MIMO-VLA (VLASCD), a unified training framework that enables concurrent multi-task outputs, exemplified by simultaneous dialogue generation and decision-making. Inspired by human cognition, MIMO-VLA eliminates interference between tasks and supports efficient parallel processing. Experiments on the CARLA autonomous driving platform demonstrate that MIMO-VLA substantially outperforms state-of-the-art MISO-based LLMs, reinforcement learning models, and VLAs in MIMO settings, establishing a new direction for multimodal and multitask learning.