VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909750309945344 |
|---|---|
| author | Tang, Zuojin Hu, Bin Zhao, Chenyang Ma, De Pan, Gang Liu, Bin |
| author_facet | Tang, Zuojin Hu, Bin Zhao, Chenyang Ma, De Pan, Gang Liu, Bin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_15885 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making Tang, Zuojin Hu, Bin Zhao, Chenyang Ma, De Pan, Gang Liu, Bin Artificial Intelligence 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. |
| title | VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Making |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2410.15885 |