paper-with-me

홈 › Papers

CT-VAM: A Cerebello-Thalamic-Inspired Vision-Action Model for Efficient Visuomotor Control

2026-06-08 · Jiacheng Li, Yize Guo, Jiabin Guo, Qingchen Liu, Jiahu Qin arxiv

Vision-language-action models have shown strong promise for robot manipulation, yet raw language is primarily needed to specify task intent rather than to be repeatedly processed during high-frequency low-level execution. Motivated by this separation, we propose a cerebello-thalamic-inspired vision-action model (CT-VAM) for efficient task-conditioned visuomotor control. CT-VAM acts as a compact local execution policy that predicts action chunks from dualview visual observations, proprioception, and a lightweight task condition, potentially enabling a practical cloud-edge paradigm in which high-level semantic reasoning can be handled by large models while fast closed-loop control runs on local hardware. To fuse heterogeneous inputs effectively, CT-VAM introduces TARS (Thalamic Action Routing Stream), a stream-separated conditional attention decoder that independently routes action, visual and task streams, preventing dense sensory tokens from overwhelming compact task-relevant conditions. With only 68M parameters, CT-VAM achieves LIBERO success rates competitive with substantially larger VLA models, while reducing inference latency. Together with flow-consistent inpainting for asynchronous chunk execution, CT-VAM supports high-frequency control and demonstrates robust realworld deployment on resource-constrained robotic platforms.

📄 PDF Abstract BibTeX arXiv:2606.09572

Code (0)

등록된 구현이 없습니다.

Tasks

Robot Manipulation

Similar Papers 제목 키워드 기반

How Fly Neural Perception Mechanisms Enhance Visuomotor Control of Micro Robots

2025-09-17 · Renyuan Liu, Haoting Zhou, Chuankai Fang, Qinbing Fu arxiv

Anyone who has tried to swat a fly has likely been frustrated by its remarkable agility.This ability stems from its visual neural perception system, particularly the collision-selective neurons within its small brain.For…

FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model

2026-03-11 · Xiaoxu Xu, Hao Li, Jinhui Ye, Yilun Chen 외 arxiv

Predictive foresight is important to intelligent embodied agents. Since the motor execution of a robot is intrinsically constrained by its visual perception of environmental geometry, effectively anticipating the future …

Learning Predictive Visuomotor Coordination

2025-03-30 · Wenqi Jia, Bolin Lai, Miao Liu, Danfei Xu 외

Understanding and predicting human visuomotor coordination is crucial for applications in robotics, human-computer interaction, and assistive technologies. This work introduces a forecasting-based task for visuomotor mod…

CTNN: Corticothalamic-inspired neural network

2019-10-28 · Leendert A Remmelzwaal, Amit K Mishra, George F R Ellis

Sensory predictions by the brain in all modalities take place as a result of bottom-up and top-down connections both in the neocortex and between the neocortex and the thalamus. The bottom-up connections in the cortex ar…

Introspective Visuomotor Control: Exploiting Uncertainty in Deep Visuomotor Control for Failure Recovery

2021-03-22 · Chia-Man Hung, Li Sun, Yizhe Wu, Ioannis Havoutis 외

End-to-end visuomotor control is emerging as a compelling solution for robot manipulation tasks. However, imitation learning-based visuomotor control approaches tend to suffer from a common limitation, lacking the abilit…

Imitation LearningRobot Manipulation