Awesome Robotics Manipulation · full_paper

HMVLA: Hyperbolic Multimodal Fusion for Vision-Language-Action Models

ICASSP 2026 · 2026-01-28 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Non-LLM-based Vision Language Action Models

VLA语言条件机器人学习
新标签打开 AlphaXiv新标签打开 Paper
HMVLA: Hyperbolic Multimodal Fusion for Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）