PanoFuse: Panorama-Enhanced Vision-Language-Action Learning with Decoupled Semantic-Geometric Routing

arXiv:2609.31717 · cs.CV, cs.RO, eess.IV · Submitted 2026-09-21 · Read on arXiv

cs.CV, cs.RO, eess.IV

Submitted: 2026-09-21

Updated: 2026-09-21

Comments: Code and data will be released publicly at https://xux-hnu.github.io/PanoFuse

Project page: https://xux-hnu.github.io/PanoFuse

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generalization — 14× in this paper · explained in 13 episodes
• Ablation — 12× in this paper · explained in 1 episode
• Decoupled Semantic-Geometric Routing — 5× in this paper
• Robustness — 5× in this paper · explained in 5 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Feature Extraction — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Calibration — 2× in this paper · explained in 7 episodes
• Depth Any Panoramas — 2× in this paper
• Flow Matching — 2× in this paper · explained in 7 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• VLA Models — 2× in this paper · explained in 3 episodes
• Vision-Language-Action (VLA) Models — 2× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Predictive Modeling — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Structural Constraints — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Learning Panorama-Aware VLA for Mobile Manipulation with Whole-Body Teleoperation
• DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning
• Multi-View Unified Camera Fields: Geometry-Shaped Action-Facing Representations for RGB-Only Multi-Camera VLA Policies
• AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models
• Uncovering and Mitigating Positional Blind Spots in Vision-Language-Action Models
• VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
• TGM-VLA: Task-Guided Mixup for Sampling-Efficient and Robust Robotic Manipulation
• LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imagination
• Intercepting the Future: Latent-Space Predictive World Model for Dynamic VLA Manipulation
• StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision
• GWM-VLA: Geometry-Aware Latent World Modeling for Vision-Language-Action Learning
• Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation
• VLA-LPAF: Lightweight Perspective-Adaptive Fusion for Vision-Language-Action to Enable More Unconstrained Robotic Manipulation
• OC-VLA++: Monocular Geometry-Guided Cross-View Consistency for Viewpoint-Robust Robotic Manipulation
• U-ARM : Ultra low-cost general teleoperation interface for robot manipulation
• FAST: Efficient Action Tokenization for Vision-Language-Action Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models