Sensing Which Modality Matters: Evidence-Gated Regularization for Robust VLA Policies

arXiv:2609.03142 · cs.RO, cs.CV, cs.LG · Submitted 2026-09-02 · Read on arXiv

cs.RO, cs.CV, cs.LG

Submitted: 2026-09-02

Updated: 2026-09-02

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

Terminology

• Entanglement — 20× in this paper · explained in 3 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Regularization — 16× in this paper · explained in 3 episodes
• Evidence-Gated Regularization — 8× in this paper
• Robustness — 8× in this paper · explained in 5 episodes
• Consistency — 7× in this paper · explained in 3 episodes
• Failure Modes — 6× in this paper · explained in 3 episodes
• Multimodal Learning — 4× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Grounding — 3× in this paper · explained in 3 episodes
• Instance Segmentation — 3× in this paper · explained in 3 episodes
• VLA Models — 2× in this paper · explained in 3 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptive Expert Routing — 1× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Current Vision-Language-Action — 1× in this paper
• Distribution Shift — 1× in this paper · explained in 5 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Mitsubishi Electric Research Laboratories — 1× in this paper
• Multimodal Fusion — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• RT-1: Robotics Transformer for Real-World Control at Scale
• Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges
• OpenVLA: An Open-Source Vision-Language-Action Model
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• RobustVLA: On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
• TacVLA: Contact-Aware Tactile Fusion for Robust Vision-Language-Action Manipulation
• Tactile-VLA: Unlocking Vision-Language-Action Model's Physical Knowledge for Tactile Generalization
• Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
• When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs
• What Makes Training Multi-Modal Classification Networks Hard?
• Balanced Multimodal Learning via On-the-fly Gradient Modulation
• On Uni-Modal Feature Learning in Supervised Multi-Modal Learning
• Deep Multimodal Learning with Missing Modality: A Survey
• Play to the Score: Stage-Guided Dynamic Multi-Sensory Fusion for Robotic Manipulation
• FocusVLA: Focused Visual Utilization for Vision-Language-Action Models
• GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
• LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policies
• Openpi Comet: Competition Solution For 2025 BEHAVIOR Challenge

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving