Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models

arXiv:2610.09496 · cs.RO, cs.AI, cs.LG · Submitted 2026-10-07 · Read on arXiv

cs.RO, cs.AI, cs.LG

Submitted: 2026-10-07

Updated: 2026-10-07

Terminology

• Hallucination — 124× in this paper · explained in 3 episodes
• Feature Selection — 7× in this paper · explained in 4 episodes
• Generalization — 4× in this paper · explained in 13 episodes
• Machine Unlearning — 4× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Foundation Models — 2× in this paper · explained in 7 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Latent Representation — 2× in this paper · explained in 2 episodes
• Sparse Autoencoders (SAEs) — 2× in this paper · explained in 3 episodes
• Sparsity — 2× in this paper · explained in 4 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Action Flow — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptive Reasoning — 1× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Hallucination Mitigation — 1× in this paper · explained in 2 episodes
• Latent Representations — 1× in this paper · explained in 3 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Steering — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

Sources

• Gemini Robotics: Bringing AI into the Physical World
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
• LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization
• Experiences from Benchmarking Vision-Language-Action Models for Robotic Manipulation
• FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models
• Action Hallucination in Generative Vision-Language-Action Models
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination
• TOFU: A Task of Fictitious Unlearning for LLMs
• BatchTopK Sparse Autoencoders
• k-Sparse Autoencoders

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