Sparse Feature Unlearning Reduces State Hallucination in Vision-Language-Action Models
Jiho Lee · hf · 2026-10-20
Researchers identify a failure mode called state hallucination in vision-language-action (VLA) models and propose sparse feature policy unlearning: by unlearning sparse features, the approach reduces hallucination-driven failure behaviors while preserving the model's manipulation skills.
More from Embodied
- New "Embodied Olympics" Benchmark: GPT and Claude Agents Play Soccer and Ping Pong — ManlingLi_ · 2026-10-20
- SF founders go deep in Shenzhen's Huaqiangbei building BCIs and wearables — LoganGrasby · 2026-10-20
- MicroAGI trains a handyman model with tens of thousands of hours of video — isnit0 · 2026-10-20
- Uber-linked group secretly campaigns to ban robotaxis in Washington D.C. — gabriberton · 2026-10-20
- Meta admits smart glasses were recording conversations without the wake word — Resident-Fall4351 · 2026-10-20
- Wayve demos its Fiat 500e autonomous prototype on Turin's iconic Lingotto rooftop track — alexgkendall · 2026-10-20