arXiv Machine Learning
Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 26
Do VLAs Know They Will Fail? Interpretable Success and Failure Patterns in Physical AI Systems
The paper investigates Vision‑Language‑Action (VLA) models used as robot policies, showing that sparse autoencoder (SAE) representations of OpenVLA activations can predict task failure before an unrecoverable state is reached. It identifies specific SAE features whose strong activations correlate with stages of success or failure, and maps these to recurring behavioral patterns by locating temporal intervals of significant activation change. A VLM‑based interpretation pipeline is then developed to generate behavioral descriptions of these patterns, with validation on held‑out intervals.
arXiv AI
Jun 2
Beyond Task Success: Behavioral and Representational Diagnostics for WAM and VLA
arXiv:2606. 01095v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies and World-Action Models (WAM) represent two increasingly important paradigms for robotic manipulation.
arXiv Machine Learning
Oct 19
When Plans Change, Remember: Replanning-Guided Visual Memory for Vision-Language-Action Models
The paper introduces RePlanMem-VLA, a selective visual memory system for Vision‑Language‑Action models that uses a policy’s own plan revisions as an online memory‑write signal. By detecting unusually large disagreements between temporally aligned action predictions, the method identifies task‑relevant events and updates a bounded visual memory while suppressing redundant frames. Experiments on MIKASA‑Robo‑VLA tasks and real‑robot replay data show that RePlanMem‑VLA retains essential observations in every episode and achieves high ROC‑AUC scores for event detection.
arXiv Computer Vision
Oct 12
Dual-Stream Memory for Vision-Language-Action Policies
The paper introduces a dual‑stream memory architecture for vision‑language‑action policies, separating a task‑agnostic temporal compressor from a task‑conditioned visual retriever. The temporal compressor uses a Gated DeltaNet to condense history into a single token, while the retriever keeps frames above a relevance threshold and fuses them into spatial tokens. Evaluated on sixteen RoboMME tasks and four real‑robot tasks, the combined model outperforms the FrameSamp+Modul baseline, achieving higher mean success rates and notable gains on tasks requiring execution‑stage discrimination.
arXiv AI
Jun 30
SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance
arXiv:2606. 30113v1 Announce Type: cross Abstract: Discrete action tokenization provides a compact interface for autoregressive VLA policies, but accurately recovering continuous robot actions from discrete codes remains challenging.
arXiv Computer Vision
Oct 7
VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models
arXiv:2610.08133v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong robotic manipulation performance but incur high computational costs from processing long token seq...