arXiv AI
Think Only When Needed: Prompt-Authority Control for Selective Slow-Path Intervention in Vision-Language-Action Manipulation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 2
When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models
The paper investigates a specific failure mode in vision‑language‑action models, termed instruction‑action binding, where models respond to language and vision separately but fail to combine them to select the correct action under counterfactual changes. Through behavioral analyses of fine‑tuned policies, the authors show that failed rollouts often preserve source behavior or switch to other demonstrated tasks, indicating that language is not ignored but mis‑bound. They propose Equivariant Counterfactual Training (ECT), which supplies counterfactual demonstrations and a paired loss to enforce correct action selection, achieving significant performance gains across simulated and real‑world benchmarks.
arXiv Machine Learning
Oct 8
Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models
arXiv:2610.10526v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness of the vision-langua...
arXiv Machine Learning
Oct 8
CARE: Certifying Acceleration for Vision-Language-Action Inference
The paper introduces CARE, a method for certifying accelerated inference in vision‑language‑action models. CARE uses paired rollouts on a calibration set to guarantee that the risk of acceleration‑induced failure stays below a user‑specified budget, selecting the fastest certified accelerator or falling back to the reference policy. Experiments on LIBERO suites show that CARE achieves 9.0–10.8× speedups while preserving at least 85.8% of reference‑solved episodes with 95% confidence, and it outperforms non‑guaranteed selectors in both budget adherence and rollout efficiency.
Hugging Face Trending Papers
Oct 6
CARE: Certifying Acceleration for Vision-Language-Action Inference
While vision-language-action (VLA) models have advanced rapidly, running them at every control step remains expensive. Prior work accelerates VLA inference using techniques like action chunking and vi...
arXiv AI
Aug 26
When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows
Large language model agents coordinate tasks via multi‑role, multi‑stage workflows that transform upstream state into intermediate artifacts such as summaries and plans. The study shows that when these artifacts are transformed—through compression, plan assimilation, or other handoff methods—the strict action‑binding constraints on upstream state can be weakened, turning mandatory requirements into optional information. In 1,296 synthetic episodes, direct handoff preserved all safety blockers, whereas transformed handoffs frequently deactivated or forbidden actions, but restoring full state fields or applying downstream verification can recover preservation.
arXiv Computation and Language
Sep 22
Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models
arXiv:2609.22243v1 Announce Type: new Abstract: Input-conditioned neural interventions raise a runtime question: what persists when one behavioral specification admits multiple actions whose validity...