BOKBO is the first conformal abstention method for K-sample VLA policies that supplies finite-sample distribution-free guarantees on executed violation rates, with global and Mondrian per-task variants.
Do what you say: Steering vision-language-action models via runtime reasoning-action alignment verification
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 9verdicts
UNVERDICTED 9roles
background 2polarities
background 2representative citing papers
Introduces ISS and NMR as interventional metrics to diagnose causal misalignment in VLA policies and link it to generalization performance.
UPS framework uses conformal prediction to calibrate VLM verifiers for choosing between high-confidence action execution, natural language task queries, or policy interventions, then applies residual learning from interventions to continually improve the base policy with minimal feedback.
A search-and-distill framework with conformalized improvement head produces a language feedback policy that boosts frozen VLA performance by 24.7% in simulation and 65% on hardware while guaranteeing harmlessness on perturbations.
ERVLA trains on a 978k-trajectory embodied CoT corpus using reasoning as supervision with dropout, then predicts actions without CoT at test time, reaching 86.9% on LIBERO-Plus and 53.2% on VLABench.
SV-VLA uses infrequent heavy VLA planning of action chunks plus a lightweight closed-loop verifier to achieve both efficiency and robustness in dynamic robot control.
R&B-EnCoRe uses self-supervised importance-weighted variational inference to distill action-predictive reasoning datasets that improve VLA performance on manipulation, navigation, and driving tasks without external verifiers.
VLESA introduces a goal-conditioned safety Q-filter trained via GRPO on egocentric video plus an intent-action predictor, achieving higher intervention accuracy and over 41 percentage points better action safety on the ASIMOV-2.0 benchmark.
TC-WM converts foundation-model visual embeddings into parsimonious task-sufficient world model latents via linear projection, contrastive physical-state alignment, and embedding reconstruction, with a theoretical identification guarantee.
citing papers explorer
-
BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies
BOKBO is the first conformal abstention method for K-sample VLA policies that supplies finite-sample distribution-free guarantees on executed violation rates, with global and Mondrian per-task variants.
-
Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models
Introduces ISS and NMR as interventional metrics to diagnose causal misalignment in VLA policies and link it to generalization performance.
-
When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering
UPS framework uses conformal prediction to calibrate VLM verifiers for choosing between high-confidence action execution, natural language task queries, or policy interventions, then applies residual learning from interventions to continually improve the base policy with minimal feedback.
-
Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering
A search-and-distill framework with conformalized improvement head produces a language feedback policy that boosts frozen VLA performance by 24.7% in simulation and 65% on hardware while guaranteeing harmlessness on perturbations.
-
Revisiting Embodied Chain-of-Thought for Generalizable Robot Manipulation
ERVLA trains on a 978k-trajectory embodied CoT corpus using reasoning as supervision with dropout, then predicts actions without CoT at test time, reaching 86.9% on LIBERO-Plus and 53.2% on VLABench.
-
Open-Loop Planning, Closed-Loop Verification: Speculative Verification for VLA
SV-VLA uses infrequent heavy VLA planning of action chunks plus a lightweight closed-loop verifier to achieve both efficiency and robustness in dynamic robot control.
-
Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning
R&B-EnCoRe uses self-supervised importance-weighted variational inference to distill action-predictive reasoning datasets that improve VLA performance on manipulation, navigation, and driving tasks without external verifiers.
-
VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring
VLESA introduces a goal-conditioned safety Q-filter trained via GRPO on egocentric video plus an intent-action predictor, achieving higher intervention accuracy and over 41 percentage points better action safety on the ASIMOV-2.0 benchmark.
-
Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations
TC-WM converts foundation-model visual embeddings into parsimonious task-sufficient world model latents via linear projection, contrastive physical-state alignment, and embedding reconstruction, with a theoretical identification guarantee.