FIDeL detects failures in imitation learning by building compact nominal representations via optimal transport, applying conformal prediction thresholds, and using VLMs for semantic filtering, outperforming baselines by 5.3% AUROC and 17.38% accuracy on the new BotFails dataset.
SafeLLM-controlledrobotswithformalguarantees via reachability analysis
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
A multi-level taxonomy of risks, attacks, and defenses across the full embodied AI pipeline, synthesizing 500+ papers and flagging overlooked failure modes.
A framework integrates user language and probabilistic environment estimates into adaptive safety certificates that guarantee long-term safety for stochastic systems via probabilistic invariance.
A Lingua Franca reactor-based method is proposed to address nondeterminism in agentic AI for human-in-the-loop cyber-physical systems such as driving coaches.
The paper proposes a bidirectional continuum between LLMs and control systems, covering LLM-assisted controller design, control-based LLM steering, and state-space modeling of LLMs.
citing papers explorer
-
Failure Identification in Imitation Learning Via Statistical and Semantic Filtering
FIDeL detects failures in imitation learning by building compact nominal representations via optimal transport, applying conformal prediction thresholds, and using VLMs for semantic filtering, outperforming baselines by 5.3% AUROC and 17.38% accuracy on the new BotFails dataset.
-
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
A multi-level taxonomy of risks, attacks, and defenses across the full embodied AI pipeline, synthesizing 500+ papers and flagging overlooked failure modes.
-
Online Adaptive Probabilistic Safety Certificate with Language Guidance
A framework integrates user language and probabilistic environment estimates into adaptive safety certificates that guarantee long-term safety for stochastic systems via probabilistic invariance.
-
Agentic Driving Coach: Robustness and Determinism of Agentic AI-Powered Human-in-the-Loop Cyber-Physical Systems
A Lingua Franca reactor-based method is proposed to address nondeterminism in agentic AI for human-in-the-loop cyber-physical systems such as driving coaches.
-
When control meets large language models: From words to dynamics
The paper proposes a bidirectional continuum between LLMs and control systems, covering LLM-assisted controller design, control-based LLM steering, and state-space modeling of LLMs.