Safety Filtering

Follow this topic Ask about this topic

Momentum

24 papers in the last four weeks, up 118% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 111

All topics

parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learning
May 15, 2026Yijun Lu, Zilei Yang, Yuyin MaReinforcement Learning Control Barrier Functions
Selective Safety Steering via Value-Filtered Decoding
May 14, 2026Bat-Sheva Einbinder, Hen Davidov, Yee Whye Teh +2Language Model Decoding Language Model Steering
Department of Electrical and Computer Engineering, Technion IIT, Israel · Department of Statistics, University of Oxford, Oxford, UK · OATML, Department of Computer Science, University of Oxford, Oxford, UK +1
AERIC: Anticipatory Hidden-State Monitoring for Implicit Harmful Dialogue
May 13, 2026Jihyung Park, Saleh Afroogh, Junfeng JiaoLanguage Model Safety Evaluation LLM Guardrails
The University of Texas at Austin
Distributionally Robust Safety Under Arbitrary Uncertainties: A Safety Filtering Approach
May 13, 2026Daniel M. Cherenson, Haejoon Lee, Taekyung Kim +1Safety-Critical Control Distributionally Robust Optimization
Department of Robotics, University of Michigan, Ann Arbor, MI, USA
Before the Last Token: Diagnosing Final-Token Safety Probe Failures
May 12, 2026Shravan DodaLanguage Model Safety Evaluation Safety Filtering
Kipo AI
Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers
May 11, 2026Nikita Kezins, Urbas Ekka, Pascal Berrang +1Neural Network Verification Language Model Safety Evaluation
Delft University of Technology · University of Birmingham & Zeroth Research
GLiGuard: Schema-Conditioned Classification for LLM Safeguard
May 8, 2026Urchade Zaratiana, Mary Newhauser, George Hurn-Maloney +1LLM Guardrails Text Classification
Fastino Labs
A Closed-Form Dual-Barrier CBF Safety Filter for Holonomic Robots on Incrementally Built Occupancy Grid Maps
May 6, 2026Himanshu Paudel, Basanta Joshi, Dhirendra Raj Madai +3Safety-Critical Control Control Barrier Functions
AgentTrust: Runtime Safety Evaluation and Interception for AI Agent Tool Use
May 6, 2026Chenglin YangAI Agent Security AI Agent Security Benchmarks
Independent Researcher
Online Safety Filter for Deformable Object Manipulation with Horizon Agnostic Neural Operators
May 1, 2026Jiaxing Li, Hanjiang Hu, Zhuoyuan Wang +2Safety-Critical Control Deformable Object Manipulation
Carnegie Mellon University, Pittsburgh, PA, USA
CRC-Screen: Certified DNA-Synthesis Hazard Screening Under Taxonomic Shift
Apr 30, 2026Najmul HasanDistribution Shift Toxicity Detection
University of North Carolina at Pembroke.
Enforcing Benign Trajectories: A Behavioral Firewall for Structured-Workflow AI Agents
Apr 29, 2026Hung DangLLM Agent Security AI Agent Monitoring
Van Lang University, Ho Chi Minh City, Vietnam
Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty
Apr 28, 2026Artur Eisele, Bernd Frauenknecht, Friedrich Solowjow +1Robot Safety Safety Filtering
Institute for Data Science in Mechanical Engineering, RWTH Aachen University, Aachen, Germany
Full-Body Dynamic Safety for Robot Manipulators: 3D Poisson Safety Functions for CBF-Based Safety Filters
Apr 23, 2026Meg Wilkinson, Gilbert Bahati, Ryan M. Bena +3Control Barrier Functions Robot Safety
Computing and Mathematical Sciences, California Institute of Technology. · Mechanical and Civil Engineering, California Institute of Technology.
Safe Control using Learned Safety Filters and Adaptive Conformal Inference
Apr 20, 2026Sacha Huriot, Ihab Tabbara, Hussein SibaiSafety-Critical Control Conformal Prediction
Computer Science & Engineering Washington University in St. Louis
Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives
Apr 18, 2026Daeyeon SonMCP Security AI Agent Security
Independent Researcher · Republic of Korea
ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems
Apr 13, 2026Daeyeon SonLLM Inference LLM Guardrails
Independent Researcher Republic of Korea
Hardening x402: PII-Safe Agentic Payments via Pre-Execution Metadata Filtering
Apr 13, 2026Vladimir StantchevAI Agent Security Safety Filtering
SRH University Heidelberg, Germany · PRESIDIO Group, Sofia, Bulgaria
PC-Diffuser: Path-Consistent Capsule CBF Safety Filtering for Diffusion-Based Trajectory Planner
Mar 11, 2026Eugene Ku, Yiwei LyuConstrained Motion Planning Trajectory Generation
Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA
CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions
Oct 16, 2025Lizhi Yang, Blake Werner, Massimiliano de Sa +1RL for Robotics Control Barrier Functions
Caltech MCE
Layered Safety: Enhancing Autonomous Collision Avoidance via Multistage CBF Safety Filters
Date pendingErina Yamaguchi, Ryan M. Bena, Gilbert Bahati +1Safety-Critical Control Control Barrier Functions
Department of Mechanical and Civil Engineering and the Department of Aerospace, Caltech, Pasadena, CA 91125, USA

May 15, 2026, cs.LGJ/K move · Enter open · S save

parallelcbf: A composable safety-filter and auditability framework for tensor-parallel reinforcement learning

Yijun Lu, Zilei Yang, Yuyin Ma

Reinforcement Learning Control Barrier Functions Constrained RL Safety Filtering ML Reproducibility Safe RL

Open paper AskPDF arXiv

While Isaac Lab provides massive parallel UAV simulation, OmniSafe and safe-control-gym provide constrained-RL benchmarks, and CBFKit provides control-barrier-function synthesis tooling, no existing framework unifies these capabilities for end-to-end safety-constrained training. ParallelCBF is the first framework to unify (i)~tensor-parallel UAV environments, (ii)~hard-gate CBF safety filters, (iii)sharded BC-to-RL pipelines, and (iv)first-class operational auditability -- pre-registration, watchdog registries, failure forensics, and dataset audits as composable APIs rather than user-implemented scripts. We release ParallelCBF v0.1.0 under Apache2.0 with a four-layer composable API, a CPU PyTorch reference implementation of a dual-barrier (squared / linear-predictive) CBF, property-based safety invariance tests across vectorized batch sizes that complete in 1.67s for the full 39-test suite, and a 31{,}415-episode behavior-cloning collection campaign whose curriculum mix, per-bucket yields, and dataset SHA-256 are auditable through the framework's own \texttt{ops} primitives. We report a representative end-to-end pipeline execution in which the framework's auditability layer halted a downstream training stage that did not meet pre-registered convergence criteria, preventing silent propagation of a degraded checkpoint -- an architectural property we argue is necessary, not merely useful, for reproducible empirical robotics research. The framework is installable via \texttt{pip install parallelcbf}; source and release artifacts are available at https://github.com/xiaoyang-123-cell/ParallelCBF.

Momentum

Related topics

Latest papers 111