RLVR maintains safety while improving reasoning capabilities in LLMs.
problem Safety-capability tradeoff in fine-tuning LLMs.
method Reinforcement Learning with Verifiable Rewards (RLVR) and theoretical analysis.
result RLVR can enhance reasoning while maintaining safety guardrails.
Project analyzes traffic videos to improve Jakarta's safety.
problem Improving traffic safety in Jakarta.
method Developed a pipeline to analyze traffic videos, turning them into usable databases.
result Better understanding of traffic challenges and safety risks.
Self-driving vehicles improve safety by predicting surrounding vehicles' trajectories.
problem Ensuring safety of self-driving vehicles through better trajectory prediction.
method Developed a Convolutional Neural Network to forecast vehicle trajectories from raw data.
result Improvement over baseline models in trajectory forecasting accuracy.
Fine-tuning LLMs improves capability but harms safety, study finds.
problem Balancing capability and safety in LLM fine-tuning.
method Theoretical framework and numerical experiments for two safety-aware fine-tuning strategies.
result Characterization of fundamental limits of safety-capability trade-off in LLM fine-tuning.
New method improves safety analytics by addressing imbalanced data issues.
problem Imbalanced safety datasets lead to inaccurate predictions and management problems.
method Extended accident triangle theory and three oversampling methods.
result Robust improvements in machine learning algorithms for safety analytics.
Classifier-based AI safety gates fail in self-improvement, even with advanced verification methods.
problem Maintaining reliable oversight of AI systems as they improve over iterations.
method Comprehensive empirical testing on neural controllers and MuJoCo benchmarks, using various classifiers and verification methods.
result Classifier-based safety gates fail in maintaining reliable oversight, even with advanced verification methods.
RAGuard improves safety in LLMs for offshore wind maintenance.
problem Conventional LLMs fail with specialised or unexpected scenarios in offshore wind maintenance.
method Integrates safety-critical documents alongside technical manuals in RAG framework.
result RAGuard increases safety recall from almost 0% to over 50% while maintaining technical recall above 60%.
A new framework ensures model safety by retaining old model capabilities while improving new tasks.
problem Catastrophic forgetting in continual learning systems.
method Retention-centric framework with data-dependent constraints and an efficient constrained optimization algorithm.
result The method ensures that new models retain important capabilities of old models while improving new tasks.
Improved AI model predicts construction safety outcomes from incident reports.
problem Predicting safety outcomes from incident reports using AI.
method Extracted attributes from incident reports using NLP, trained machine learning models (XGBoost, linear SVM), used model stacking, analyzed per-category attribute importance.
result Attributes are highly predictive of safety outcomes, injury severity is well predicted.
Survey of algorithms for testing AI-driven CPS safety.
problem Testing AI-driven CPS for safety in complex environments.
method Survey of applied algorithms for safety validation.
result Survey of existing tools and techniques for safety validation.
Parenting algorithm improves AI safety by learning from human input.
problem Safety concerns in reinforcement learning, especially reward hacking and unsafe exploration.
method Inspired by parenting, a precise framework for learning from human input.
result Parenting algorithm solves safety problems in AI Safety gridworlds.
LLM safety alignment explained as divergence estimation.
problem Aligning large language models to avoid harmful outputs.
method Presented a theoretical framework showing alignment methods as divergence estimators.
result KLDO method improves safety alignment using compliance-refusal datasets.
The paper proposes a machine learning method to detect drivers' affective states using physiological signals.
problem Detecting and assessing drivers' affective states to improve driving safety and well-being.
method Multiview multi-task machine learning approach using physiological signals.
result Accounting for drive-specific differences significantly improves model performance.
System predicts ice formation to improve road safety.
problem Improving road safety through accurate ice formation prediction.
method Combining physical models and machine learning for data correction.
result Machine learning effectively corrects incorrect data in forecasts.
Improves policies with high certainty, even in small samples.
problem Ensuring new policies are better than the baseline with high probability.
method Leverages powerful safety tests and multiple testing for threshold policies.
result Controls the rate of adopting a worse policy to pre-specified error level.
SECRM-2D improves RL-based autonomous driving with safety guarantees.
problem Safety and efficiency trade-offs in RL-based autonomous driving.
method RL-based controller with safety constraints for efficient and comfortable driving.
result SECRM-2D avoids crashes and improves efficiency and comfort compared to baselines.
Paper improves autonomous vehicle safety and efficiency with new reinforcement learning methods.
problem Improving robustness and safety in autonomous vehicle control.
method Developed and compared two algorithms: Robust Adversarial Reinforcement Learning and Neural Fictitious Self Play.
result The new algorithms lead to improved driving efficiency and reduced collision rates.
Formal constraints improve RL safety in complex environments.
problem Safety constraints in reinforcement learning for complex environments.
method Specify constraints in formal languages, instantiate as finite automata, augment MDP states, learn dense cost function.
result Improved safety in training RL algorithms over various constraints.
Safe learning of stochastic dynamics with safety constraints.
problem Learning controlled stochastic dynamics with safety constraints.
method Iterative expansion of a safe control set using kernel-based confidence bounds.
result The method ensures safe exploration and efficient estimation of system dynamics.
A new method reduces the computational burden of safety alignment for large language models.
problem Safety concerns in large language models and the need to align them with human preferences.
method Optimal dualization approach to reduce constrained alignment to an unconstrained problem.
result Our algorithms MoCAN and PeCAN significantly reduce computational burden and improve training stability.
This work improves safety validation of autonomous vehicles by finding interpretable failures.
problem Finding interpretable failures of autonomous systems in simulation.
method Signal temporal logic expressions optimized for high likelihood and human interpretability.
result Our methodology finds more interpretable failures with higher likelihood compared to baseline approaches.
Safe Bayesian Optimization algorithms are improved to ensure safety in real-world applications.
problem Ensuring safety in Bayesian Optimization algorithms for real-world applications.
method Investigated and improved three safety-related issues of SafeOpt-type algorithms: frequentist uncertainty bounds, RKHS norm assumptions, and discrete search spaces.
result Introduced Real-{eta}-SafeOpt, Lipschitz-only Safe Bayesian Optimization (LoSBO), and Lipschitz-only GP-UCB (LoS-GP-UCB) algorithms that retain safety guarantees and superior performance.
Paper presents LSTMMDN for hourly bike flow estimation in Copenhagen.
problem Sparse or unavailable hourly bike flow data for safety analysis.
method Hybrid LSTM MDN model for hourly bike flow estimation.
result 66-77% more accurate bike flow estimates compared to calibration factors.
ELS framework improves safety alignment by dynamically steering LLMs towards helpful responses.
problem Over-Refusal in Aligned Large Language Models
method Fine-tuning free framework using an Energy-Based Model (EBM) to dynamically steer LLMs during inference.
result Extensive experiments show a significant reduction in false refusals (from 57.3% to 82.6%) while maintaining safety performance.
SafeQ-Learning uses Wasserstein DRO to ensure safety in online learning.
problem Ensuring safety in online Q-Learning algorithms.
method DrQ algorithm that uses Wasserstein ambiguity sets and offset variables.
result SafeQ-Learning provides idealistic probabilistic safety guarantees.
The paper tackles safe exploration in RL by a conservative safety critic.
problem Safe exploration in reinforcement learning (RL) when partially trained policies are deployed.
method Learning a conservative safety estimate through a critic, provably bounding catastrophic failures.
result The approach provably converges to competitive task performance with significantly lower catastrophic failure rates.
By building on a recently introduced genetic-inspired attribute-based conceptual framework for safety risk analysis, we propose a novel methodology to compute construction univariate and bivariate construction safety risk at a situational level. Our fully data-driven approach provides construction practitioners and aca…
Toolkit improves neural network safety for self-driving cars.
problem Ensuring safety of neural networks in autonomous driving systems.
method Structured approach using Goal Structuring Notation and recent scientific results.
result Improves quality of a level-3 autonomous driving component.
A new error bound improves safety in Bayesian optimization.
problem Ensuring safety in Bayesian optimization with probabilistic models.
method Introducing a novel error bound using Wiener kernel regression for Gaussian processes and noise.
result The new error bound provides larger safety regions than previous methods.
Holographic Invariant Storage uses vector architectures to ensure LLM safety at design time.
problem Mitigating context drift in large language models (LLMs) during deployment.
method Introduces Holographic Invariant Storage (HIS) protocol that combines known properties of bipolar Vector Symbolic Architectures into a design-time safety contract.
result Closed-form guarantees for single-signal recovery fidelity, continuous-noise robustness, and multi-signal capacity degradation are provided and validated.
ARTEO algorithm optimizes safety-critical systems with uncertainty.
problem Decision-making under uncertainty with safety constraints in real-time optimization.
method ARTEO algorithm uses multi-armed bandits as a mathematical programming problem subject to safety constraints, learning unknown characteristics through exploration and incorporating uncertainty quantification.
result ARTEO achieves less cumulative regret with accurate and safe decisions.
Meta-learning priors improves safe Bayesian optimization.
problem Optimizing robot controllers under safety constraints.
method Meta-learning priors from offline data using F-PACOH.
result Meta-learned priors accelerate safe BO convergence.
New approach checks neural networks for safety properties efficiently.
problem Ensuring neural networks are robust to adversarial and accidental perturbations.
method Efficient formal safety analysis of neural networks using tight output bounds.
result Significantly outperforms existing techniques for larger networks.
CRC improves multivariate forecasting accuracy without risking performance degradation.
problem Systematic errors and lack of guarantees in multivariate forecasters.
method CRC uses a causality-inspired encoder and hybrid corrector with a safety mechanism.
result CRC consistently improves accuracy and ensures high non-degradation rates.
CitySim dataset captures vehicle trajectories for safety research.
problem Lack of fine-grain vehicle trajectories for safety-oriented research.
method Five-step procedure: video stabilization, object filtering, stitching, detection, and error filtering.
result CitySim dataset improves safety evaluations and facilitates digital-twin research.
This paper explores formal verification for autonomous systems, identifying limitations and proposing improvements.
problem Ensuring safety of autonomous systems like self-driving cars and drones.
method Formal verification techniques based on formal methods, analyzing three assumptions and their limitations.
result Preliminary work to improve the strength of evidence provided by formal verification.
Quantum model improves safety in machine learning.
problem Improving safety and robustness in machine learning models.
method Variational quantum classifier with amplitude encoding and SAFE-AI metrics.
result Quantum model provides competitive performance and improved robustness.
A new RL model ensures safe learning in uncertain environments.
problem Safe reinforcement learning in uncertain, partially observable environments.
method Lyapunov-based uncertainty quantification and Transformers for memory.
result Significant improvement in safety and optimality in grid-world tasks.
Improves safety region certification for smoothed classifiers without changing smoothing scheme.
problem Certified safety regions for smoothed classifiers are often small compared to optimal.
method Generalizes certified radius calculation as nested optimization problem, uses 0th-1st order information, and designs efficient estimators.
result Certified safety regions are significantly larger than current methods, achieving significant improvements on various metrics.
Safe reinforcement learning framework using optimal transport for robustness.
problem Robustness and safety in deep reinforcement learning with limited data assumptions.
method Optimal transport perturbations to construct worst-case virtual state transitions.
result Significantly improved safety at deployment time compared to standard methods.
Paper explores anchoring for vision models, improving generalization and safety.
problem Anchoring can lead to undesirable shortcuts, limiting generalization.
method Introduced a new anchored training protocol with a regularizer to mitigate undesirable shortcuts.
result Significant performance gains in generalization and safety metrics.
Safe active learning for multi-output Gaussian processes reduces data acquisition costs and ensures safety.
problem Expensive data acquisition and safety concerns in multi-output regression problems.
method Proposes a safe active learning approach considering data informativeness and safety constraints.
result Improved convergence compared to competitors on simulated and real-world datasets.
New RL approach tackles constrained Markov decision processes.
problem Applying RL to physical systems with safety constraints.
method Formulated as a Constrained Markov Decision Process (CMDP), introduced a safe policy improvement method.
result Agent learns to maximize returns while satisfying constraints.
Study improves self-driving safety in dynamic environments.
problem Safe self-driving in non-stationary urban settings.
method Neurosymbolic Meta-Reinforcement Lookahead Learning (NUMERLA).
result Self-driving agents can adapt safely in real-time.
Deep-PrAE improves rare-event simulation for black-box systems.
problem Evaluating rare safety-critical events in learning-based systems.
method Combines deep neural networks with IS to create statistically guaranteed estimations.
result Deep-PrAE provides accurate bounds on safety-critical event probabilities.
New algorithm for safe bandits with unknown parameters and constraints.
problem Safety-critical systems with unknown parameters and constraints.
method Safe-LUCB algorithm with two phases: pure exploration and safe exploration-exploitation.
result General and problem-dependent regret bounds for the Safe-LUCB algorithm.
The paper reviews machine learning safety techniques for autonomous vehicles.
problem Challenges in machine learning safety for autonomous vehicles.
method Organizes practical safety techniques to complement engineering safety.
result Enhances dependability and safety of machine learning algorithms in autonomous vehicles.
A framework identifies worst-case decision points in safety-critical scenarios, improving risk assessment by 10 hours.
problem Identifying worst-case outcomes in safety-critical decision-making under uncertainty.
method Explicitly estimating distributions of expected return to identify dead-ends, tuning based on risk tolerance.
result Significantly improves risk assessment, providing indications 10 hours earlier and increasing detection by 20%.