Proposes a mathematical model for safe and scalable self-driving cars.
problem Ensuring safety and scalability in self-driving cars.
method Introduces Responsibility-Sensitive Safety (RSS) model and scalable design.
result Proposes a mathematical model for safety assurance and scalable design.
Paper presents a new Wi-Fi RSS and geomagnetic field database for indoor localization and trajectory estimation.
problem Indoor localization and trajectory estimation challenges.
method Convolutional neural network (CNN) for RSS data and LSTM network for geomagnetic field intensity.
result CNN and LSTM networks show feasibility for localization and trajectory estimation.
Proposes Siegel neural networks for improved classification tasks.
problem Classification on Siegel spaces is underexplored.
method Uses quotient structure and vector-valued distance notation.
result Demonstrates state-of-the-art performance in radar and node classification.
Paper tackles indoor localization issues with reduced dimensionality and improved fingerprint matching.
problem Curse of dimensionality and asymmetric matching in fingerprint-based indoor localization.
method Proposes a semi-supervised RSS dimensionality reduction algorithm and integrates it with a fingerprint-based algorithm.
result Improves indoor localization accuracy by reducing dimensionality and addressing matching issues.
New method uses SVBI to quickly generate radio maps for indoor positioning.
problem Time-consuming site surveys for creating radio maps in large indoor spaces.
method Combines fingerprinting positioning and SVBI for efficient radio map generation.
result Significantly reduces the cost and time of creating radio maps for indoor positioning.
Paper proposes DRL for unsupervised IoT localization.
problem Challenges in unsupervised localization of IoT devices.
method Modeling localization as MDP, using DRL with reward-setting and RSS measurements.
result Demonstrated effectiveness of DRL in wireless localization.
WiFi helps align and calibrate foot-mounted IMU trajectories.
problem Inertial drift and unknown initial states in FMIP.
method Graph-based SLAM with RSS measurements for WiFi APs.
result Aligns and calibrates trajectories accurately.
RecSim creates customizable simulation environments for RSs.
problem Creating realistic simulation environments for RSs.
method Configurable platform for authoring simulation environments.
result Enables pushing the limits of RL and RS techniques.
A multiple classifiers fusion localization technique using received signal strengths (RSSs) of visible light is proposed, in which the proposed system transmits different intensity modulated sinusoidal signals by LEDs and the signals received by a Photo Diode (PD) placed at various grid points. First, we obtain some {\…
New proof shows random neural networks contain sparse subnetworks.
problem Finding sparse subnetworks in random neural networks.
method Proof of the Strong Lottery Ticket Hypothesis using the Random Fixed-Size Subset Sum Problem.
result Guaranteed sparsity of subnetworks in random neural networks.
Noise-ignorant empirical risk minimization achieves state-of-the-art performance on noisy data.
problem Learning with noisy labels in multi-class classification problems.
method Introducing relative signal strength (RSS) to quantify transferability and applying Noise Ignorant Empirical Risk Minimization (NI-ERM).
result NI-ERM achieves state-of-the-art performance on CIFAR-N data challenge.
Paper presents an energy-efficient RL method for sensor networks.
problem Energy consumption in sensor networks for health monitoring.
method Adaptive Reinforcement Learning framework using SARSA algorithm.
result Achieves performance enhancement and energy savings over time.
DeepPos uses deep learning to improve indoor location accuracy.
problem Indoor GPS accuracy issues with mobile devices.
method Supervised autoencoder network for modeling CSI-based environments.
result Robust and efficient indoor localization system developed.
Gradient optimization improves preference elicitation for large item spaces.
problem Computational infeasibility of EVOI for large item spaces in recommender systems.
method Continuous formulation of EVOI as a differentiable network, optimized using gradient methods.
result Gradient-based EVOI optimization achieves state-of-the-art performance and scalability.
New model uses symmetries and scaling laws to predict consumer advertising response.
problem Understanding consumer response to advertising efforts.
method Introduces a physics-based mathematical model to describe consumer response dynamics.
result The model better captures nonlinearities in advertising effects and provides new parameters for audience engagement.
Most existing fingerprints-based indoor localization approaches are based on some single fingerprints, such as received signal strength (RSS), channel impulse response (CIR), and signal subspace. However, the localization accuracy obtained by the single fingerprint approach is rather susceptible to the changing environ…
New job recommendation system improves job seekers' welfare through field experiments.
problem Current job recommendation systems focus on clicks and applications, not job seekers' welfare.
method Developed a job-search model with two dimensions: utility and success probability. Conducted field experiments to validate model predictions.
result Welfare-optimal job recommendation algorithms outperform existing approaches and perform close to the benchmark.
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.
The Lagrange regularisation method detects financial bubbles' start times objectively.
problem Identifying the start time of financial bubbles.
method Lagrange regularisation of the normalised sum of squared residuals.
result The method provides well-defined determinations of bubble start times.
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.
Quantum analysis tags news for sentiment and entities.
problem Identifying bias in news reporting.
method Continuous data collection, NER and sentiment analysis.
result A corpus of tagged news articles for public use.
Research tackles safety of deep learning in safety-critical tasks.
problem Safety concerns of deep learning in perception tasks for autonomous agents.
method Technical enumeration and discussions on safety concerns and mitigation methods.
result Need for more mitigation methods to ensure safety of deep learning.
We study contact structures compatible with genus one open book decompositions with one boundary component. Any monodromy for such an open book can be written as a product of Dehn twists around dual non-separating curves in the once-punctured torus. Given such a product, we supply an algorithm to determine whether the …
The paper discusses safety assessment for AI systems, focusing on machine learning models.
problem Safety assessment of AI systems, especially machine learning models, in safety-related applications.
method Analyzed AI models as statistical models and proposed a new budget allocation for AI safety.
result Safety assessment of AI systems requires a new approach focusing on the model used, not just the system.
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 safety measure reduces failures in learning systems.
problem Challenges in learning to control physical systems due to failures.
method Implicitly captures system dynamics to failure states using Gaussian processes for model-free active sampling.
result Significant reduction in failures during learning with estimated safety measure.
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%.
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.
Safe imitation learning with a safety layer for flexible training.
problem Flexible yet safe imitation learning for complex tasks.
method Theory and modular method with a safety layer for continuous policy, adversarial training, and worst-case safety guarantees.
result Robustness advantage of safety layer during training compared to test time.
This paper formalizes AI safety using hypothesis testing in GenAI.
problem Ensuring safety of generative AI tools that create realistic content.
method Formalization of computational safety through hypothesis testing and signal processing.
result Demonstrates how AI safety can be assessed quantitatively using mathematical frameworks.
Deep learning maps road safety features from streetview imagery.
problem Accurate mapping of road safety features for safer roads.
method Proposes a deep learning approach with LSTM to capture spatial autocorrelation.
result Model outperforms baseline methods in mapping road safety features.
A new algorithm for identifying the best arm in linear feedback with safety constraints.
problem Identifying the best arm in linear feedback with safety constraints.
method A gap-based algorithm that ensures safety while minimizing sample complexity.
result The algorithm achieves meaningful sample complexity while ensuring safety.
Safety filter for unknown discrete-time systems with learned models and noise covariance.
problem Ensuring safety for unknown discrete-time linear systems with Gaussian noise.
method Develops a learning-based safety filter using empirical model and noise covariance, optimizing control actions to stay within safety constraints.
result Minimally modifies nominal control actions to ensure safety with high probability, tightening constraints as more data is collected.
SafeML monitors ML systems for safety and security risks.
problem Ensuring safety and explainability of ML systems in safety-critical domains.
method Statistical difference measures of ECDF to detect distributional shifts.
result Approach can detect invalid application contexts of ML components.
Paper defines and quantifies safety risks in deep neural networks.
problem Safety concerns in deep neural networks applied to critical sectors.
method Defines safety property, computes maximum safe radius, identifies new risk class, develops algorithm.
result Method achieves competitive performance in safety quantification.
Study best arm identification with safety constraints in bandit problems.
problem Real-world decision-making with safety constraints.
method Analyzed linear and monotonic reward and safety constraints, proposed algorithms.
result Guaranteed safe learning in both linear and general reward/safety constraint settings.
A scoring method for driving safety using trajectory data.
problem Managing traffic safety through driver behaviors and violations.
method Extract driving habits and violations from trajectories, train a model, score drivers.
result Proves the effectiveness of the scoring method using traffic simulation.
Safe reinforcement learning tackles safety constraints with linear approximations.
problem Ensuring safety in reinforcement learning without violating constraints.
method Modeling safety as a linear cost function, developing SLUCB-QVI and RSLUCB-QVI algorithms for MDPs with linear function approximation.
result Achieved a nearly optimal regret bound for safe reinforcement learning, matching state-of-the-art unsafe algorithms.
Enhances safety of 3D object detection neural networks.
problem Ensuring robustness and safety of 3D object detection systems.
method Symbolic error propagation, specialized loss function, safety-aware non-max-inclusion algorithm.
result Improved safety and robustness of 3D object detection neural networks.
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.
Bayesian Optimization verifies robot controllers against safety violations.
problem Ensuring safety of complex robot controllers in real-world applications.
method Bayesian Optimization framework to test and verify safety constraints.
result The method can find adversarial examples quickly and verify complex safety specifications.
CARL safely adapts RL agents for safety-critical tasks.
problem Safety hazards in RL for safety-critical tasks.
method CARL combines model-based RL and cautious adaptation.
result CARL achieves higher rewards with fewer failures in safety-critical tasks.
Automated system forecasts safety and security issues in internet-connected devices.
problem Challenges in real-time large-scale forecasting by human experts.
method Developed a scalable and versatile forecasting system using models and methods.
result Automated short and long-term forecasts detect safety and security issues in internet-connected devices.
A novel approach for safe offline RL using latent safety constraints.
problem Balancing safety constraints and reward maximization in offline RL.
method Conditional Variational Autoencoders for latent safety modeling, Constrained Reward-Return Maximization.
result Our approach maintains safety compliance while optimizing rewards, outperforming existing methods.
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.
Deep learning method identifies precursors to aviation safety incidents.
problem Mining correlated events in multi-dimensional time series data for aviation safety.
method Combining multiple-instance learning and deep recurrent neural networks.
result The proposed algorithm identifies precursors to safety incidents more effectively than baseline models.
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.
Machine learning algorithms increasingly influence our decisions and interact with us in all parts of our daily lives. Therefore, just as we consider the safety of power plants, highways, and a variety of other engineered socio-technical systems, we must also take into account the safety of systems involving machine le…