We present the HOH (Human-Object-Human) Handover Dataset, a large object count dataset with 136 objects, to accelerate data-driven research on handover studies, human-robot handover implementation, and artificial intelligence (AI) on handover parameter estimation from 2D and 3D data of person interactions. HOH contains multi-view RGB and depth data, skeletons, fused point clouds, grasp type and handedness labels, object, giver hand, and receiver hand 2D and 3D segmentations, giver and receiver comfort ratings, and paired object metadata and aligned 3D models for 2,720 handover interactions spanning 136 objects and 20 giver-receiver pairs-40 with role-reversal-organized from 40 participants. We also show experimental results of neural networks trained using HOH to perform grasp, orientation, and trajectory prediction. As the only fully markerless handover capture dataset, HOH represents natural human-human handover interactions, overcoming challenges with markered datasets that require specific suiting for body tracking, and lack high-resolution hand tracking. To date, HOH is the largest handover dataset in number of objects, participants, pairs with role reversal accounted for, and total interactions captured.

Survival analysis is a valuable tool for estimating the time until specific events, such as death or cancer recurrence, based on baseline observations. This is particularly useful in healthcare to prognostically predict clinically important events based on patient data. However, existing approaches often have limitations; some focus only on ranking patients by survivability, neglecting to estimate the actual event time, while others treat the problem as a classification task, ignoring the inherent time-ordered structure of the events. Furthermore, the effective utilization of censored samples - training data points where the exact event time is unknown - is essential for improving the predictive accuracy of the model. In this paper, we introduce CenTime, a novel approach to survival analysis that directly estimates the time to event. Our method features an innovative event-conditional censoring mechanism that performs robustly even when uncensored data is scarce. We demonstrate that our approach forms a consistent estimator for the event model parameters, even in the absence of uncensored data. Furthermore, CenTime is easily integrated with deep learning models with no restrictions on batch size or the number of uncensored samples. We compare our approach with standard survival analysis methods, including the Cox proportional-hazard model and DeepHit. Our results indicate that CenTime offers state-of-the-art performance in predicting time-to-death while maintaining comparable ranking performance. Our implementation is publicly available at https://github.com/ahmedhshahin/CenTime.

The final set of Jeffrey Epstein-related documents in a 2015 lawsuit between accuser Virginia Giuffre and his accomplice Ghislaine Maxwell revealed the plaintiff had accused Bill Richardson, Marvin Minsky and Les Wexner of sex trafficking her in a 2016 deposition. Their names had been redacted in a previous version of the 223-page filing unsealed in May 2022. Jean-Luc Brunel, who died in a French jail while awaiting trial on sex trafficking charges of his own, is also accused of victimizing her in the latest filings. Richardson was the former Democratic governor of New Mexico who died in September. Minsky was a leading computer scientist at the Massachusetts Institute of Technology who died in 2016.

Amid the growing clamor in Congress to regulate AI, the company is bringing in reinforcements. After years of outreach to lawmakers, OpenAI in fall 2023 disclosed its first in-house lobbyist, and reported that it is working with global law firm DLA Piper, according to federal disclosures. OpenAI to date has not advocated for or against any specific bill, Makanju says, but she anticipates that will change in 2024, especially with the Schumer effort that is underway. Makanju's team is also growing around the world, with more than 20 people in the United Kingdom, Germany, Japan and Brazil.

And based on what OpenAI told the House of Lords Communications and Digital Select Committee, we might see more lawsuits against the companies in the future. It added that "[l]imiting training data to public domain books and drawings created more than a century ago might yield an interesting experiment, but would not provide AI systems that meet the needs of today's citizens." In a new post on its blog made in response to the The New York Times' lawsuit, it said the use of publicly available internet materials to train AI falls under fair use doctrine. It admitted, however, that there is "still work to be done to support and empower creators." The company talked about the ways it's allowing publishers to block the GPTBot web crawler from being able to access their websites. It also said that it's developing additional mechanisms allowing rightsholders to opt out of training and that it's engaging with them to find mutually beneficial agreements.

With the rise of individual and collaborative networks of autonomous agents, AI is deployed in more key reasoning and decision-making roles. For this reason, ethics-based audits play a pivotal role in the rapidly growing fields of AI safety and regulation. This paper undertakes an ethics-based audit to probe the 8 leading commercial and open-source Large Language Models including GPT-4. We assess explicability and trustworthiness by a) establishing how well different models engage in moral reasoning and b) comparing normative values underlying models as ethical frameworks. We employ an experimental, evidence-based approach that challenges the models with ethical dilemmas in order to probe human-AI alignment. The ethical scenarios are designed to require a decision in which the particulars of the situation may or may not necessitate deviating from normative ethical principles. A sophisticated ethical framework was consistently elicited in one model, GPT-4. Nonetheless, troubling findings include underlying normative frameworks with clear bias towards particular cultural norms.

Recently, various Large Language Models (LLMs) evaluation datasets have emerged, but most of them have issues with distorted rankings and difficulty in model capabilities analysis. Addressing these concerns, this paper introduces ANGO, a Chinese multi-choice question evaluation benchmark. ANGO proposes \textit{Keypoint} categorization standard for the first time, each question in ANGO can correspond to multiple keypoints, effectively enhancing interpretability of evaluation results. Base on performance of real humans, we build a quantifiable question difficulty standard and divide ANGO questions into 9 difficulty levels, which provide more precise guidance for model training. To minimize data leakage impact and fully leverage ANGO's innovative features, we have engineered exclusive sampling strategies and a new evaluation framework that support swift testset iteration. Our experiments demonstrate that ANGO poses a stronger challenge to models and reveals more details in evaluation result compared to existing benchmarks.

Improving energy efficiency in industrial production processes is crucial for competitiveness, and compliance with climate policies. This paper introduces a data-driven approach to identify optimal melting patterns in induction furnaces. Through time-series K-means clustering the melting patterns could be classified into distinct clusters based on temperature profiles. Using the elbow method, 12 clusters were identified, representing the range of melting patterns. Performance parameters such as melting time, energy-specific performance, and carbon cost were established for each cluster, indicating furnace efficiency and environmental impact. Multiple criteria decision-making methods including Simple Additive Weighting, Multiplicative Exponential Weighting, Technique for Order of Preference by Similarity to Ideal Solution, modified TOPSIS, and VlseKriterijumska Optimizacija I Kompromisno Resenje were utilized to determine the best-practice cluster. The study successfully identified the cluster with the best performance. Implementing the best practice operation resulted in an 8.6 % reduction in electricity costs, highlighting the potential energy savings in the foundry.

The conservation of hydrological resources involves continuously monitoring their contamination. A multi-agent system composed of autonomous surface vehicles is proposed in this paper to efficiently monitor the water quality. To achieve a safe control of the fleet, the fleet policy should be able to act based on measurements and to the the fleet state. It is proposed to use Local Gaussian Processes and Deep Reinforcement Learning to jointly obtain effective monitoring policies. Local Gaussian processes, unlike classical global Gaussian processes, can accurately model the information in a dissimilar spatial correlation which captures more accurately the water quality information. A Deep convolutional policy is proposed, that bases the decisions on the observation on the mean and variance of this model, by means of an information gain reward. Using a Double Deep Q-Learning algorithm, agents are trained to minimize the estimation error in a safe manner thanks to a Consensus-based heuristic. Simulation results indicate an improvement of up to 24% in terms of the mean absolute error with the proposed models. Also, training results with 1-3 agents indicate that our proposed approach returns 20% and 24% smaller average estimation errors for, respectively, monitoring water quality variables and monitoring algae blooms, as compared to state-of-the-art approaches

Machine unlearning techniques, which involve retracting data records and reducing influence of said data on trained models, help with the user privacy protection objective but incur significant computational costs. Weight perturbation-based unlearning is a general approach, but it typically involves globally modifying the parameters. We propose fine-grained Top-K and Random-k parameters perturbed inexact machine unlearning strategies that address the privacy needs while keeping the computational costs tractable. In order to demonstrate the efficacy of our strategies we also tackle the challenge of evaluating the effectiveness of machine unlearning by considering the model's generalization performance across both unlearning and remaining data. To better assess the unlearning effect and model generalization, we propose novel metrics, namely, the forgetting rate and memory retention rate. However, for inexact machine unlearning, current metrics are inadequate in quantifying the degree of forgetting that occurs after unlearning strategies are applied. To address this, we introduce SPD-GAN, which subtly perturbs the distribution of data targeted for unlearning. Then, we evaluate the degree of unlearning by measuring the performance difference of the models on the perturbed unlearning data before and after the unlearning process. By implementing these innovative techniques and metrics, we achieve computationally efficacious privacy protection in machine learning applications without significant sacrifice of model performance. Furthermore, this approach provides a novel method for evaluating the degree of unlearning.