There is an increasing imperative to anticipate and understand the performance and safety of generative AI systems in real-world deployment contexts. However, the current evaluation ecosystem is insufficient: commonly used static benchmarks face validity challenges, and ad hoc case-by-case approaches rarely scale. In this piece, we advocate for maturing an evaluation science for generative AI systems. While generative AI creates unique challenges for system safety engineering and measurement science, the field can draw valuable insights from the development of safety evaluation practices in other fields including transportation, aerospace, and pharmaceutical engineering. In particular, we present three key lessons: evaluation metrics must be applicable to real-world performance, metrics must be iteratively refined, and evaluation institutions and norms must be established. Applying these insights, we outline a concrete path toward a more rigorous approach for evaluating generative AI systems.

Federated learning leverages data across institutions to improve clinical discovery while complying with data-sharing restrictions and protecting patient privacy. As the evolution of biobanks in genetics and systems biology has proved, accessing more extensive and varied data pools leads to a faster and more robust exploration and translation of results. More widespread use of federated learning may have the same impact in bioinformatics, allowing access to many combinations of genotypic, phenotypic and environmental information that are undercovered or not included in existing biobanks. This paper reviews the methodological, infrastructural and legal issues that academic and clinical institutions must address before implementing it. Finally, we provide recommendations for the reliable use of federated learning and its effective translation into clinical practice.

The Justice Department said in a filing that Google will have to break up its network of myriad, overlapping businesses and services, upholding the previous administration's proposal. The DOJ reiterated Google will have to sell the Chrome browser -- saying, last year, that selling off Chrome "will permanently stop Google's control of this critical search access point and allow rival search engines the ability to access the browser that for many users is a gateway to the internet." Google is likely to file its own alternate remedies, of course. In a December filing, the company said the Justice Department's original remedies went "overboard" and reflected an "interventionist agenda." But Google is huge, and the DOJ is trying to grasp how its parts intermingle and make it less monopolistic.

Techno-optimism – the belief that technology will usher in a golden age for humanity – is in vogue once more. In 2022, a clutch of pseudonymous San Francisco artificial intelligence (AI) scenesters published a Substack post entitled "Effective Accelerationism", which argued for maximum acceleration of technological advancement. The 10-point manifesto, which proclaimed that "the next evolution of consciousness, creating unthinkable next-generation lifeforms and silicon-based awareness" was imminent, quickly went viral, as did follow-up posts. Effective accelerationism, or "e/acc", exploded from being a fringe movement dedicated to pushing back against AI extinction-fearing "doomers" to being namechecked by major Silicon Valley CEOs such as Garry Tan, the CEO of start-up accelerator Y Combinator; Sam Altman, head of OpenAI; Marc Andreessen, the billionaire software engineer; and Elon Musk. In 2023, Andreessen issued his Techno-Optimist Manifesto, expanding beyond the e/acc's focus on AI to encompass all questions of technological progress.

Existing power dynamics, social injustices and structural barriers may exacerbate challenges related to support and advocacy, limiting some students' ability to articulate their needs effectively [59]. This disparity highlights an increasing need for alternative approaches to student advocacy that may empower students with disabilities in ways that current practices may not. While human disability support practitioners can play a crucial role in bridging gaps between students and institutions, these efforts are resource-intensive, relying on trained personnel, availability, and sustained institutional commitment. This study explores the feasibility and ethical implications of employing artificial intelligence (AI) and in particular social robots as tools for mediation and advocacy for disabled students in higher education. While the overarching focus regards social robots and LLMs, the study adopts a broader perspective of understanding the use of technology and AI in general for disabled students, to draw insights and identify patterns that can inform the design, implementation, and ethical considerations of AI-driven assistive technologies.

Large Language Models (LLMs) offer a promising alternative to traditional survey methods, potentially enhancing efficiency and reducing costs. In this study, we use LLMs to create virtual populations that answer survey questions, enabling us to predict outcomes comparable to human responses. We evaluate several LLMs-including GPT-4o, GPT-3.5, Claude 3.5-Sonnet, and versions of the Llama and Mistral models-comparing their performance to that of a traditional Random Forests algorithm using demographic data from the World Values Survey (WVS). LLMs demonstrate competitive performance overall, with the significant advantage of requiring no additional training data. However, they exhibit biases when predicting responses for certain religious and population groups, underperforming in these areas. On the other hand, Random Forests demonstrate stronger performance than LLMs when trained with sufficient data. We observe that removing censorship mechanisms from LLMs significantly improves predictive accuracy, particularly for underrepresented demographic segments where censored models struggle. These findings highlight the importance of addressing biases and reconsidering censorship approaches in LLMs to enhance their reliability and fairness in public opinion research.

This paper introduces and tests a framework integrating traffic regulation compliance into automated driving systems (ADS). The framework enables ADS to follow traffic laws and make informed decisions based on the driving environment. Using RGB camera inputs and a vision-language model (VLM), the system generates descriptive text to support a regulation-aware decision-making process, ensuring legal and safe driving practices. This information is combined with a machine-readable ADS regulation database to guide future driving plans within legal constraints. Key features include: 1) a regulation database supporting ADS decision-making, 2) an automated process using sensor input for regulation-aware path planning, and 3) validation in both simulated and real-world environments. Particularly, the real-world vehicle tests not only assess the framework's performance but also evaluate the potential and challenges of VLMs to solve complex driving problems by integrating detection, reasoning, and planning. This work enhances the legality, safety, and public trust in ADS, representing a significant step forward in the field.

Model merging has achieved significant success, with numerous innovative methods proposed to enhance capabilities by combining multiple models. However, challenges persist due to the lack of a unified framework for classification and systematic comparative analysis, leading to inconsistencies in terminologies and categorizations. Meanwhile, as an increasing number of fine-tuned models are publicly available, their original training data often remain inaccessible due to privacy concerns or intellectual property restrictions. This makes traditional multi-task learning based on shared training data impractical. In scenarios where direct access to training data is infeasible, merging model parameters to create a unified model with broad generalization across multiple domains becomes crucial, further underscoring the importance of model merging techniques. Despite the rapid progress in this field, a comprehensive taxonomy and survey summarizing recent advances and predicting future directions are still lacking. This paper addresses these gaps by establishing a new taxonomy of model merging methods, systematically comparing different approaches, and providing an overview of key developments. By offering a structured perspective on this evolving area, we aim to help newcomers quickly grasp the field's landscape and inspire further innovations.

Reinforcement learning from human feedback (RLHF) has become essential for improving language model capabilities, but traditional approaches rely on the assumption that human preferences follow a transitive Bradley-Terry model. This assumption fails to capture the non-transitive nature of populational human preferences. Nash learning from human feedback (NLHF), targeting non-transitive preferences, is a problem of computing the Nash equilibrium (NE) of the two-player constant-sum game defined by the human preference. We introduce Extragradient preference optimization (EGPO), a novel algorithm for NLHF achieving last-iterate linear convergence to the NE of KL-regularized games and polynomial convergence to the NE of original games, while being robust to noise. Unlike previous approaches that rely on nested optimization, we derive an equivalent implementation using gradients of an online variant of the identity preference optimization (IPO) loss, enabling more faithful implementation for neural networks. Our empirical evaluations demonstrate EGPO's superior performance over baseline methods when training for the same number of epochs, as measured by pairwise win-rates using the ground truth preference.

Source-free domain adaptation (SFDA) has been exploited for cross-domain bearing fault diagnosis without access to source data. Current methods select partial target samples with reliable pseudo-labels for model adaptation, which is sub-optimal due to the ignored target samples. We argue that every target sample can contribute to model adaptation, and accordingly propose in this paper a novel SFDA-based approach for bearing fault diagnosis that exploits both reliable and unreliable pseudo-labels. We develop a data-augmentation-based label voting strategy to divide the target samples into reliable and unreliable ones. We propose to explore the underlying relation between feature space and label space by using the reliable pseudo-labels as ground-truth labels, meanwhile, alleviating negative transfer by maximizing the entropy of the unreliable pseudo-labels. The proposed method achieves well-balance between discriminability and diversity by taking advantage of reliable and unreliable pseudo-labels. Extensive experiments are conducted on two bearing fault benchmarks, demonstrating that our approach achieves significant performance improvements against existing SFDA-based bearing fault diagnosis methods. Our code is available at https://github.com/BdLab405/SDALR.