This paper explores the challenge of procedure planning in instructional videos, which involves creating goal-directed plans based on visual start and goal observations from videos. Previous research has tackled this problem with gradually weaker training supervision, from heavy intermediate visual observations or language instructions to task class supervision. However, with the advent of large language models, even given only the task name, these models can produce a detailed plan. In this study, we propose a much weaker setting without task name as supervision, which is not currently solvable by existing large language models since they require good prompts with sufficient information. Specifically, we hypothesize that previous intermediate supervisions can serve as context information, and we use captions of visual start and goal observations as a much cheaper form of supervision. This approach greatly reduces the labeling cost since the captions can be easily obtained by large pre-trained vision-language foundation models. Technically, we apply BLIP to generate captions as supervision to train the context feature with contrastive learning loss. Afterward, the context feature is fed into the generator to aid in plan generation. Our experiments on two datasets with varying scales demonstrate that our model can achieve comparable performance on multiple metrics, which validates our hypothesis.

Steering the behavior of a strong model pre-trained on internet-scale data can be difficult due to the scarcity of competent supervisors. Recent studies reveal that, despite supervisory noises, a strong student model may surpass its weak teacher when fine-tuned on specific objectives. Yet, the effectiveness of such weak-to-strong generalization remains limited, especially in the presence of large capability gaps. In this paper, we propose to address this challenge by harnessing a diverse set of specialized teachers, instead of a single generalist one, that collectively supervises the strong student. Our approach resembles the classical hierarchical mixture of experts, with two components tailored for co-supervision: (i) we progressively alternate student training and teacher assignment, leveraging the growth of the strong student to identify plausible supervisions; (ii) we conservatively enforce teacher-student and local-global consistency, leveraging their dependencies to reject potential annotation noises. We validate the proposed method through visual recognition tasks on the OpenAI weak-to-strong benchmark and additional multi-domain datasets. Our code is available at \url{https://github.com/yuejiangliu/csl}.

Predictive analytics is widely used in various domains, including education, to inform decision-making and improve outcomes. However, many predictive models are proprietary and inaccessible for evaluation or modification by researchers and practitioners, limiting their accountability and ethical design. Moreover, predictive models are often opaque and incomprehensible to the officials who use them, reducing their trust and utility. Furthermore, predictive models may introduce or exacerbate bias and inequity, as they have done in many sectors of society. Therefore, there is a need for transparent, interpretable, and fair predictive models that can be easily adopted and adapted by different stakeholders. In this paper, we propose a fair predictive model based on multivariate adaptive regression splines(MARS) that incorporates fairness measures in the learning process. MARS is a non-parametric regression model that performs feature selection, handles non-linear relationships, generates interpretable decision rules, and derives optimal splitting criteria on the variables. Specifically, we integrate fairness into the knot optimization algorithm and provide theoretical and empirical evidence of how it results in a fair knot placement. We apply our fairMARS model to real-world data and demonstrate its effectiveness in terms of accuracy and equity. Our paper contributes to the advancement of responsible and ethical predictive analytics for social good.

With the explosive growth of data, continual learning capability is increasingly important for neural networks. Due to catastrophic forgetting, neural networks inevitably forget the knowledge of old tasks after learning new ones. In visual classification scenario, a common practice of alleviating the forgetting is to constrain the backbone. However, the impact of classifiers is underestimated. In this paper, we analyze the variation of model predictions in sequential binary classification tasks and find that the norm of the equivalent one-class classifiers significantly affects the forgetting level. Based on this conclusion, we propose a two-stage continual learning algorithm named Fixed Random Classifier Rearrangement (FRCR). In first stage, FRCR replaces the learnable classifiers with fixed random classifiers, constraining the norm of the equivalent one-class classifiers without affecting the performance of the network. In second stage, FRCR rearranges the entries of new classifiers to implicitly reduce the drift of old latent representations. The experimental results on multiple datasets show that FRCR significantly mitigates the model forgetting; subsequent experimental analyses further validate the effectiveness of the algorithm.

A number of prestigious awards were announced shortly before the start of AAAI 2024, and will be officially presented during an awards ceremony at the conference, on 24 February. Some of the winners will also be giving invited talks as part of the programme. The AAAI Award for Artificial Intelligence for the Benefit of Humanity recognises the positive impacts of artificial intelligence to protect, enhance, and improve human life in meaningful ways with long-lived effects. The winner of this year's award is Milind Tambe (Harvard University/Google Research). Milind has been recognised for "ground-breaking applications of novel AI techniques to public safety and security, conservation, and public health, benefiting humanity on an international scale".

Though many doctors today get help from robots for procedures ranging from hernia repairs to coronary bypasses, those are used to assist surgeons, not replace them. This new research marks progress toward robots that can operate more autonomously on very intricate, complicated tasks like suturing. The lessons learned in its development could also be useful in other fields of robotics. "From a robotics perspective, this is a really challenging manipulation task," says Ken Goldberg, a researcher at UC Berkeley and director of the lab that worked on the robot. One issue is that shiny or reflective objects like needles can throw off a robot's image sensors.

Purpose: The study aims to analyze the synergy of Artificial Intelligence (AI), with scientometrics, webometrics, and bibliometrics to unlock and to emphasize the potential of the applications and benefits of AI algorithms in these fields. Design/methodology/approach: By conducting a systematic literature review, our aim is to explore the potential of AI in revolutionizing the methods used to measure and analyze scholarly communication, identify emerging research trends, and evaluate the impact of scientific publications. To achieve this, we implemented a comprehensive search strategy across reputable databases such as ProQuest, IEEE Explore, EBSCO, Web of Science, and Scopus. Our search encompassed articles published from January 1, 2000, to September 2022, resulting in a thorough review of 61 relevant articles. Findings: (i) Regarding scientometrics, the application of AI yields various distinct advantages, such as conducting analyses of publications, citations, research impact prediction, collaboration, research trend analysis, and knowledge mapping, in a more objective and reliable framework. (ii) In terms of webometrics, AI algorithms are able to enhance web crawling and data collection, web link analysis, web content analysis, social media analysis, web impact analysis, and recommender systems. (iii) Moreover, automation of data collection, analysis of citations, disambiguation of authors, analysis of co-authorship networks, assessment of research impact, text mining, and recommender systems are considered as the potential of AI integration in the field of bibliometrics. Originality/value: This study covers the particularly new benefits and potential of AI-enhanced scientometrics, webometrics, and bibliometrics to highlight the significant prospects of the synergy of this integration through AI.

As datasets used in scientific applications become more complex, studying the geometry and topology of data has become an increasingly prevalent part of the data analysis process. This can be seen for example with the growing interest in topological tools such as persistent homology. However, on the one hand, topological tools are inherently limited to providing only coarse information about the underlying space of the data. On the other hand, more geometric approaches rely predominately on the manifold hypothesis, which asserts that the underlying space is a smooth manifold. This assumption fails for many physical models where the underlying space contains singularities. In this paper we develop a machine learning pipeline that captures fine-grain geometric information without having to rely on any smoothness assumptions. Our approach involves working within the scope of algebraic geometry and algebraic varieties instead of differential geometry and smooth manifolds. In the setting of the variety hypothesis, the learning problem becomes to find the underlying variety using sample data. We cast this learning problem into a Maximum A Posteriori optimization problem which we solve in terms of an eigenvalue computation. Having found the underlying variety, we explore the use of Gr\"obner bases and numerical methods to reveal information about its geometry. In particular, we propose a heuristic for numerically detecting points lying near the singular locus of the underlying variety.

This research investigates the enhancement of knowledge distillation (KD) processes in pre-trained models, an emerging field in knowledge transfer with significant implications for distributed training and federated learning environments. These environments benefit from reduced communication demands and accommodate various model architectures. Despite the adoption of numerous KD approaches for transferring knowledge among pre-trained models, a comprehensive understanding of KD's application in these scenarios is lacking. Our study conducts an extensive comparison of multiple KD techniques, including standard KD, tuned KD (via optimized temperature and weight parameters), deep mutual learning, and data partitioning KD. We assess these methods across various data distribution strategies to identify the most effective contexts for each. Through detailed examination of hyperparameter tuning, informed by extensive grid search evaluations, we pinpoint when adjustments are crucial to enhance model performance. This paper sheds light on optimal hyperparameter settings for distinct data partitioning scenarios and investigates KD's role in improving federated learning by minimizing communication rounds and expediting the training process. By filling a notable void in current research, our findings serve as a practical framework for leveraging KD in pre-trained models within collaborative and federated learning frameworks.

As Large Language Models (LLMs) are integrated with human daily applications rapidly, many societal and ethical concerns are raised regarding the behavior of LLMs. One of the ways to comprehend LLMs' behavior is to analyze their personalities. Many recent studies quantify LLMs' personalities using self-assessment tests that are created for humans. Yet many critiques question the applicability and reliability of these self-assessment tests when applied to LLMs. In this paper, we investigate LLM personalities using an alternate personality measurement method, which we refer to as the external evaluation method, where instead of prompting LLMs with multiple-choice questions in the Likert scale, we evaluate LLMs' personalities by analyzing their responses toward open-ended situational questions using an external machine learning model. We first fine-tuned a Llama2-7B model as the MBTI personality predictor that outperforms the state-of-the-art models as the tool to analyze LLMs' responses. Then, we prompt the LLMs with situational questions and ask them to generate Twitter posts and comments, respectively, in order to assess their personalities when playing two different roles. Using the external personality evaluation method, we identify that the obtained personality types for LLMs are significantly different when generating posts versus comments, whereas humans show a consistent personality profile in these two different situations. This shows that LLMs can exhibit different personalities based on different scenarios, thus highlighting a fundamental difference between personality in LLMs and humans. With our work, we call for a re-evaluation of personality definition and measurement in LLMs.