Timely, personalized feedback is essential for students learning programming, especially as class sizes expand. LLM-based tools like ChatGPT offer instant support, but reveal direct answers with code, which may hinder deep conceptual engagement. We developed CodeAid, an LLM-based programming assistant delivering helpful, technically correct responses, without revealing code solutions. For example, CodeAid can answer conceptual questions, generate pseudo-code with line-by-line explanations, and annotate student's incorrect code with fix suggestions. We deployed CodeAid in a programming class of 700 students for a 12-week semester. A thematic analysis of 8,000 usages of CodeAid was performed, further enriched by weekly surveys, and 22 student interviews. We then interviewed eight programming educators to gain further insights on CodeAid. Findings revealed students primarily used CodeAid for conceptual understanding and debugging, although a minority tried to obtain direct code. Educators appreciated CodeAid's educational approach, and expressed concerns about occasional incorrect feedback and students defaulting to ChatGPT.

Agents based on Large Language Models (LLMs) are increasingly permeating various domains of human production and life, highlighting the importance of aligning them with human values. The current alignment of AI systems primarily focuses on passively aligning LLMs through human intervention. However, agents possess characteristics like receiving environmental feedback and self-evolution, rendering the LLM alignment methods inadequate. In response, we propose an evolutionary framework for agent evolution and alignment, named EvolutionaryAgent, which transforms agent alignment into a process of evolution and selection under the principle of survival of the fittest. In an environment where social norms continuously evolve, agents better adapted to the current social norms will have a higher probability of survival and proliferation, while those inadequately aligned dwindle over time. Experimental results assessing the agents from multiple perspectives in aligning with social norms demonstrate that EvolutionaryAgent can align progressively better with the evolving social norms while maintaining its proficiency in general tasks. Effectiveness tests conducted on various open and closed-source LLMs as the foundation for agents also prove the applicability of our approach.

One of the most prestigious universities in the country is offering a course in playing video games as part of a shocking 40,000-a-year curriculum. The University of California (UC), Berkeley will launch a course in'The Art of Fighting Games' - which aims to make students better at video games for its Spring 2024 curriculum. The class will focus on the Japanese video game, 'Street Fighter III 3rd Strike,' with homework assignments consisting of students actually recording themselves playing the game, according to the class syllabus. University of California Berkeley is offering a course in'The Art of Fighting Games' Prerequisites are not required and students will not be graded based on their performance. UC Berkeley labels the class as an'introduction to fighting games, geared towards people with less than 100 hours in the genre,' but the university does not explain how the class could help students enter and succeed in life after college. Enrollment continues through January 24 and the university has encouraged students to sign up by stating: 'The only thing you do need is a willingness to learn and fail!' The university continues to explain that students will be graded on their'eagerness, commitment to improvement, and effort in the course assignments.'

Japan's Slim (Smart Lander for Investigating Moon) mission has now touched on the Moon. If this proves to have been a safe landing, Japan will become only the fifth country to land on the moon. Slim has completed its descent to the lunar surface and we are awaiting confirmation of whether the landing was a success. JAXA, Japan's space agency, expects the landing to take around 20 minutes, with touchdown expected by 15:20 GMT. MailOnline will also be bringing you all the latest updates as the landing progresses, so make sure you check back in!

Existing multimodal sentiment analysis tasks are highly rely on the assumption that the training and test sets are complete multimodal data, while this assumption can be difficult to hold: the multimodal data are often incomplete in real-world scenarios. Therefore, a robust multimodal model in scenarios with randomly missing modalities is highly preferred. Recently, CLIP-based multimodal foundational models have demonstrated impressive performance on numerous multimodal tasks by learning the aligned cross-modal semantics of image and text pairs, but the multimodal foundational models are also unable to directly address scenarios involving modality absence. To alleviate this issue, we propose a simple and effective framework, namely TRML, Toward Robust Multimodal Learning using Multimodal Foundational Models. TRML employs generated virtual modalities to replace missing modalities, and aligns the semantic spaces between the generated and missing modalities. Concretely, we design a missing modality inference module to generate virtual modaliites and replace missing modalities. We also design a semantic matching learning module to align semantic spaces generated and missing modalities. Under the prompt of complete modality, our model captures the semantics of missing modalities by leveraging the aligned cross-modal semantic space. Experiments demonstrate the superiority of our approach on three multimodal sentiment analysis benchmark datasets, CMU-MOSI, CMU-MOSEI, and MELD.

Large Language Models (LLMs) have upended decades of pedagogy in computing education. Students previously learned to code through \textit{writing} many small problems with less emphasis on code reading and comprehension. Recent research has shown that free code generation tools powered by LLMs can solve introductory programming problems presented in natural language with ease. In this paper, we propose a new way to teach programming with Prompt Problems. Students receive a problem visually, indicating how input should be transformed to output, and must translate that to a prompt for an LLM to decipher. The problem is considered correct when the code that is generated by the student prompt can pass all test cases. In this paper we present the design of this tool, discuss student interactions with it as they learn, and provide insights into this new class of programming problems as well as the design tools that integrate LLMs.

This chapter is a preprint from our book by , focusing on leveraging machine learning (ML) in chemical and polyolefin manufacturing optimization. It's crafted for both novices and seasoned professionals keen on the latest ML applications in chemical processes. We trace the evolution of AI and ML in chemical industries, delineate core ML components, and provide resources for ML beginners. A detailed discussion on various ML methods is presented, covering regression, classification, and unsupervised learning techniques, with performance metrics and examples. Ensemble methods, deep learning networks, including MLP, DNNs, RNNs, CNNs, and transformers, are explored for their growing role in chemical applications. Practical workshops guide readers through predictive modeling using advanced ML algorithms. The chapter culminates with insights into science-guided ML, advocating for a hybrid approach that enhances model accuracy. The extensive bibliography offers resources for further research and practical implementation. This chapter aims to be a thorough primer on ML's practical application in chemical engineering, particularly for polyolefin production, and sets the stage for continued learning in subsequent chapters. Please cite the original work [169,170] when referencing.

We introduce a cryptographic method to hide an arbitrary secret payload in the response of a Large Language Model (LLM). A secret key is required to extract the payload from the model's response, and without the key it is provably impossible to distinguish between the responses of the original LLM and the LLM that hides a payload. In particular, the quality of generated text is not affected by the payload. Our approach extends a recent result of Christ, Gunn and Zamir (2023) who introduced an undetectable watermarking scheme for LLMs.

Sensor-based human activity recognition (HAR) has been an active research area, owing to its applications in smart environments, assisted living, fitness, healthcare, etc. Recently, deep learning based end-to-end training has resulted in state-of-the-art performance in domains such as computer vision and natural language, where large amounts of annotated data are available. However, large quantities of annotated data are not available for sensor-based HAR. Moreover, the real-world settings on which the HAR is performed differ in terms of sensor modalities, classification tasks, and target users. To address this problem, transfer learning has been employed extensively. In this survey, we focus on these transfer learning methods in the application domains of smart home and wearables-based HAR. In particular, we provide a problem-solution perspective by categorizing and presenting the works in terms of their contributions and the challenges they address. We also present an updated view of the state-of-the-art for both application domains. Based on our analysis of 205 papers, we highlight the gaps in the literature and provide a roadmap for addressing them. This survey provides a reference to the HAR community, by summarizing the existing works and providing a promising research agenda.

Multiobjective optimization is a hot topic in the artificial intelligence and operations research communities. The design and development of multiobjective methods is a frequent task for researchers and practitioners. As a result of this vibrant activity, a myriad of techniques have been proposed in the literature to date, demonstrating a significant effectiveness for dealing with situations coming from a wide range of real-world areas. This paper is focused on a multiobjective problem related to optimizing Infrastructure-as-Code deployment configurations. The system implemented for solving this problem has been coined as IaC Optimizer Platform (IOP). Despite the fact that a prototypical version of the IOP has been introduced in the literature before, a deeper analysis focused on the resolution of the problem is needed, in order to determine which is the most appropriate multiobjective method for embedding in the IOP. The main motivation behind the analysis conducted in this work is to enhance the IOP performance as much as possible. This is a crucial aspect of this system, deeming that it will be deployed in a real environment, as it is being developed as part of a H2020 European project. Going deeper, we resort in this paper to nine different evolutionary computation-based multiobjective algorithms. For assessing the quality of the considered solvers, 12 different problem instances have been generated based on real-world settings. Results obtained by each method after 10 independent runs have been compared using Friedman's non-parametric tests. Findings reached from the tests carried out lad to the creation of a multi-algorithm system, capable of applying different techniques according to the user's needs.