Federated Learning (FL) is a machine learning approach where nodes collaboratively train a global model. As more nodes participate in a round of FL, the effectiveness of individual model updates by nodes also diminishes. In this study, we increase the effectiveness of client updates by dividing the network into smaller partitions, or cohorts. We introduce Cohort-Parallel Federated Learning (CPFL): a novel learning approach where each cohort independently trains a global model using FL, until convergence, and the produced models by each cohort are then unified using one-shot Knowledge Distillation (KD) and a cross-domain, unlabeled dataset. The insight behind CPFL is that smaller, isolated networks converge quicker than in a one-network setting where all nodes participate. Through exhaustive experiments involving realistic traces and non-IID data distributions on the CIFAR-10 and FEMNIST image classification tasks, we investigate the balance between the number of cohorts, model accuracy, training time, and compute and communication resources. Compared to traditional FL, CPFL with four cohorts, non-IID data distribution, and CIFAR-10 yields a 1.9$\times$ reduction in train time and a 1.3$\times$ reduction in resource usage, with a minimal drop in test accuracy.

Workplace learning is used to train employees systematically, e.g., via e-learning or in 1:1 training. However, this is often deemed ineffective and costly. Whereas pure e-learning lacks the possibility of conversational exercise and personal contact, 1:1 training with human instructors involves a high level of personnel and organizational costs. Hence, pedagogical conversational agents (PCAs), based on generative AI, seem to compensate for the disadvantages of both forms. Following Action Design Research, this paper describes an organizational communication training with a Generative PCA (GenPCA). The evaluation shows promising results: the agent was perceived positively among employees and contributed to an improvement in self-determined learning. However, the integration of such agent comes not without limitations. We conclude with suggestions concerning the didactical methods, which are supported by a GenPCA, and possible improvements of such an agent for workplace learning.

Achieving energy efficiency in learning is a key challenge for artificial intelligence (AI) computing platforms. Biological systems demonstrate remarkable abilities to learn complex skills quickly and efficiently. Inspired by this, we present a hardware implementation of model-based reinforcement learning (MBRL) using spiking neural networks (SNNs) on mixed-signal analog/digital neuromorphic hardware. This approach leverages the energy efficiency of mixed-signal neuromorphic chips while achieving high sample efficiency through an alternation of online learning, referred to as the "awake" phase, and offline learning, known as the "dreaming" phase. The model proposed includes two symbiotic networks: an agent network that learns by combining real and simulated experiences, and a learned world model network that generates the simulated experiences. We validate the model by training the hardware implementation to play the Atari game Pong. We start from a baseline consisting of an agent network learning without a world model and dreaming, which successfully learns to play the game. By incorporating dreaming, the number of required real game experiences are reduced significantly compared to the baseline. The networks are implemented using a mixed-signal neuromorphic processor, with the readout layers trained using a computer in-the-loop, while the other layers remain fixed. These results pave the way toward energy-efficient neuromorphic learning systems capable of rapid learning in real world applications and use-cases.

Cognitive diagnosis is a fundamental and critical task in learning assessment, which aims to infer students' proficiency on knowledge concepts from their response logs. Current works assume each knowledge concept will certainly be tested and covered by multiple exercises. However, whether online or offline courses, it's hardly feasible to completely cover all knowledge concepts in several exercises. Restricted tests lead to undiscovered knowledge deficits, especially untested knowledge concepts(UKCs). In this paper, we propose a novel \underline{Dis}entangling Heterogeneous \underline{K}nowledge \underline{C}ognitive \underline{D}iagnosis framework on untested knowledge(DisKCD). Specifically, we leverage course grades, exercise questions, and resources to learn the potential representations of students, exercises, and knowledge concepts. In particular, knowledge concepts are disentangled into tested and untested based on the limiting actual exercises. We construct a heterogeneous relation graph network via students, exercises, tested knowledge concepts(TKCs), and UKCs. Then, through a hierarchical heterogeneous message-passing mechanism, the fine-grained relations are incorporated into the embeddings of the entities. Finally, the embeddings will be applied to multiple existing cognitive diagnosis models to infer students' proficiency on UKCs. Experimental results on real-world datasets show that the proposed model can effectively improve the performance of the task of diagnosing students' proficiency on UKCs. Our anonymous code is available at https://anonymous.4open.science/r/DisKCD.

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information. Traditional alignment methods based on reinforcement learning often struggle with the identified instability, whereas preference optimization methods are limited by their overfitting to pre-collected hard-label datasets. In this paper, we propose a novel LLM alignment framework named $i$REPO, which utilizes implicit Reward pairwise difference regression for Empirical Preference Optimization. Particularly, $i$REPO employs self-generated datasets labelled by empirical human (or AI annotator) preference to iteratively refine the aligned policy through a novel regression-based loss function. Furthermore, we introduce an innovative algorithm backed by theoretical guarantees for achieving optimal results under ideal assumptions and providing a practical performance-gap result without such assumptions. Experimental results with Phi-2 and Mistral-7B demonstrate that $i$REPO effectively achieves self-alignment using soft-label, self-generated responses and the logit of empirical AI annotators. Furthermore, our approach surpasses preference optimization baselines in evaluations using the Language Model Evaluation Harness and Multi-turn benchmarks.

Motivated by the use of LLM as a scientific assistant, our paper assesses the domain knowledge of LLMs We are beginning to see progress in language through their understanding of different mathematical model assisted scientific discovery. Motivated skills required to solve problems. Understanding by the use of LLMs as a general scientific can be measured in two ways: the degree to which it assistant, this paper assesses the domain solves problems correctly; and the degree to which it knowledge of LLMs through its understanding enables fast adaptation to new knowledge. Similarly, of different mathematical skills required "understanding" in an LLM has two facets: on the one to solve problems. In particular, we look at hand, pre-trained LLMs possess knowledge that allows not just what the pre-trained model already remarkable performance in zero-shot tasks; on the knows, but how it learned to learn from other hand, pre-trained LLMs can learn new knowledge, information during in-context learning or either by leveraging in-context learning or by instruction-tuning through exploiting the instruction-tuning from base parameters as initialization.

The workforce will need to continually upskill in order to meet the evolving demands of industry, especially working with robotic and autonomous systems. Current training methods are not scalable and do not adapt to the skills that learners already possess. In this work, we develop a system that automatically assesses learner skill in a quadrotor teleoperation task using temporal logic task specifications. This assessment is used to generate multimodal feedback based on the principles of effective formative feedback. Participants perceived the feedback positively. Those receiving formative feedback viewed the feedback as more actionable compared to receiving summary statistics. Participants in the multimodal feedback condition were more likely to achieve a safe landing and increased their safe landings more over the experiment compared to other feedback conditions. Finally, we identify themes to improve adaptive feedback and discuss and how training for complex psychomotor tasks can be integrated with learning theories.

Text generation has become more accessible than ever, and the increasing interest in these systems, especially those using large language models, has spurred an increasing number of related publications. We provide a systematic literature review comprising 244 selected papers between 2017 and 2024. This review categorizes works in text generation into five main tasks: open-ended text generation, summarization, translation, paraphrasing, and question answering. For each task, we review their relevant characteristics, sub-tasks, and specific challenges (e.g., missing datasets for multi-document summarization, coherence in story generation, and complex reasoning for question answering). Additionally, we assess current approaches for evaluating text generation systems and ascertain problems with current metrics. Our investigation shows nine prominent challenges common to all tasks and sub-tasks in recent text generation publications: bias, reasoning, hallucinations, misuse, privacy, interpretability, transparency, datasets, and computing. We provide a detailed analysis of these challenges, their potential solutions, and which gaps still require further engagement from the community. This systematic literature review targets two main audiences: early career researchers in natural language processing looking for an overview of the field and promising research directions, as well as experienced researchers seeking a detailed view of tasks, evaluation methodologies, open challenges, and recent mitigation strategies.

Gradient flows play a substantial role in addressing many machine learning problems. We examine the convergence in continuous-time of a \textit{Fisher-Rao} (Mean-Field Birth-Death) gradient flow in the context of solving convex-concave min-max games with entropy regularization. We propose appropriate Lyapunov functions to demonstrate convergence with explicit rates to the unique mixed Nash equilibrium.

With the availability of large pre-trained models, a modern workflow for building real-world machine learning solutions is to fine-tune such models on a downstream task with a relatively small domain-specific dataset. In such applications, one major challenge is that the small fine-tuning dataset does not have sufficient coverage of the distribution encountered when the model is deployed. It is thus important to design fine-tuning methods that are robust to out-of-distribution (OOD) data that are under-represented by the training data. This paper compares common fine-tuning methods to investigate their OOD performance and demonstrates that standard methods will result in a significant change to the pre-trained model so that the fine-tuned features overfit the fine-tuning dataset. However, this causes deteriorated OOD performance. To overcome this issue, we show that protecting pre-trained features leads to a fine-tuned model more robust to OOD generalization. We validate the feature protection methods with extensive experiments of fine-tuning CLIP on ImageNet and DomainNet.