This review explores the intersection of bio-plausible artificial intelligence in the form of Spiking Neural Networks (SNNs) with the analog In-Memory Computing (IMC) domain, highlighting their collective potential for low-power edge computing environments. Through detailed investigation at the device, circuit, and system levels, we highlight the pivotal synergies between SNNs and IMC architectures. Additionally, we emphasize the critical need for comprehensive system-level analyses, considering the inter-dependencies between algorithms, devices, circuit & system parameters, crucial for optimal performance. An in-depth analysis leads to identification of key system-level bottlenecks arising from device limitations which can be addressed using SNN-specific algorithm-hardware co-design techniques. This review underscores the imperative for holistic device to system design space co-exploration, highlighting the critical aspects of hardware and algorithm research endeavors for low-power neuromorphic solutions.

Preference-based reinforcement learning (PbRL) stands out by utilizing human preferences as a direct reward signal, eliminating the need for intricate reward engineering. However, despite its potential, traditional PbRL methods are often constrained by the indivisibility of annotations, which impedes the learning process. In this paper, we introduce a groundbreaking approach, Skill-Enhanced Preference Optimization Algorithm~(S-EPOA), which addresses the annotation indivisibility issue by integrating skill mechanisms into the preference learning framework. Specifically, we first conduct the unsupervised pretraining to learn useful skills. Then, we propose a novel query selection mechanism to balance the information gain and discriminability over the learned skill space. Experimental results on a range of tasks, including robotic manipulation and locomotion, demonstrate that S-EPOA significantly outperforms conventional PbRL methods in terms of both robustness and learning efficiency. The results highlight the effectiveness of skill-driven learning in overcoming the challenges posed by annotation indivisibility.

This underscores the critical role of information as a precursor to knowledge, rather than knowledge itself (Zins, 2007; Frické, 2009). In digital environments, symbols, letters, words, and phrases have the potential to contribute to knowledge formation, necessitating effective communication and optimal information presentation for Information Systems (IS) success (Delone & McLean, 2003; Venkatesh & Bala, 2008; ISO, 2019). Engagement, defined as the emotional, cognitive, and behavioral connection between users and technological resources, has emerged as a key metric for evaluating user experience (UX), reflecting user interaction depth with a system (O'Brien et al., 2020; Attfield et al., 2011; O'Brien & Cairns, 2016). The digitization of communication through Information and Communication Technologies (ICT) has revolutionized information conveyance, demanding engaging and effective digital content to ensure successful knowledge transmission and user retention (Beaudry, 2005; Dvir, 2018). Information Engagement (IE) has gained prominence, focusing on the quality of user-system interactions and the impact of digital content design on user decision-making and UX (ISO, 2019; O'Brien, 2020). IE is crucial in enhancing user interactions across domains such as education, government, and industry, aiming to foster meaningful user engagement with digital text (Choi et al., 2018; Feng et al., 2020; Han et al., 2022). Failure to achieve IE with digital text hinders content producers, yet overcoming this challenge is complicated by a lack of engaging information experience guidelines (Blythe, 2005; Overbeeke et al., 2003). Limited research on IE development has resulted in a scarcity of systematic approaches for its initiation, sustainment, and improvement (O'Brien, 2017; O'Brien & Toms, 2016).

This research focuses on developing a real-time posture monitoring and risk assessment system for manual lifting tasks using advanced AI and computer vision technologies. Musculoskeletal disorders (MSDs) are a significant concern for workers involved in manual lifting, and traditional methods for posture correction are often inadequate due to delayed feedback and lack of personalized assessment. Our proposed solution integrates AI-driven posture detection, detailed keypoint analysis, risk level determination, and real-time feedback delivered through a user-friendly web interface. The system aims to improve posture, reduce the risk of MSDs, and enhance user engagement. The research involves comprehensive data collection, model training, and iterative development to ensure high accuracy and user satisfaction. The solution's effectiveness is evaluated against existing methodologies, demonstrating significant improvements in real-time feedback and risk assessment. This study contributes to the field by offering a novel approach to posture correction that addresses existing gaps and provides practical, immediate benefits to users.

Due to high accuracy, BERT-like models have been widely adopted by discriminative text mining and web searching. However, large BERT-like models suffer from inefficient online inference, as they face the following two problems on GPUs. First, they rely on the large model depth to achieve high accuracy, which linearly increases the sequential computation on GPUs. Second, stochastic and dynamic online workloads cause extra costs. In this paper, we present Academus for low-latency online inference of BERT-like models. At the core of Academus is the novel student parallelism, which adopts boosting ensemble and stacking distillation to distill the original deep model into an equivalent group of parallel and shallow student models. This enables Academus to achieve the lower model depth (e.g., two layers) than baselines and consequently the lowest inference latency without affecting the accuracy.For occasional workload bursts, it can temporarily decrease the number of students with minimal accuracy loss to improve throughput. Additionally, it employs specialized system designs for student parallelism to better handle stochastic online workloads. We conduct comprehensive experiments to verify the effectiveness. The results show that Academus outperforms the baselines by 4.1X~1.6X in latency without compromising accuracy, and achieves up to 22.27X higher throughput for workload bursts.

In this work, we address the question of how to enhance signal-agnostic searches by leveraging multiple testing strategies. Specifically, we consider hypothesis tests relying on machine learning, where model selection can introduce a bias towards specific families of new physics signals. We show that it is beneficial to combine different tests, characterised by distinct choices of hyperparameters, and that performances comparable to the best available test are generally achieved while providing a more uniform response to various types of anomalies. Focusing on the New Physics Learning Machine, a methodology to perform a signal-agnostic likelihood-ratio test, we explore a number of approaches to multiple testing, such as combining p-values and aggregating test statistics.

Large language models (LLMs) have become increasingly prevalent in our daily lives, leading to an expectation for LLMs to be trustworthy -- - both accurate and well-calibrated (the prediction confidence should align with its ground truth correctness likelihood). Nowadays, fine-tuning has become the most popular method for adapting a model to practical usage by significantly increasing accuracy on downstream tasks. Despite the great accuracy it achieves, we found fine-tuning is still far away from satisfactory trustworthiness due to "tuning-induced mis-calibration". In this paper, we delve deeply into why and how mis-calibration exists in fine-tuned models, and how distillation can alleviate the issue. Then we further propose a brand new method named Efficient Trustworthy Distillation (FIRST), which utilizes a small portion of teacher's knowledge to obtain a reliable language model in a cost-efficient way. Specifically, we identify the "concentrated knowledge" phenomenon during distillation, which can significantly reduce the computational burden. Then we apply a "trustworthy maximization" process to optimize the utilization of this small portion of concentrated knowledge before transferring it to the student. Experimental results demonstrate the effectiveness of our method, where better accuracy (+2.3%) and less mis-calibration (-10%) are achieved on average across both in-domain and out-of-domain scenarios, indicating better trustworthiness.

Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data. Empirical observations indicate that such algorithms are able to learn a shared representation across tasks, which is regarded as a key factor in their success. However, the in-depth theoretical understanding of the learning dynamics and the origin of the shared representation remains underdeveloped. In this work, we investigate the meta-learning dynamics of the non-linear two-layer neural networks trained on streaming tasks in the teach-student scenario. Through the lens of statistical physics analysis, we characterize the macroscopic behavior of the meta-training processes, the formation of the shared representation, and the generalization ability of the model on new tasks. The analysis also points to the importance of the choice of certain hyper-parameters of the learning algorithms.

Evolving networks are complex data structures that emerge in a wide range of systems in science and engineering. Learning expressive representations for such networks that encode their structural connectivity and temporal evolution is essential for downstream data analytics and machine learning applications. In this study, we introduce a self-supervised method for learning representations of temporal networks and employ these representations in the dynamic link prediction task. While temporal networks are typically characterized as a sequence of interactions over the continuous time domain, our study focuses on their discrete-time versions. This enables us to balance the trade-off between computational complexity and precise modeling of the interactions. We propose a recurrent message-passing neural network architecture for modeling the information flow over time-respecting paths of temporal networks. The key feature of our method is the contrastive training objective of the model, which is a combination of three loss functions: link prediction, graph reconstruction, and contrastive predictive coding losses. The contrastive predictive coding objective is implemented using infoNCE losses at both local and global scales of the input graphs. We empirically show that the additional self-supervised losses enhance the training and improve the model's performance in the dynamic link prediction task. The proposed method is tested on Enron, COLAB, and Facebook datasets and exhibits superior results compared to existing models.

Large language models (LLMs) are aligned with human preferences by reinforcement learning from human feedback (RLHF). Effective data sampling is crucial for RLHF, as it determines the efficiency of model training, ensuring that models learn from the informative samples. To achieve better data generation, we propose a new sampling method called Preference-Guided Reflective Sampling (PRS). PRS frames the response generation as an optimization process to the explicitly specified user preference described in natural language. It employs a tree-based generation framework to enable an efficient sampling process, which guides the direction of generation through preference and better explores the sampling space with adaptive self-refinement. Notably, PRS can align LLMs to diverse preferences. We study preference-controlled text generation for instruction following and keyword-focused document summarization. Our findings indicate that PRS, across different LLM policies, generates training data with much higher rewards than strong baselines. PRS also excels in post-RL training.