Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. Existing KD and QAT works focus on improving the accuracy of quantized models from the network output perspective by designing better KD loss functions or optimizing QAT's forward and backward propagation. However, limited attention has been given to understanding the impact of input transformations, such as data augmentation (DA). The relationship between quantization-aware KD and DA remains unexplored. In this paper, we address the question: how to select a good DA in quantization-aware KD, especially for the models with low precisions? We propose a novel metric which evaluates DAs according to their capacity to maximize the Contextual Mutual Information--the information not directly related to an image's label--while also ensuring the predictions for each class are close to the ground truth labels on average. The proposed method automatically ranks and selects DAs, requiring minimal training overhead, and it is compatible with any KD or QAT algorithm. Extensive evaluations demonstrate that selecting DA strategies using our metric significantly improves state-of-the-art QAT and KD works across various model architectures and datasets.

Evaluating sign language generation is often done through back-translation, where generated signs are first recognized back to text and then compared to a reference using text-based metrics. However, this two-step evaluation pipeline introduces ambiguity: it not only fails to capture the multimodal nature of sign language-such as facial expressions, spatial grammar, and prosody-but also makes it hard to pinpoint whether evaluation errors come from sign generation model or the translation system used to assess it. In this work, we propose SiLVERScore, a novel semantically-aware embedding-based evaluation metric that assesses sign language generation in a joint embedding space. Our contributions include: (1) identifying limitations of existing metrics, (2) introducing SiLVERScore for semantically-aware evaluation, (3) demonstrating its robustness to semantic and prosodic variations, and (4) exploring generalization challenges across datasets. On PHOENIX-14T and CSL-Daily datasets, SiLVERScore achieves near-perfect discrimination between correct and random pairs (ROC AUC = 0.99, overlap < 7%), substantially outperforming traditional metrics.

Eye-tracking offers rich insights into student cognition and engagement, but remains underutilized in classroom-facing educational technology due to challenges in data interpretation and accessibility. In this paper, we present the iterative design and evaluation of a gaze-based learning analytics dashboard for English Language Arts (ELA), developed through five studies involving teachers and students. Guided by user-centered design and data storytelling principles, we explored how gaze data can support reflection, formative assessment, and instructional decision-making. Our findings demonstrate that gaze analytics can be approachable and pedagogically valuable when supported by familiar visualizations, layered explanations, and narrative scaffolds. We further show how a conversational agent, powered by a large language model (LLM), can lower cognitive barriers to interpreting gaze data by enabling natural language interactions with multimodal learning analytics. We conclude with design implications for future EdTech systems that aim to integrate novel data modalities in classroom contexts.

Accessible communication through sign language is vital for deaf communities, 1 yet robotic solutions are often costly and limited. This study presents VulcanV3, a low- 2 cost, open-source, 3D-printed ambidextrous robotic hand capable of reproducing the full 3 American Sign Language (ASL) alphabet (52 signs for right- and left-hand configurations). 4 The system employs 23 direct-drive servo actuators for precise finger and wrist movements, 5 controlled by an Arduino Mega with dual PCA9685 modules. Unlike most humanoid upper- 6 limb systems, which rarely employ direct-drive actuation, VulcanV3 achieves complete ASL 7 coverage with a reversible design. All CAD files and code are released under permissive 8 open-source licenses to enable replication. Empirical tests confirmed accurate reproduction 9 of all 52 ASL handshapes, while a participant study (n = 33) achieved 96.97% recognition 10 accuracy, improving to 98.78% after video demonstration. VulcanV3 advances assistive 11 robotics by combining affordability, full ASL coverage, and ambidexterity in an openly 12 shared platform, contributing to accessible communication technologies and inclusive 13 innovation.

Abstraction--the ability to recognize and distill essential computational patterns from complex problem statements--is a foundational skill in computer science, critical both for human problem-solvers and coding-oriented large language models (LLMs). Despite recent advances in training LLMs for code generation using reinforcement learning (RL), most existing approaches focus primarily on superficial pattern recognition, overlooking explicit training for abstraction. In this study, we propose AR$^2$ (Adversarial Reinforcement Learning for Abstract Reasoning), a novel framework explicitly designed to enhance the abstraction abilities of LLMs. AR$^2$ employs a teacher model to transform kernel problems into narrative-rich, challenging descriptions without changing their fundamental logic. Simultaneously, a student coding model is trained to solve these complex narrative problems by extracting their underlying computational kernels. Experimental results demonstrate that AR$^2$ substantially improves the student model's accuracy on previously unseen, challenging programming tasks, underscoring abstraction as a key skill for enhancing LLM generalization.

--In today's information-rich era, learners have access to abundant educational resources, but the lack of practice materials tailored to these resources presents a significant challenge. This project addresses that gap by developing a multimodal question generation system that can automatically generate diverse question types from various content formats. This project lays the foundation for automated, scalable, and intelligent question generation, carefully balancing resource efficiency, robust functionality and a smooth user experience. Creating assessment questions is a time-consuming and labor-intensive task for educators. Traditional methods require manual extraction of information from materials, which can lead to inconsistencies and errors. Additionally, students often struggle to find varied practice questions that cover all aspects of the material they are studying. With the increasing use of multimedia in educational content, there is a growing need for systems that can process various data types, including text, diagrams, and audio recordings.

-- Vision-based tactile sensors (VBTS) have gained widespread application in robotic hands, grippers and prosthetics due to their high spatial resolution, low manufacturing costs, and ease of customization. While VBTSs have common design features, such as a camera module, they can differ in a rich diversity of sensing principles, material compositions, multimodal approaches, and data interpretation methods. Here, we propose a novel classification of VBTS that categorizes the technology into two primary sensing principles based on the underlying transduction of contact into a tactile image: the Marker-Based Transduction Principle and the Intensity-Based Transduction Principle. Marker-Based Transduction interprets tactile information by detecting marker displacement and changes in marker density. Depending on the design of the contact module, Marker-Based Transduction can be further divided into two subtypes: Simple Marker-Based (SMB) and Morphological Marker-Based (MMB) mechanisms. Similarly, the Intensity-Based Transduction Principle encompasses the Reflective Layer-based (RLB) and Transparent Layer-Based (TLB) mechanisms. This paper provides a comparative study of the hardware characteristics of these four types of sensors including various combination types, and discusses the commonly used methods for interpreting tactile information. This comparison reveals some current challenges faced by VBTS technology and directions for future research. In robotic systems, tactile sensing is fundamental for enabling robots to interact with their environment through physical contact. By delivering real-time tactile feedback, such as object stiffness, local force, slip and contact position feedback, this capability empowers robotic systems to achieve precise object manipulation while preventing damage [1]-[4]. CL, HL and YL were supported by the the China Scholarship Council and Bristol joint scholarship. EP and NL were supported by the Horizon Europe research and innovation program under grant agreement No. 101120823 (MANiBOT) and the Royal Society International Collaboration Awards (South Korea). NL was also supported by an award from ARIA on'Democratising Hardware And Control For Robot Dexterity'. Lepora) HL is with School of Robotics, Xi'an Jiaotong-Liverpool University, China, and was with the School of Engineering Mathematics and T ech-nology, and Bristol Robotics Laboratory, University of Bristol, Bristol, U.K. (Email: haoran.li@xjtlu.edu.cn). YL, CL, MY, EP, and NL are with the School of Engineering Mathematics and T echnology, and Bristol Robotics Laboratory, University of Bristol, Bristol, U.K. (Email: {yijiong.lin, Traditional electronic technologies such as piezoelectric and piezoresistive sensor arrays have been considered promising due to their high temporal resolution and thin profiles.

How to balance training accuracy and adversarial robustness has become a challenge since the birth of deep learning. Here, we introduce a geometry-aware deep learning framework that leverages layer-wise local training to sculpt the internal representations of deep neural networks. This framework promotes intra-class compactness and inter-class separation in feature space, leading to manifold smoothness and adversarial robustness against white or black box attacks. The performance can be explained by an energy model with Hebbian coupling between elements of the hidden representation. Our results thus shed light on the physics of learning in the direction of alignment between biological and artificial intelligence systems. Using the current framework, the deep network can assimilate new information into existing knowledge structures while reducing representation interference.

The ability of large language models (LLMs) to process and reason over long textual inputs is critical for a wide range of real-world applications. However, progress in this area is significantly constrained by the absence of high-quality, diverse, and verifiable long-context datasets suitable for both training and evaluation. This work introduces a modular, extensible framework for synthetic long-context data generation via prompt-based interaction with LLMs. The framework supports multiple training and alignment objectives, including Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Group Relative Policy Optimization (GRPO). It encompasses four core generation paradigms: multi-turn conversational dialogues, document-grounded input-output pairs, verifiable instruction-response tasks, and long-context reasoning examples. Through templated prompting, a model-agnostic architecture, and metadata-enriched outputs, the proposed approach facilitates scalable, controllable, and purpose-aligned dataset creation for advancing long-context capabilities in LLMs.

Robotic Manipulation (RM) is central to the advancement of autonomous robots, enabling them to interact with and manipulate objects in real-world environments. This survey focuses on RM methodologies that leverage imitation learning, a powerful technique that allows robots to learn complex manipulation skills by mimicking human demonstrations. We identify and analyze the most influential studies in this domain, selected based on community impact and intrinsic quality. For each paper, we provide a structured summary, covering the research purpose, technical implementation, hierarchical classification, input formats, key priors, strengths and limitations, and citation metrics. Additionally, we trace the chronological development of imitation learning techniques within RM policy (RMP), offering a timeline of key technological advancements. Where available, we report benchmark results and perform quantitative evaluations to compare existing methods. By synthesizing these insights, this review provides a comprehensive resource for researchers and practitioners, highlighting both the state of the art and the challenges that lie ahead in the field of robotic manipulation through imitation learning.