This quasi-experimental study integrates a large language model (LLM) with expert qualitative analysis to examine how instructional design variations in computer-supported collaborative learning (CSCL) shape collaboration in data-centric programming. We collected 73 team transcripts from two contrasting CSCL designs deployed across five course offerings: a closed-ended variant with prescribed solution paths and auto-graded milestones, and an open-ended variant supporting exploratory tasks with multiple valid paths. LLM annotation revealed statistically significant differences in knowledge co-construction patterns: the open-ended design yielded a higher proportion of utterances focused on developing a shared understanding of problems and solutions. Guided by these quantitative results, human experts conducted qualitative coding that confirmed and enriched these findings, showing how open-ended tasks fostered elaborative solution negotiation while closed-ended structures promoted non-elaborative exchanges. Our contributions are: (1) instructional insights for data science education, demonstrating how open-ended CSCL designs better support collaborative sense-making essential for real-world data science projects; and (2) a documented workflow for human-LLM co-evaluation, providing the methodological detail necessary for others to replicate our process and apply it to future studies.

We propose Cross-Attention in Audio, Space, and Time (C$\text{A}^{2}$A2ST), a transformer-based method for holistic video recognition. Recognizing actions in videos requires both spatial and temporal understanding, yet most existing models lack a balanced spatio-temporal understanding of videos. To address this, we propose a novel two-stream architecture, called Cross-Attention in Space and Time (CAST), using only RGB input. In each layer of CAST, Bottleneck Cross-Attention (B-CA) enables spatial and temporal experts to exchange information and make synergistic predictions. For holistic video understanding, we extend CAST by integrating an audio expert, forming Cross-Attention in Visual and Audio (CAVA). We validate the CAST on benchmarks with different characteristics, EPIC-KITCHENS-100, Something-Something-V2, Kinetics-400, ActivityNet, and HD-EPIC to show balanced performance. We also validate the CAVA on audio-visual action recognition benchmarks, including UCF-101, VGG-Sound, KineticsSound, EPIC- SOUNDS, and HD-EPIC-SOUNDS. CAVA shows favorable performance on these datasets, demonstrating the effective information exchange among multiple experts within the B-CA module. In addition, C$\text{A}^{2}$A2ST combines CAST and CAVA by employing spatial, temporal, and audio experts through cross-attention, achieving balanced and holistic video understanding.

Recognizing human actions in videos requires spatial and temporal understanding. Most existing action recognition models lack a balanced spatio-temporal understanding of videos. In this work, we propose a novel two-stream architecture, called Cross-Attention in Space and Time (CAST), that achieves a balanced spatio-temporal understanding of videos using only RGB input. Our proposed bottleneck cross-attention mechanism enables the spatial and temporal expert models to exchange information and make synergistic predictions, leading to improved performance. We validate the proposed method with extensive experiments on public benchmarks with different characteristics: EPIC-Kitchens-100, Something-Something-V2, and Kinetics-400. Our method consistently shows favorable performance across these datasets, while the performance of existing methods fluctuates depending on the dataset characteristics. The code is available at https://github.com/KHU-VLL/CAST.

Both entity typing and relation extraction from text corpora are widely used to identify the semantic types of an entity and a relation in a knowledge graph (KG). Most existing approaches rely on a pre-defined set of entity types and relation types in a KG. They thus cannot map entity mentions (relation mentions) to unseen entity types (relation types). To fundamentally overcome the limitations, we should add new semantic types of entities and relations to a KG schema. However, schema expansion traditionally requires manual conceptualization through a user’s observation on the text corpus while assuming the existence of suitable target KG schemas. In this work, we propose anActive learning framework forKnowledge graphSchemaExpansion (AKSE), which can generate a new semantic type for KG schemas, without depending on a set of target schemas and human users’ observation. Specifically, a granularity based active learning algorithm determines whether a KG schema requires new semantic types or not. We also introduce a KG schema attention-based neural method which assigns semantic types to the entities and relationships extracted. To the best of our knowledge, our work is the first study to expand a KG schema with active learning.

In this paper, we introduce dynamic lifting to a quantum circuit-description language, following the Proto-Quipper language approach. Dynamic lifting allows programs to transfer the result of measuring quantum data - qubits - into classical data - booleans -. We propose a type system and an operational semantics for the language and we state safety properties. Next, we introduce a concrete categorical semantics for the proposed language, basing our approach on a recent model from Rios&Selinger for Proto-Quipper-M. Our approach is to construct on top of a concrete category of circuits with measurements a Kleisli category, capturing as a side effect the action of retrieving classical content out of a quantum memory. We then show a soundness result for this semantics.

News recommendation systems? purpose is to tackle the immense amount of news and offer personalized recommendations to users. A major issue in news recommendation is to capture the precise news representations for the efficacy of recommended items. Commonly, news contents are filled with well-known entities of different types. However, existing recommendation systems overlook exploiting external knowledge about entities and topical relatedness among the news. To cope with the above problem, in this paper, we propose Topic-Enriched Knowledge Graph Recommendation System(TEKGR). Three encoders in TEKGR handle news titles in two perspectives to obtain news representation embedding: (1) to extract meaning of news words without considering latent knowledge features in the news and (2) to extract semantic knowledge of news through topic information and contextual information from a knowledge graph. After obtaining news representation vectors, an attention network compares clicked news to the candidate news in order to get the user's final embedding. Our TEKGR model is superior to existing news recommendation methods by manipulating topical relations among entities and contextual features of entities. Experimental results on two public datasets show that our approach outperforms state-of-the-art deep recommendation approaches.

A large number of spatial knowledge graphs (SKGs) are available from spatially enriched knowledge bases, e.g., DBpedia and YAGO2. This provides a great chance to understand valuable information about the regions surrounding us. However, it is hard to comprehend SKGs due to the explosively growing volume and the complication of the graph structures. Thus we study the problem of similar region search (SRS), which is an easy-to-use but effective way to explore spatial data. The effectiveness of SRS highly depends on how to measure the region similarity. However, existing approaches cannot make use of the rich information contained in SKGs thus may lead to incorrect results. In this paper, we propose a spatial knowledge representation learning method for region similarity, namely SKRL4RS. SKRL4RS firstly encodes the spatial entities of an SKG into a vector space to make it easier to extract useful features. Then regions are represented by 3-D tensors using the spatial entity embeddings together with geographical information. Finally, region tensors are fed into the conventional triplet network to learn the feature vectors of regions. The region similarity measure learned by SKRL4RS can capture the hierarchical types, semantic relatedness, and relative locations of spatial entities inside a region. Experimental results on two real-world datasets show that our SKRL4RS outperforms the state-of-the-art by a significant margin in terms of the accuracy of measuring region similarity.

The paper presents a parallel computing model, called H-BSP, which adds a hierarchical concept to the BSP (Bulk Synchronous Parallel) computing model. A H-BSP program consists of a number of BSP groups which are dynamically created at run time and executed in a hierarchical fashion. H-BSP allows the algorithm designer to develop a more efficient algorithm by utilizing processor locality in the program. The paper describes the structure of the H-BSP model, complexity analysis and an example of the H-BSP algorithm. Also presented are the performance characteristics of the H-BSP algorithm based on simulation analysis. Simulation results show that H-BSP model takes advantages of processor locality and performs well in low bandwidth networks or in a constant valence architecture such as a 2 dimensional mesh. It is also proved that H-BSP model can predict algorithm performance better than the BSP model due to its locality preserving nature.