This study evaluated the ability of ChatGPT to generate simulated data for theory replication and validation, focusing on the Computational Thinking Scale (CTS). The CTS model was replicated ten times, resulting in 10 trial models and 4,427 simulated responses. Each trial was analyzed using Structural Equation Modeling (SEM) to evaluate validity, reliability, and consistency. The results showed that ChatGPT-simulated data performed comparably to the original models. Key metrics—including Composite Reliability (simulated: 0.767–0.816; original: 0.84–0.88), Average Variance Extracted (simulated: 0.455–0.563; original: 0.57–0.67), Cronbach’s Alpha (simulated: 0.595–0.702; original: 0.74–0.83), and R-squared (simulated: 0.215–0.33; original: 0.38–0.43)—were lower but aligned. Similar patterns were observed in structural path coefficients (simulated: 0.015–0.504; original: 0.20–0.43), further supporting comparability. These findings highlight the potential of ChatGPT as a generative tool for research simulations, enabling cost-effective, scalable methodological testing and a pathway for future investigation.

The progress on generative models has led to significant advances on text-to-video (T2V) generation, yet the motion controllability of generated videos remains limited. Existing motion transfer methods explored the motion representations of reference videos to guide generation. Nevertheless, these methods typically rely on sample-specific optimization strategy, resulting in high computational burdens. In this paper, we propose EfficientMT, a novel and efficient end-to-end framework for video motion transfer. By leveraging a small set of synthetic paired motion transfer samples, EfficientMT effectively adapts a pretrained T2V model into a general motion transfer framework that can accurately capture and reproduce diverse motion patterns. Specifically, we repurpose the backbone of the T2V model to extract temporal information from reference videos, and further propose a scaler module to distill motion-related information. Subsequently, we introduce a temporal integration mechanism that seamlessly incorporates reference motion features into the video generation process. After training on our self-collected synthetic paired samples, EfficientMT enables general video motion transfer without requiring test-time optimization. Extensive experiments demonstrate that our EfficientMT outperforms existing methods in efficiency while maintaining flexible motion controllability. Our code will be available https://github.com/PrototypeNx/EfficientMT.

Customized text-to-image generation, which aims to learn user-specified concepts with a few images, has drawn significant attention recently. However, existing methods usually suffer from overfitting issues and entangle the subject-unrelated information (e.g., background and pose) with the learned concept, limiting the potential to compose concept into new scenes. To address these issues, we propose the DETEX, a novel approach that learns the disentangled concept embedding for flexible customized text-to-image generation. Unlike conventional methods that learn a single concept embedding from the given images, our DETEX represents each image using multiple word embeddings during training, i.e., a learnable image-shared subject embedding and several image-specific subject-unrelated embeddings. To decouple irrelevant attributes (i.e., background and pose) from the subject embedding, we further present several attribute mappers that encode each image as several image-specific subject-unrelated embeddings. To encourage these unrelated embeddings to capture the irrelevant information, we incorporate them with corresponding attribute words and propose a joint training strategy to facilitate the disentanglement. During inference, we only use the subject embedding for image generation, while selectively using image-specific embeddings to retain image-specified attributes. Extensive experiments demonstrate that the subject embedding obtained by our method can faithfully represent the target concept, while showing superior editability compared to the state-of-the-art methods. Our code will be available at https://github.com/PrototypeNx/DETEX.

Graph neural networks (GNNs) have achieved remarkable performance in many graph analytics tasks such as node classification, link prediction and graph clustering. Existing GNN systems (e.g., PyG and DGL) adopt a tensor-centric programming model and train GNNs with manually written operators. Such design results in poor usability due to the large semantic gap between the API and the GNN models, and suffers from inferior efficiency because of high memory consumption and massive data movement. We demonstrateSeastar, a novel GNN training framework that adopts avertex-centric programming paradigm and supportsautomatic kernel generation, to simplify model development and improve training efficiency. We will (i) show how to express GNN models succinctly using a visual "drag-and-drop'' interface or Seastar's vertex-centric python API; (ii) demonstrate the performance advantage of Seastar over existing GNN systems in convergence speed, training throughput and memory consumption; and (iii) illustrate how Seastar's optimizations (e.g., operator fusion and constant folding) improve training efficiency by profiling the run-time performance.

We present a modular semantic account of Bayesian inference algorithms for probabilistic programming languages, as used in data science and machine learning. Sophisticated inference algorithms are often explained in terms of composition of smaller parts. However, neither their theoretical justification nor their implementation reflects this modularity. We show how to conceptualise and analyse such inference algorithms as manipulating intermediate representations of probabilistic programs using higher-order functions and inductive types, and their denotational semantics. Semantic accounts of continuous distributions use measurable spaces. However, our use of higher-order functions presents a substantial technical difficulty: it is impossible to define a measurable space structure over the collection of measurable functions between arbitrary measurable spaces that is compatible with standard operations on those functions, such as function application. We overcome this difficulty using quasi-Borel spaces, a recently proposed mathematical structure that supports both function spaces and continuous distributions. We define a class of semantic structures for representing probabilistic programs, and semantic validity criteria for transformations of these representations in terms of distribution preservation. We develop a collection of building blocks for composing representations. We use these building blocks to validate common inference algorithms such as Sequential Monte Carlo and Markov Chain Monte Carlo. To emphasize the connection between the semantic manipulation and its traditional measure theoretic origins, we use Kock's synthetic measure theory. We demonstrate its usefulness by proving a quasi-Borel counterpart to the Metropolis-Hastings-Green theorem.

Traversing an algebraic datatype by hand requires boilerplate code which duplicates the structure of the datatype. Datatype-generic programming (DGP) aims to eliminate such boilerplate code by decomposing algebraic datatypes into type constructor applications from which generic traversals can be synthesized. However, different traversals require different decompositions, which yield isomorphic but unequal types. This hinders the interoperability of different DGP techniques. In this paper, we propose Fωμ, an extension of the higher-order polymorphic lambda calculus Fω with records, variants, and equirecursive types. We prove the soundness of the type system, and show that type checking for first-order recursive types is decidable with a practical type checking algorithm. In our soundness proof we define type equality by interpreting types as infinitary λ-terms (in particular, Berarducci-trees). To decide type equality we β-normalize types, and then use an extension of equivalence checking for usual equirecursive types. Thanks to equirecursive types, new decompositions for a datatype can be added modularly and still interoperate with each other, allowing multiple DGP techniques to work together. We sketch how generic traversals can be synthesized, and apply these components to some examples. Since the set of datatype decomposition becomes extensible, System Fωμ enables using DGP techniques incrementally, instead of planning for them upfront or doing invasive refactoring.

If the result of an expensive computation is invalidated by a small change to the input, the old result should be updated incrementally instead of reexecuting the whole computation. We incrementalize programs through their derivative. A derivative maps changes in the program's input directly to changes in the program's output, without reexecuting the original program. We present a program transformation taking programs to their derivatives, which is fully static and automatic, supports first-class functions, and produces derivatives amenable to standard optimization.