State-of-the-art vision-language models (VLMs) still have limited performance in structural knowledge extraction, such as relations between objects. In this work, we present ViStruct, a training framework to learn VLMs for effective visual structural knowledge extraction. Two novel designs are incorporated. First, we propose to leverage the inherent structure of programming language to depict visual structural information. This approach enables explicit and consistent representation of visual structural information of multiple granularities, such as concepts, relations, and events, in a well-organized structured format. Second, we introduce curriculum-based learning for VLMs to progressively comprehend visual structures, from fundamental visual concepts to intricate event structures. Our intuition is that lower-level knowledge may contribute to complex visual structure understanding. Furthermore, we compile and release a collection of datasets tailored for visual structural knowledge extraction. We adopt a weakly-supervised approach to directly generate visual event structures from captions for ViStruct training, capitalizing on abundant image-caption pairs from the web. In experiments, we evaluate ViStruct on visual structure prediction tasks, demonstrating its effectiveness in improving the understanding of visual structures. The code is public at \url{https://github.com/Yangyi-Chen/vi-struct}.

Video semantic segmentation is a pivotal aspect of video representation learning. However, significant domain shifts present a challenge in effectively learning invariant spatio-temporal features across the labeled source domain and unlabeled target domain for video semantic segmentation. To solve the challenge, we propose a novel DA-STC method for domain adaptive video semantic segmentation, which incorporates a bidirectional multi-level spatio-temporal fusion module and a category-aware spatio-temporal feature alignment module to facilitate consistent learning for domain-invariant features. Firstly, we perform bidirectional spatio-temporal fusion at the image sequence level and shallow feature level, leading to the construction of two fused intermediate video domains. This prompts the video semantic segmentation model to consistently learn spatio-temporal features of shared patch sequences which are influenced by domain-specific contexts, thereby mitigating the feature gap between the source and target domain. Secondly, we propose a category-aware feature alignment module to promote the consistency of spatio-temporal features, facilitating adaptation to the target domain. Specifically, we adaptively aggregate the domain-specific deep features of each category along spatio-temporal dimensions, which are further constrained to achieve cross-domain intra-class feature alignment and inter-class feature separation. Extensive experiments demonstrate the effectiveness of our method, which achieves state-of-the-art mIOUs on multiple challenging benchmarks. Furthermore, we extend the proposed DA-STC to the image domain, where it also exhibits superior performance for domain adaptive semantic segmentation. The source code and models will be made available at \url{https://github.com/ZHE-SAPI/DA-STC}.

Instruction tuning is crucial for enabling Language Learning Models (LLMs) in responding to human instructions. The quality of instruction pairs used for tuning greatly affects the performance of LLMs. However, the manual creation of high-quality instruction datasets is costly, leading to the adoption of automatic generation of instruction pairs by LLMs as a popular alternative in the training of open-source LLMs. To ensure the high quality of LLM-generated instruction datasets, several approaches have been proposed. Nevertheless, existing methods either compromise dataset integrity by filtering a large proportion of samples, or are unsuitable for industrial applications. In this paper, instead of discarding low-quality samples, we propose CoachLM, a novel approach to enhance the quality of instruction datasets through automatic revisions on samples in the dataset. CoachLM is trained from the samples revised by human experts and significantly increases the proportion of high-quality samples in the dataset from 17.7% to 78.9%. The effectiveness of CoachLM is further assessed on various real-world instruction test sets. The results show that CoachLM improves the instruction-following capabilities of the instruction-tuned LLM by an average of 29.9%, which even surpasses larger LLMs with nearly twice the number of parameters. Furthermore, CoachLM is successfully deployed in a data management system for LLMs at Huawei, resulting in an efficiency improvement of up to 20% in the cleaning of 40k real-world instruction pairs. We release the training data and code of CoachLM (https://github.com/lunyiliu/CoachLM).

With the rapid development of artificial intelligence technology, large language models (LLMs) have become a hot research topic. Education plays an important role in human social development and progress. Traditional education faces challenges such as individual student differences, insufficient allocation of teaching resources, and assessment of teaching effectiveness. Therefore, the applications of LLMs in the field of digital/smart education have broad prospects. The research on educational large models (EduLLMs) is constantly evolving, providing new methods and approaches to achieve personalized learning, intelligent tutoring, and educational assessment goals, thereby improving the quality of education and the learning experience. This article aims to investigate and summarize the application of LLMs in smart education. It first introduces the research background and motivation of LLMs and explains the essence of LLMs. It then discusses the relationship between digital education and EduLLMs and summarizes the current research status of educational large models. The main contributions are the systematic summary and vision of the research background, motivation, and application of large models for education (LLM4Edu). By reviewing existing research, this article provides guidance and insights for educators, researchers, and policy-makers to gain a deep understanding of the potential and challenges of LLM4Edu. It further provides guidance for further advancing the development and application of LLM4Edu, while still facing technical, ethical, and practical challenges requiring further research and exploration.

Dynamic Graph Neural Networks (DGNNs) have emerged as the predominant approach for processing dynamic graph-structured data. However, the influence of temporal information on model performance and robustness remains insufficiently explored, particularly regarding how models address prediction tasks with different time granularities. In this paper, we explore the impact of time granularity when training DGNNs on dynamic graphs through extensive experiments. We examine graphs derived from various domains and compare three different DGNNs to the baseline model across four varied time granularities. We mainly consider the interplay between time granularities, model architectures, and negative sampling strategies to obtain general conclusions. Our results reveal that a sophisticated memory mechanism and proper time granularity are crucial for a DGNN to deliver competitive and robust performance in the dynamic link prediction task. We also discuss drawbacks in considered models and datasets and propose promising directions for future research on the time granularity of temporal graphs. Our benchmark suite and codebase are available at https://github.

Lifelong sequence generation (LSG), a problem in continual learning, aims to continually train a model on a sequence of generation tasks to learn constantly emerging new generation patterns while avoiding the forgetting of previous knowledge. Existing LSG methods mainly focus on maintaining old knowledge while paying little attention to knowledge transfer across tasks. In contrast, humans can better learn new tasks by leveraging previously acquired knowledge from similar tasks. Inspired by the learning paradigm of humans, we propose Dynamic Module Expansion and Adaptation (DMEA), which enables the model to dynamically determine the architecture for acquiring new knowledge based on task correlation and select the most similar previous tasks to facilitate adaptation to new tasks. In addition, as the learning process can easily be biased towards the current task which might cause more severe forgetting of previously learned knowledge, we propose dynamic gradient scaling to balance the learning of the current task and replayed tasks. With extensive experiments, we demonstrate that DMEA can consistently outperform existing methods in different LSG settings.

Learning style refers to a type of training mechanism adopted by an individual to gain new knowledge. As suggested by the VARK model, humans have different learning preferences, like Visual (V), Auditory (A), Read/Write (R), and Kinesthetic (K), for acquiring and effectively processing information. Our work endeavors to leverage this concept of knowledge diversification to improve the performance of model compression techniques like Knowledge Distillation (KD) and Mutual Learning (ML). Consequently, we use a single-teacher and two-student network in a unified framework that not only allows for the transfer of knowledge from teacher to students (KD) but also encourages collaborative learning between students (ML). Unlike the conventional approach, where the teacher shares the same knowledge in the form of predictions or feature representations with the student network, our proposed approach employs a more diversified strategy by training one student with predictions and the other with feature maps from the teacher. We further extend this knowledge diversification by facilitating the exchange of predictions and feature maps between the two student networks, enriching their learning experiences. We have conducted comprehensive experiments with three benchmark datasets for both classification and segmentation tasks using two different network architecture combinations. These experimental results demonstrate that knowledge diversification in a combined KD and ML framework outperforms conventional KD or ML techniques (with similar network configuration) that only use predictions with an average improvement of 2%. Furthermore, consistent improvement in performance across different tasks, with various network architectures, and over state-of-the-art techniques establishes the robustness and generalizability of the proposed model

A key property of deep neural networks (DNNs) is their ability to learn new features during training. This intriguing aspect of deep learning stands out most clearly in recently reported Grokking phenomena. While mainly reflected as a sudden increase in test accuracy, Grokking is also believed to be a beyond lazy-learning/Gaussian Process (GP) phenomenon involving feature learning. Here we apply a recent development in the theory of feature learning, the adaptive kernel approach, to two teacher-student models with cubic-polynomial and modular addition teachers. We provide analytical predictions on feature learning and Grokking properties of these models and demonstrate a mapping between Grokking and the theory of phase transitions. We show that after Grokking, the state of the DNN is analogous to the mixed phase following a first-order phase transition. In this mixed phase, the DNN generates useful internal representations of the teacher that are sharply distinct from those before the transition.

Influencer marketing has become a very popular tool to reach customers. Despite the rapid growth in influencer videos, there has been little research on the effectiveness of their constituent features in explaining video engagement. We study YouTube influencers and analyze their unstructured video data across text, audio and images using an "interpretable deep learning" framework that accomplishes both goals of prediction and interpretation. Our prediction-based approach analyzes unstructured data and finds that "what is said" in words (text) is more influential than "how it is said" in imagery (images) or acoustics (audio). Our novel interpretation-based approach is implemented after completion of model prediction by analyzing the same source of unstructured data to measure importance attributed to the video features. We eliminate several spurious relationships in two steps, identifying a subset of relationships which are confirmed using theory. We uncover novel findings that establish distinct associations for measures of shallow and deep engagement based on the dual-system framework of human thinking. Our approach is validated using simulated data, and we discuss the learnings from our findings for influencers and brands.

Engineering Design is undergoing a transformative shift with the advent of AI, marking a new era in how we approach product, system, and service planning. Large language models have demonstrated impressive capabilities in enabling this shift. Yet, with text as their only input modality, they cannot leverage the large body of visual artifacts that engineers have used for centuries and are accustomed to. This gap is addressed with the release of multimodal vision language models, such as GPT-4V, enabling AI to impact many more types of tasks. In light of these advancements, this paper presents a comprehensive evaluation of GPT-4V, a vision language model, across a wide spectrum of engineering design tasks, categorized into four main areas: Conceptual Design, System-Level and Detailed Design, Manufacturing and Inspection, and Engineering Education Tasks. Our study assesses GPT-4V's capabilities in design tasks such as sketch similarity analysis, concept selection using Pugh Charts, material selection, engineering drawing analysis, CAD generation, topology optimization, design for additive and subtractive manufacturing, spatial reasoning challenges, and textbook problems. Through this structured evaluation, we not only explore GPT-4V's proficiency in handling complex design and manufacturing challenges but also identify its limitations in complex engineering design applications. Our research establishes a foundation for future assessments of vision language models, emphasizing their immense potential for innovating and enhancing the engineering design and manufacturing landscape. It also contributes a set of benchmark testing datasets, with more than 1000 queries, for ongoing advancements and applications in this field.