StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond

Text-rich images have significant and extensive value, deeply integrated into various aspects of human life. Notably, both visual cues and linguistic symbols in text-rich images play crucial roles in information transmission but are accompanied by diverse challenges. Therefore, the efficient and effective understanding of text-rich images is a crucial litmus test for the capability of Vision-Language Models. We have crafted an efficient vision-language model, StrucTexTv3, tailored to tackle various intelligent tasks for text-rich images. The significant design of StrucTexTv3 is presented in the following aspects: Firstly, we adopt a combination of an effective multi-scale reduced visual transformer and a multi-granularity token sampler (MG-Sampler) as a visual token generator, successfully solving the challenges of high-resolution input and complex representation learning for text-rich images. Secondly, we enhance the perception and comprehension abilities of StrucTexTv3 through instruction learning, seamlessly integrating various text-oriented tasks into a unified framework. Thirdly, we have curated a comprehensive collection of high-quality text-rich images, abbreviated as TIM-30M, encompassing diverse scenarios like incidental scenes, office documents, web pages, and screenshots, thereby improving the robustness of our model. Our method achieved SOTA results in text-rich image perception tasks, and significantly improved performance in comprehension tasks. Among multimodal models with LLM decoder of approximately 1.8B parameters, it stands out as a leader, which also makes the deployment of edge devices feasible. In summary, the StrucTexTv3 model, featuring efficient structural design, outstanding performance, and broad adaptability, offers robust support for diverse intelligent application tasks involving text-rich images, thus exhibiting immense potential for widespread application.

Leveraging Foundation Model Automatic Data Augmentation Strategies and Skeletal Points for Hands Action Recognition in Industrial Assembly Lines

On modern industrial assembly lines, many intelligent algorithms have been developed to replace or supervise workers. However, we found that there were bottlenecks in both training datasets and real-time performance when deploying algorithms on actual assembly line. Therefore, we developed a promising strategy for expanding industrial datasets, which utilized large models with strong generalization abilities to achieve efficient, high-quality, and large-scale dataset expansion, solving the problem of insufficient and low-quality industrial datasets. We also applied this strategy to video action recognition. We proposed a method of converting hand action recognition problems into hand skeletal trajectory classification problems, which solved the real-time performance problem of industrial algorithms. In the "hand movements during wire insertion" scenarios on the actual assembly line, the accuracy of hand action recognition reached 98.8\%. We conducted detailed experimental analysis to demonstrate the effectiveness and superiority of the method, and deployed the entire process on Midea's actual assembly line.

LinkSAGE: Optimizing Job Matching Using Graph Neural Networks

We present LinkSAGE, an innovative framework that integrates Graph Neural Networks (GNNs) into large-scale personalized job matching systems, designed to address the complex dynamics of LinkedIns extensive professional network. Our approach capitalizes on a novel job marketplace graph, the largest and most intricate of its kind in industry, with billions of nodes and edges. This graph is not merely extensive but also richly detailed, encompassing member and job nodes along with key attributes, thus creating an expansive and interwoven network. A key innovation in LinkSAGE is its training and serving methodology, which effectively combines inductive graph learning on a heterogeneous, evolving graph with an encoder-decoder GNN model. This methodology decouples the training of the GNN model from that of existing Deep Neural Nets (DNN) models, eliminating the need for frequent GNN retraining while maintaining up-to-date graph signals in near realtime, allowing for the effective integration of GNN insights through transfer learning. The subsequent nearline inference system serves the GNN encoder within a real-world setting, significantly reducing online latency and obviating the need for costly real-time GNN infrastructure. Validated across multiple online A/B tests in diverse product scenarios, LinkSAGE demonstrates marked improvements in member engagement, relevance matching, and member retention, confirming its generalizability and practical impact.

LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations

The extraordinary performance of large language models has not only reshaped the research landscape in the field of NLP but has also demonstrated its exceptional applicative potential in various domains. However, the potential of these models in mining relationships from graph data remains under-explored. Graph neural networks, as a popular research area in recent years, have numerous studies on relationship mining. Yet, current cutting-edge research in graph neural networks has not been effectively integrated with large language models, leading to limited efficiency and capability in graph relationship mining tasks. A primary challenge is the inability of LLMs to deeply exploit the edge information in graphs, which is critical for understanding complex node relationships. This gap limits the potential of LLMs to extract meaningful insights from graph structures, limiting their applicability in more complex graph-based analysis. We focus on how to utilize existing LLMs for mining and understanding relationships in graph data, applying these techniques to recommendation tasks. We propose an innovative framework that combines the strong contextual representation capabilities of LLMs with the relationship extraction and analysis functions of GNNs for mining relationships in graph data. Specifically, we design a new prompt construction framework that integrates relational information of graph data into natural language expressions, aiding LLMs in more intuitively grasping the connectivity information within graph data. Additionally, we introduce graph relationship understanding and analysis functions into LLMs to enhance their focus on connectivity information in graph data. Our evaluation on real-world datasets demonstrates the framework's ability to understand connectivity information in graph data.

Performance Trade-off and Joint Waveform Design for MIMO-OFDM DFRC Systems

Dual-functional radar-communication (DFRC) has attracted considerable attention. This paper considers the frequency-selective multipath fading environment and proposes DFRC waveform design strategies based on multiple-input and multiple-output (MIMO) and orthogonal frequency division multiplexing (OFDM) techniques. In the proposed waveform design strategies, the Cramer-Rao bound (CRB) of the radar system, the inter-stream interference (ISI) and the achievable rate of the communication system, are respectively considered as the performance metrics. In this paper, we focus on the performance trade-off between the radar system and the communication system, and the optimization problems are formulated. In the ISI minimization based waveform design strategy, the optimization problem is convex and can be easily solved. In the achievable rate maximization based waveform design strategy, we propose a water-filling (WF) and sequential quadratic programming (SQP) based algorithm to derive the covariance matrix and the precoding matrix. Simulation results validate the proposed DFRC waveform designs and show that the achievable rate maximization based strategy has a better performance than the ISI minimization based strategy.

Large Scale Foundation Models for Intelligent Manufacturing Applications: A Survey

Although the applications of artificial intelligence especially deep learning had greatly improved various aspects of intelligent manufacturing, they still face challenges for wide employment due to the poor generalization ability, difficulties to establish high-quality training datasets, and unsatisfactory performance of deep learning methods. The emergence of large scale foundational models(LSFMs) had triggered a wave in the field of artificial intelligence, shifting deep learning models from single-task, single-modal, limited data patterns to a paradigm encompassing diverse tasks, multimodal, and pre-training on massive datasets. Although LSFMs had demonstrated powerful generalization capabilities, automatic high-quality training dataset generation and superior performance across various domains, applications of LSFMs on intelligent manufacturing were still in their nascent stage. A systematic overview of this topic was lacking, especially regarding which challenges of deep learning can be addressed by LSFMs and how these challenges can be systematically tackled. To fill this gap, this paper systematically expounded current statue of LSFMs and their advantages in the context of intelligent manufacturing. and compared comprehensively with the challenges faced by current deep learning models in various intelligent manufacturing applications. We also outlined the roadmaps for utilizing LSFMs to address these challenges. Finally, case studies of applications of LSFMs in real-world intelligent manufacturing scenarios were presented to illustrate how LSFMs could help industries, improve their efficiency.

AI-driven emergence of frequency information non-uniform distribution via THz metasurface spectrum prediction

Recently, artificial intelligence has been extensively deployed across various scientific disciplines, optimizing and guiding the progression of experiments through the integration of abundant datasets, whilst continuously probing the vast theoretical space encapsulated within the data. Particularly, deep learning models, due to their end-to-end adaptive learning capabilities, are capable of autonomously learning intrinsic data features, thereby transcending the limitations of traditional experience to a certain extent. Here, we unveil previously unreported information characteristics pertaining to different frequencies emerged during our work on predicting the terahertz spectral modulation effects of metasurfaces based on AI-prediction. Moreover, we have substantiated that our proposed methodology of simply adding supplementary multi-frequency inputs to the existing dataset during the target spectral prediction process can significantly enhance the predictive accuracy of the network. This approach effectively optimizes the utilization of existing datasets and paves the way for interdisciplinary research and applications in artificial intelligence, chemistry, composite material design, biomedicine, and other fields.

Collaborative Large Language Model for Recommender Systems

Recently, there is a growing interest in developing next-generation recommender systems (RSs) based on pretrained large language models (LLMs), fully utilizing their encoded knowledge and reasoning ability. However, the semantic gap between natural language and recommendation tasks is still not well addressed, leading to multiple issues such as spuriously-correlated user/item descriptors, ineffective language modeling on user/item contents, and inefficient recommendations via auto-regression, etc. In this paper, we propose CLLM4Rec, the first generative RS that tightly integrates the LLM paradigm and ID paradigm of RS, aiming to address the above challenges simultaneously. We first extend the vocabulary of pretrained LLMs with user/item ID tokens to faithfully model the user/item collaborative and content semantics. Accordingly, in the pretraining stage, a novel soft+hard prompting strategy is proposed to effectively learn user/item collaborative/content token embeddings via language modeling on RS-specific corpora established from user-item interactions and user/item features, where each document is split into a prompt consisting of heterogeneous soft (user/item) tokens and hard (vocab) tokens and a main text consisting of homogeneous item tokens or vocab tokens that facilitates stable and effective language modeling. In addition, a novel mutual regularization strategy is introduced to encourage the CLLM4Rec to capture recommendation-oriented information from user/item contents. Finally, we propose a novel recommendation-oriented finetuning strategy for CLLM4Rec, where an item prediction head with multinomial likelihood is added to the pretrained CLLM4Rec backbone to predict hold-out items based on the soft+hard prompts established from masked user-item interaction history, where recommendations of multiple items can be generated efficiently.

GraphLLM: Boosting Graph Reasoning Ability of Large Language Model

The advancement of Large Language Models (LLMs) has remarkably pushed the boundaries towards artificial general intelligence (AGI), with their exceptional ability on understanding diverse types of information, including but not limited to images and audio. Despite this progress, a critical gap remains in empowering LLMs to proficiently understand and reason on graph data. Recent studies underscore LLMs' underwhelming performance on fundamental graph reasoning tasks. In this paper, we endeavor to unearth the obstacles that impede LLMs in graph reasoning, pinpointing the common practice of converting graphs into natural language descriptions (Graph2Text) as a fundamental bottleneck. To overcome this impediment, we introduce GraphLLM, a pioneering end-to-end approach that synergistically integrates graph learning models with LLMs. This synergy equips LLMs with the ability to proficiently interpret and reason on graph data, harnessing the superior expressive power of graph learning models. Our empirical evaluations across four fundamental graph reasoning tasks validate the effectiveness of GraphLLM. The results exhibit a substantial average accuracy enhancement of 54.44%, alongside a noteworthy context reduction of 96.45% across various graph reasoning tasks.

From $O$ to $O)$ in Quadratic Programming

A "dark cloud" hangs over numerical optimization theory for decades, namely, whether an optimization algorithm $O(\log(n))$ iteration complexity exists. "Yes", this paper answers, with a new optimization algorithm and strict theory proof. It starts with box-constrained quadratic programming (Box-QP), and many practical optimization problems fall into Box-QP. General smooth quadratic programming (QP), nonsmooth Lasso, and support vector machine (or regression) can be reformulated as Box-QP via duality theory. It is the first time to present an $O(\log(n))$ iteration complexity QP algorithm, in particular, which behaves like a "direct" method: the required number of iterations is deterministic with exact value $\left\lceil\log\left(\frac{3.125n}{\epsilon}\right)/\log(1.5625)\right\rceil$. This significant breakthrough enables us to transition from the $O(\sqrt{n})$ to the $O(\log(n))$ optimization algorithm, whose amazing scalability is particularly relevant in today's era of big data and artificial intelligence.