Search

Personalized recommendation serves as a ubiquitous channel for users to discover information or items tailored to their interests. However, traditional recommendation models primarily rely on unique IDs and categorical features for user-item matching, potentially overlooking the nuanced essence of raw item contents across multiple modalities such as text, image, audio, and video. This underutilization of multimodal data poses a limitation to recommender systems, especially in multimedia services like news, music, and short-video platforms. The recent advancements in pretrained multimodal models offer new opportunities and challenges in developing content-aware recommender systems. This survey seeks to provide a comprehensive exploration of the latest advancements and future trajectories in multimodal pretraining, adaptation, and generation techniques, as well as their applications to recommender systems. Furthermore, we discuss open challenges and opportunities for future research in this domain. We hope that this survey, along with our tutorial materials, will inspire further research efforts to advance this evolving landscape., Comment: Draft version submitted to KDD'2024 tutorials

Neuroscientific research has revealed that the complex brain network can be organized into distinct functional communities, each characterized by a cohesive group of regions of interest (ROIs) with strong interconnections. These communities play a crucial role in comprehending the functional organization of the brain and its implications for neurological conditions, including Autism Spectrum Disorder (ASD) and biological differences, such as in gender. Traditional models have been constrained by the necessity of predefined community clusters, limiting their flexibility and adaptability in deciphering the brain's functional organization. Furthermore, these models were restricted by a fixed number of communities, hindering their ability to accurately represent the brain's dynamic nature. In this study, we present a token clustering brain transformer-based model ($\texttt{TC-BrainTF}$) for joint community clustering and classification. Our approach proposes a novel token clustering (TC) module based on the transformer architecture, which utilizes learnable prompt tokens with orthogonal loss where each ROI embedding is projected onto the prompt embedding space, effectively clustering ROIs into communities and reducing the dimensions of the node representation via merging with communities. Our results demonstrate that our learnable community-aware model $\texttt{TC-BrainTF}$ offers improved accuracy in identifying ASD and classifying genders through rigorous testing on ABIDE and HCP datasets. Additionally, the qualitative analysis on $\texttt{TC-BrainTF}$ has demonstrated the effectiveness of the designed TC module and its relevance to neuroscience interpretations.

Large Language Models (LLM) based agents have shown promise in autonomously completing tasks across various domains, e.g., robotics, games, and web navigation. However, these agents typically require elaborate design and expert prompts to solve tasks in specific domains, which limits their adaptability. We introduce AutoManual, a framework enabling LLM agents to autonomously build their understanding through interaction and adapt to new environments. AutoManual categorizes environmental knowledge into diverse rules and optimizes them in an online fashion by two agents: 1) The Planner codes actionable plans based on current rules for interacting with the environment. 2) The Builder updates the rules through a well-structured rule system that facilitates online rule management and essential detail retention. To mitigate hallucinations in managing rules, we introduce \textit{case-conditioned prompting} strategy for the Builder. Finally, the Formulator agent compiles these rules into a comprehensive manual. The self-generated manual can not only improve the adaptability but also guide the planning of smaller LLMs while being human-readable. Given only one simple demonstration, AutoManual significantly improves task success rates, achieving 97.4\% with GPT-4-turbo and 86.2\% with GPT-3.5-turbo on ALFWorld benchmark tasks. The source code will be available soon.

The deep complex-valued neural network provides a powerful way to leverage complex number operations and representations, which has succeeded in several phase-based applications. However, most previously published networks have not fully accessed the impact of complex-valued networks in the frequency domain. Here, we introduced a unified complex-valued deep learning framework - artificial Fourier transform network (AFT-Net) - which combined domain-manifold learning and complex-valued neural networks. The AFT-Net can be readily used to solve the image inverse problems in domain-transform, especially for accelerated magnetic resonance imaging (MRI) reconstruction and other applications. While conventional methods only accept magnitude images, the proposed method takes raw k-space data in the frequency domain as inputs, allowing a mapping between the k-space domain and the image domain to be determined through cross-domain learning. We show that AFT-Net achieves superior accelerated MRI reconstruction and is comparable to existing approaches. Also, our approach can be applied to different tasks like denoised MRS reconstruction and different datasets with various contrasts. The AFT-Net presented here is a valuable preprocessing component for different preclinical studies and provides an innovative alternative for solving inverse problems in imaging and spectroscopy.

In the field of music information retrieval (MIR), cover song identification (CSI) is a challenging task that aims to identify cover versions of a query song from a massive collection. Existing works still suffer from high intra-song variances and inter-song correlations, due to the entangled nature of version-specific and version-invariant factors in their modeling. In this work, we set the goal of disentangling version-specific and version-invariant factors, which could make it easier for the model to learn invariant music representations for unseen query songs. We analyze the CSI task in a disentanglement view with the causal graph technique, and identify the intra-version and inter-version effects biasing the invariant learning. To block these effects, we propose the disentangled music representation learning framework (DisCover) for CSI. DisCover consists of two critical components: (1) Knowledge-guided Disentanglement Module (KDM) and (2) Gradient-based Adversarial Disentanglement Module (GADM), which block intra-version and inter-version biased effects, respectively. KDM minimizes the mutual information between the learned representations and version-variant factors that are identified with prior domain knowledge. GADM identifies version-variant factors by simulating the representation transitions between intra-song versions, and exploits adversarial distillation for effect blocking. Extensive comparisons with best-performing methods and in-depth analysis demonstrate the effectiveness of DisCover and the and necessity of disentanglement for CSI.

Schizophrenia is a chronic neuropsychiatric disorder that causes distinct structural alterations within the brain. We hypothesize that deep learning applied to a structural neuroimaging dataset could detect disease-related alteration and improve classification and diagnostic accuracy. We tested this hypothesis using a single, widely available, and conventional T1-weighted MRI scan, from which we extracted the 3D whole-brain structure using standard post-processing methods. A deep learning model was then developed, optimized, and evaluated on three open datasets with T1-weighted MRI scans of patients with schizophrenia. Our proposed model outperformed the benchmark model, which was also trained with structural MR images using a 3D CNN architecture. Our model is capable of almost perfectly (area under the ROC curve = 0.987) distinguishing schizophrenia patients from healthy controls on unseen structural MRI scans. Regional analysis localized subcortical regions and ventricles as the most predictive brain regions. Subcortical structures serve a pivotal role in cognitive, affective, and social functions in humans, and structural abnormalities of these regions have been associated with schizophrenia. Our finding corroborates that schizophrenia is associated with widespread alterations in subcortical brain structure and the subcortical structural information provides prominent features in diagnostic classification. Together, these results further demonstrate the potential of deep learning to improve schizophrenia diagnosis and identify its structural neuroimaging signatures from a single, standard T1-weighted brain MRI., Comment: 13 pages, 6 figures

Di Zhang,1 Qian Xu,1 Ning Wang,1 Yanting Yang,1 Jiaqi Liu,1 Guohua Yu,2 Xin Yang,3 Hui Xu,1 Hongbo Wang1 1School of Pharmacy, Key Laboratory of Molecular Pharmacology and Drug Evaluation, (Yantai University), Ministry of Education, Collaborative Innovation Center of Advanced Drug Delivery System and Biotech Drugs in Universities of Shandong, Yantai University, Yantai, People’s Republic of China; 2Department of Pathology, Yantai Yuhuangding Hospital, Yantai, People’s Republic of China; 3School of Chemistry and Chemical Engineering, Yantai University, Yantai, People’s Republic of China Background: Dose-dependent irreversible cardiac toxicity of doxorubicin (DOX) becomes a major obstacle for the clinical use. Nowadays much attention is being paid to combination therapy with DOX and antioxidant agents, which would improve the clinical efficacy by protecting from cardiotoxicity along with the maintained performance as an antitumor drug. With the assistance of nanoscience and polymer engineering, herein a complex polymeric micellar system was developed for co-loading DOX and a premium natural antioxidant curcumin (CUR), and we investigated whether this new formulation for DOX delivery could achieve such a goal. Methods: The dually loaded micelles co-encapsulating DOX and CUR (CPMDC) were prepared through thin-film rehydration by using the amphiphilic diblock copolymer monomethoxy poly(ethylene glycol) (mPEG)–poly(ε-caprolactone) (PCL)–N-t-butoxycarbonyl-phenylalanine (BP) synthesized by end-group modification of mPEG–PCL with BP. Quantitative analysis was conducted by HPLC methods for drugs in micelles or biosamples. Molecular dynamics simulation was performed using HyperChem software to illustrate interactions among copolymer and active pharmaceutical ingredients. The safety and antitumor efficacy were evaluated by in vitro viability of H9C2 cells, and tumor growth inhibition in tumor-bearing mice re

Di Zhang,1 Qian Xu,1 Ning Wang,1 Yanting Yang,1 Jiaqi Liu,1 Guohua Yu,2 Xin Yang,3 Hui Xu,1 Hongbo Wang1 1School of Pharmacy, Key Laboratory of Molecular Pharmacology and Drug Evaluation, (Yantai University), Ministry of Education, Collaborative Innovation Center of Advanced Drug Delivery System and Biotech Drugs in Universities of Shandong, Yantai University, Yantai, People’s Republic of China; 2Department of Pathology, Yantai Yuhuangding Hospital, Yantai, People’s Republic of China; 3School of Chemistry and Chemical Engineering, Yantai University, Yantai, People’s Republic of China Background: Dose-dependent irreversible cardiac toxicity of doxorubicin (DOX) becomes a major obstacle for the clinical use. Nowadays much attention is being paid to combination therapy with DOX and antioxidant agents, which would improve the clinical efficacy by protecting from cardiotoxicity along with the maintained performance as an antitumor drug. With the assistance of nanoscience and polymer engineering, herein a complex polymeric micellar system was developed for co-loading DOX and a premium natural antioxidant curcumin (CUR), and we investigated whether this new formulation for DOX delivery could achieve such a goal. Methods: The dually loaded micelles co-encapsulating DOX and CUR (CPMDC) were prepared through thin-film rehydration by using the amphiphilic diblock copolymer monomethoxy poly(ethylene glycol) (mPEG)–poly(ε-caprolactone) (PCL)–N-t-butoxycarbonyl-phenylalanine (BP) synthesized by end-group modification of mPEG–PCL with BP. Quantitative analysis was conducted by HPLC methods for drugs in micelles or biosamples. Molecular dynamics simulation was performed using HyperChem software to illustrate interactions among copolymer and active pharmaceutical ingredients. The safety and antitumor efficacy were evaluated by in vitro viability of H9C2 cells, and tumor growth inhibition in tumor-bearing mice re

楊炎廷., 手稿本, 複本據原稿影印., Thesis (M.A.)--香港中文大學硏究院歷史學部., Shou gao ben, fu ben ju yuan gao ying yin., Includes bibliographical references (leaves 277-301)., Yang Yanting., Thesis (M.A.)--Xianggang Zhong wen da xue yan jiu yuan li shi xue bu., 緒言 --- p.1-3, Chapter 第一章 --- 唐末五代至宋初卅縣衙門的演變 --- p.4-4, Chapter 第二章 --- 北宋的衙前役 --- p.15, Chapter 第一節 --- 衙前將吏 --- p.15-16, Chapter 第二節 --- 熙寧變法以前的衙前役, Chapter 甲 --- 一般制度 --- p.26-32, Chapter 乙 --- 長名衙前 --- p.32-37, Chapter 丙 --- 里正衙前、鄉戶衙前 --- p.37-65, Chapter 第三節 --- 熙寧變法以後的衙前役 --- p.65-88, Chapter 第三章 --- 北宋卅縣衙門的吏役 --- p.89, Chapter 第一節 --- 卅縣之吏人 --- p.91, Chapter 甲 --- 卅之吏人 --- p.91-100, Chapter 乙 --- 縣之吏人 --- p.100-103, Chapter 丙 --- 卅縣吏人在地方行政上所扮演的角色 --- p.104-112, Chapter 第二節 --- 卅縣之公人 --- p.112, Chapter 甲 --- 散從官、雜職、手力、 解子、所由 --- p.112-115, Chapter 乙 --- 卅之院虞侯 --- p.115-117, Chapter 丙 --- 縣之弓手 --- p.117-119, Chapter 丁 --- 卅縣的庫子、斗子、搯子、秤子、揀子、攔頭 --- p.119-122, Chapter 第四章 --- 北宋的鄉役制度, Chapter 第一節 --- 唐、五代鄉村制度的變 --- p.123-130, Chapter 第二節 --- 北宋前期的鄉村制度 --- p.130, Chapter 甲 --- 鄉之里正及鄉書手 --- p.137-141, Chapter 乙 --- 管之戶長 --- p.141-143, Chapter 丙 --- 耆之耆長、壯丁 --- p.143-149, Chapter 第三節 --- 熙寧變法以後鄉村制度的轉變 --- p.150-158, 結語 --- p.159-163, 注釋 --- p.164-276, 參考資料 --- p.277-301, http://library.cuhk.edu.hk/record=b5887923, Use of this resource is governed by the terms and conditions of the Creative Commons “Attribution-NonCommercial-NoDerivatives 4.0 International” License (http://creativecommons.org/licenses/by-nc-nd/4.0/)