检索结果-内蒙古大学图书馆

S-INF: Towards Realistic Indoor Scene Synthesis via Scene Implicit Neural Field 39

学校读者我要写书评

暂无评论

S-INF: Towards Realistic Indoor Scene Synthesis via Scene Im...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liang, Zixi Xu, Guowei Wu, Haifeng Huang, Ye Li, Wen Duan, Lixin Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China School of Computer Science and Engineering University of Electronic Science and Technology of China China Sichuan Provincial Key Laboratory for Human Disease Gene Study The Center for Medical Genetics Department of Laboratory Medicine Sichuan Academy of Medical Sciences Sichuan Provincial People’s Hospital UESTC China

ISBN: (纸本)157735897X

Learning-based methods have become increasingly popular in 3D indoor scene synthesis (ISS), showing superior performance over traditional optimization-based approaches. These learning-based methods typically model distributions on simple yet explicit scene representations using generative models. However, due to the oversimplified explicit representations that overlook detailed information and the lack of guidance from multimodal relationships within the scene, most learning-based methods struggle to generate indoor scenes with realistic object arrangements and styles. In this paper, we introduce a new method, Scene Implicit Neural Field (S-INF), for indoor scene synthesis, aiming to learn meaningful representations of multimodal relationships, to enhance the realism of indoor scene synthesis. S-INF assumes that the scene layout is often related to the object-detailed information. It disentangles the multimodal relationships into scene layout relationships and detailed object relationships, fusing them later through implicit neural fields (INFs). By learning specialized scene layout relationships and projecting them into S-INF, we achieve a realistic generation of scene layout. Additionally, S-INF captures dense and detailed object relationships through differentiable rendering, ensuring stylistic consistency across objects. Through extensive experiments on the benchmark 3D-FRONT dataset, we demonstrate that our method consistently achieves state-of-the-art performance under different types of ISS. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Jialin Zhang, Zhuosheng Zhao, Hai School of Mathematical Sciences Shanghai Jiao Tong University China Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Machine reading comprehension (MRC) poses new challenges over logical reasoning, which aims to understand the implicit logical relations entailed in the given contexts and perform inference over them. Due to the complexity of logic, logical relations exist at different granularity levels. However, most existing methods of logical reasoning individually focus on either entity-aware or discourse-based information but ignore the hierarchical relations that may even have mutual effects. In this paper, we propose a holistic graph network (HGN) which deals with context at both discourse level and word level, as the basis for logical reasoning, to provide a more fine-grained relation extraction. Specifically, node-level and type-level relations, which can be interpreted as bridges in the reasoning process, are modeled by a hierarchical interaction mechanism to improve the interpretation of MRC systems. Experimental results on logical reasoning QA datasets (ReClor and LogiQA) and natural language inference datasets (SNLI and ANLI) show the effectiveness and generalization of our method, and in-depth analysis verifies its capability to understand complex logical relations. Copyright © 2023, The Authors. All rights reserved.

关键词： Complex networks

Unveiling Vulnerability of Self-Attention

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liong, Khai Jiet Wu, Hongqiu Zhao, Hai Xiaoshan, Li Minjie, Bian Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Technology Innovation Department Shanghai Data Group Co. Ltd China Shanghai Data Group Co. Ltd China

Pre-trained language models (PLMs) are shown to be vulnerable to minor word changes, which poses a big threat to real-world systems. While previous studies directly focus on manipulating word inputs, they are limited by their means of generating adversarial samples, lacking generalization to versatile real-world attack. This paper studies the basic structure of transformer-based PLMs, the self-attention (SA) mechanism. (1) We propose a powerful perturbation technique HackAttend, which perturbs the attention scores within the SA matrices via meticulously crafted attention masks. We show that state-of-the-art PLMs fall into heavy vulnerability that minor attention perturbations (1%) can produce a very high attack success rate (98%). Our paper expands the conventional text attack of word perturbations to more general structural perturbations. (2) We introduce S-Attend, a novel smoothing technique that effectively makes SA robust via structural perturbations. We empirically demonstrate that this simple yet effective technique achieves robust performance on par with adversarial training when facing various text attackers. Code is publicly available at ***/liongkj/HackAttend. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

Biomolecular condensates and disease pathogenesis

学校读者我要写书评

暂无评论

science China(Life sciences) 2024年第9期67卷 1792-1832页

作者： Ke Ruan Ge Bai Yanshan Fang Dan Li Tingting Li Xingguo Liu Boxun Lu Qing Lu Zhou Songyang Shuguo Sun Zheng Wang Xin Zhang Wen Zhou Hong Zhang The First Affiliated Hospital&School of Life Sciences Ministry of Education Key Laboratory for Membrane-less Organelles&Cellular DynamicsHefei National Research Center for Interdisciplinary Sciences at the MicroscaleCenter for Advanced Interdisciplinary Science and Biomedicine of IHMDivision of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefei 230027China Nanhu Brain-computer Interface Institute Hangzhou 311100China Department of Neurology of Second Affiliated Hospital and School of Brain Science and Brain Medicine Zhejiang University School of MedicineHangzhou 310058China Interdisciplinary Research Center on Biology and Chemistry Shanghai Institute of Organic ChemistryChinese Academy of SciencesShanghai 201210China University of Chinese Academy of Sciences Beijing 100049China Bio-X Institutes Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders(Ministry of Education)Shanghai Jiao Tong UniversityShanghai 200030China Department of Biomedical Informatics School of Basic Medical SciencesPeking University Health Science CenterBeijing 100191China CAS Key Laboratory of Regenerative Biology Joint School of Life SciencesGuangzhou Institutes of Biomedicine and HealthChinese Academy of SciencesGuangzhou 510530China Joint School of Life Sciences Guangzhou Medical UniversityGuangzhou 510000China Neurology Department at Huashan Hospital State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain ScienceInstitutes of Brain ScienceSchool of Life SciencesFudan UniversityShanghai 200433 China Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders Ministry of EducationBio-X InstitutesShanghai Jiao Tong UniversityShanghai 200030China State Key Laboratory of Biocontrol MOE Key Laboratory of Gene Function and Regulation and Guangzhou Key Laboratory of Healthy Aging ResearchSchool of Life SciencesSun Yat-sen Memorial HospitalSun Yat-sen UniversityGuangzhou 510275China Department of Human Anatomy Hist

Biomolecular condensates or membraneless organelles(MLOs)formed by liquid-liquid phase separation(LLPS)divide intracellular spaces into discrete compartments for specific *** of LLPS or aberrant phase transition that disturbs the formation or material states of MLOs is closely correlated with neurodegeneration,tumorigenesis,and many other pathological ***,we summarize the recent progress in development of methods to monitor phase separation and we discuss the biogenesis and function of MLOs formed through phase *** then present emerging proof-of-concept examples regarding the disruption of phase separation homeostasis in a diverse array of clinical conditions including neurodegenerative disorders,hearing loss,cancers,and immunological ***,we describe the emerging discovery of chemical modulators of phase separation.

关键词： liquid-liquid phase separation biomolecular condensate membraneless organelle

HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion and Intensity of Emotion Classes from Meme Images using Single and Multi Modalities 1

学校读者我要写书评

暂无评论

HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion ...

1st Workshop on Multimodal Fact-Checking and Hate Speech Detection, DE-FACTIFY 2022

作者： Nguyen, Thanh Tin Pham, Nhat Truong Nguyen, Ngoc Duy Nguyen, Hai Nguyen, Long H. Kim, Yong-Guk Human Computer Interaction Lab Department of Computer Engineering Sejong University Seoul Korea Republic of Division of Computational Mechatronics Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam Institute for Intelligent Systems Research and Innovation Deakin University Victoria Australia Khoury College of Computer Sciences Northeastern University Boston United States Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam

Nowadays, memes found on internet are overwhelming. Although they are innocuous and sometimes entertaining, there exist memes that contain sarcasm, offensive, or motivational feelings. In this study, several approaches are proposed to solve the multiple modality problem in analysing the given meme dataset. The imbalance issue has been addressed by using a new Auto Augmentation method and the uncorrelation issue has been mitigated by adopting deep Canonical Correlation Analysis to find the most correlated projections of visual and textual feature embedding. In addition, both stacked attention and multi-hop attention network are employed to efficiently generate aggregated features. As a result, our team, i.e. HCILab, achieved a weighted F1 score of 0.4995 for sentiment analysis, 0.7414 for emotion classification, and 0.5301 for scale/intensity of emotion classes on the leaderboard. This results are obtained by using concatenation between image and text model and our code can be found at https://***/JMRa8. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (***)

关键词： Sentiment analysis

RBP-Former: Joint Prediction of RNA-protein Binding Sites on Full-length RNA Transcripts for Multiple RBPs

学校读者我要写书评

暂无评论

RBP-Former: Joint Prediction of RNA-protein Binding Sites on...

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yichong Li Xiaojian Liu Fan Cheng Xiaoyong Pan Yang Yang Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

RNA-binding proteins (RBPs) are essential for gene expression, and the complex RNA-protein interaction mechanisms require analysis of global RNA information. Therefore, accurate prediction of RBP binding sites on full-length RNA transcripts is crucial for understanding these mechanisms and their roles in diseases. While machine learning methods can predict RBP binding to RNA fragments, extending this to full-length transcripts presents challenges due to sequence length and data imbalance. In this paper, we introduce RBP-Former, a binding site joint prediction model designed specifically for full-length RNA transcripts that can be used for multiple RBPs. This model processes information at both coarse and fine-grained levels to fully exploit sequence data and its interactions with multiple RBPs. We develop multi-level imbalance learning strategies, achieving favorable results on imbalanced data. Our method outperforms existing methods in predicting binding sites on full-length RNA transcripts for multiple RBPs, demonstrating its effectiveness in handling imbalanced label and sample distributions.

关键词： Proteins Protein engineering Accuracy RNA Machine learning Predictive models Data models Gene expression Bioinformatics Diseases

Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Yiyang Zhao, Hai Zhang, Zhuosheng Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Multi-turn dialogue modeling as a challenging branch of natural language understanding (NLU), aims to build representations for machines to understand human dialogues, which provides a solid foundation for multiple downstream tasks. Recent studies of dialogue modeling commonly employ pre-trained language models (PrLMs) to encode the dialogue history as successive tokens, which is insufficient in capturing the temporal characteristics of dialogues. Therefore, we propose Bidirectional Information Decoupling Network (BiDeN) as a universal dialogue encoder, which explicitly incorporates both the past and future contexts and can be generalized to a wide range of dialogue-related tasks. Experimental results on datasets of different downstream tasks demonstrate the universality and effectiveness of our BiDeN. The official implementation of BiDeN is available at https://***/EricLee8/BiDeN. © 2022, CC BY.

关键词： Modeling languages

How Deep is Love in LLMs’ Hearts? Exploring Semantic Size in human-like Cognition

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yao, Yao Yang, Yifei Ma, Xinbei Yang, Dongjie Zhang, Zhuosheng Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 Shanghai China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan University Wuhan430072 China

How human cognitive abilities are formed has long captivated researchers. However, a significant challenge lies in developing meaningful methods to measure these complex processes. With the advent of large language models (LLMs), which now rival human capabilities in various domains, we are presented with a unique testbed to investigate human cognition through a new lens. Among the many facets of cognition, one particularly crucial aspect is the concept of semantic size—the perceived magnitude of both abstract and concrete words or concepts. This study seeks to investigate whether LLMs exhibit similar tendencies in understanding semantic size, thereby providing insights into the underlying mechanisms of human cognition. We begin by exploring metaphorical reasoning, comparing how LLMs and humans associate abstract words with concrete objects of varying sizes. Next, we examine LLMs’ internal representations to evaluate their alignment with human cognitive processes. Our findings reveal that multi-modal training is crucial for LLMs to achieve more human-like understanding, suggesting that real-world, multi-modal experiences are similarly vital for human cognitive development. Lastly, we examine whether LLMs are influenced by attention-grabbing headlines with larger semantic sizes in a real-world web shopping scenario. The results show that multi-modal LLMs are more emotionally engaged in decision-making, but this also introduces potential biases, such as the risk of manipulation through clickbait headlines. Ultimately, this study offers a novel perspective on how LLMs interpret and internalize language, from the smallest concrete objects to the most profound abstract concepts like ‘love’. The insights gained not only improve our understanding of LLMs but also provide new avenues for exploring the cognitive abilities that define human intelligence. Our code and dataset is publicly available at https://***/Zoeyyao27/LLM-Semantic-Size-Understanding. © 2025, CC BY.

关键词： Semantics

Generative or Contrastive? Phrase Reconstruction for Better Sentence Representation Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wu, Bohong Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Though offering amazing contextualized token-level representations, current pre-trained language models actually take less attention on acquiring sentence-level representation during its self-supervised pre-training. If self-supervised learning can be distinguished into two subcategories, generative and contrastive, then most existing studies show that sentence representation learning may more benefit from the contrastive methods but not the generative methods. However, contrastive learning cannot be well compatible with the common token-level generative self-supervised learning, and does not guarantee good performance on downstream semantic retrieval tasks. Thus, to alleviate such obvious inconveniences, we instead propose a novel generative self-supervised learning objective based on phrase reconstruction. Empirical studies show that our generative learning may yield powerful enough sentence representation and achieve performance in Sentence Textual Similarity (STS) tasks on par with contrastive learning. Further, in terms of unsupervised setting, our generative method outperforms previous state-of-the-art SimCSE on the benchmark of downstream semantic retrieval tasks. © 2022, CC BY.

关键词： Semantics