Hierarchical Structure-Property Alignment for Data-Efficient Molecular Generation and Editing
School of Computer Science and Engineering（计算机科学与工程学院）；Central South University（中南大学）；Institute for Infocomm Research Agency for Science, Technology and Research (A* STAR)（信息通信研究所（A* STAR））
Ziyu Fan, Zhijian Huang, Yahan Li, Xiaowen Hu, Siyuan Shen, Yunliang Wang, Zeyu Zhong, Shuhong Liu, Shuning Yang, Shangqian Wu, Min Wu, Lei Deng
Property-constrained molecular generation and editing are crucial in AI-driven drug discovery but remain hindered by two factors: (i) capturing the complex relationships between molecular structures and multiple properties remains challenging, and (ii) the narrow coverage and incomplete annotations of molecular properties weaken the effectiveness of property-based models. To tackle these limitations, we propose HSPAG, a data-efficient framework featuring hierarchical structure-property alignment. By treating SMILES and molecular properties as complementary modalities, the model learns their relationships at atom, substructure, and whole-molecule levels. Moreover, we select representative samples through scaffold clustering and hard samples via an auxiliary variational auto-encoder (VAE), substantially reducing the required pre-training data. In addition, we incorporate a property relevance-aware masking mechanism and diversified perturbation strategies to enhance generation quality under sparse annotations. Experiments demonstrate that HSPAG captures fine-grained structure-property relationships and supports controllable generation under multiple property constraints. Two real-world case studies further validate the editing capabilities of HSPAG.
Matthias Anderer GmbH（Matthias Anderer有限公司）；Central University of Finance and Economics（中央财经大学）
Hierarchical forecasting with intermittent time series is a challenge in both research and empirical studies. Extensive research focuses on improving the accuracy of each hierarchy, especially the intermittent time series at bottom levels. Then hierarchical reconciliation could be used to improve the overall performance further. In this paper, we present a \emph{hierarchical-forecasting-with-alignment} approach that treats the bottom level forecasts as mutable to ensure higher forecasting accuracy on the upper levels of the hierarchy. We employ a pure deep learning forecasting approach N-BEATS…
Controllable Value Alignment in Large Language Models through Neuron-Level Editing
National University of Singapore（新加坡国立大学）；Hefei University of Technology（合肥工业大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；ST Engineering Ltd.（ST工程有限公司）
Preference Alignment on Diffusion Model: A Comprehensive Survey for Image Generation and Editing
University of Liverpool（利物浦大学）；Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；University of Edinburgh（爱丁堡大学）；University of Bristol（布里斯托大学）；University of Exeter（埃克塞特大学）
We introduce agents that use object-oriented reasoning to consider alternate states of the world in order to more quickly find solutions to problems. Specifically, a hierarchical controller directs a low-level agent to behave as if objects in the scene were added, deleted, or modified. The actions taken by the controller are defined over a graph-based representation of the scene, with actions corresponding to adding, deleting, or editing the nodes of a graph. We present preliminary results on three environments, demonstrating that our approach can achieve similar levels of reward as non-hierar…
EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
Institute for Clarity in Documentation（文档清晰度研究所）；Inria Paris-Rocquencourt（法国国家信息与自动化研究所巴黎-罗康库尔中心）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕默研究实验室）
TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment
Max Planck Institute for Informatics, Saarland Informatics Campus, Saarbrücken, Germany（马克斯·普朗克研究所信息学院，萨尔兰信息学院，德国萨尔布吕肯）；Department of Language Science and Technology, Saarland University, Saarbrücken, Germany（语言科学与技术系，萨尔兰大学，德国萨尔布吕肯）
Most existing metric learning methods focus on learning a similarity or distance measure relying on similar and dissimilar relations between sample pairs. However, pairs of samples cannot be simply identified as similar or dissimilar in many real-world applications, e.g., multi-label learning, label distribution learning. To this end, relation alignment metric learning (RAML) framework is proposed to handle the metric learning problem in those scenarios. But RAML learn a linear metric, which can't model complex datasets. Combining with deep learning and RAML framework, we propose a hierarchica…
DSO National Laboratories（新加坡国防科学技术局国家实验室）；Georgia Institute of Technology（佐治亚理工学院）
In many machine learning applications, it is necessary to meaningfully aggregate, through alignment, different but related datasets. Optimal transport (OT)-based approaches pose alignment as a divergence minimization problem: the aim is to transform a source dataset to match a target dataset using the Wasserstein distance as a divergence measure. We introduce a hierarchical formulation of OT which leverages clustered structure in data to improve alignment in noisy, ambiguous, or multimodal settings. To solve this numerically, we propose a distributed ADMM algorithm that also exploits the Sinkh…
DashFusion: Dual-stream Alignment with Hierarchical Bottleneck Fusion for Multimodal Sentiment Analysis
School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；Beijing National Research Center for Information Science and Technology, Tsinghua University（清华大学信息科学与技术国家研究中心）；Department of Automation, Tsinghua University（清华大学自动化系）
HIGHT: Hierarchical Graph Tokenization for Molecule-Language Alignment
MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Carnegie Mellon University（卡内基梅隆大学）；The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；University of Maryland, College Park（马里兰大学学院市分校）；National University of Singapore（新加坡国立大学）
Vision and Language Pretraining has become the prevalent approach for tackling multimodal downstream tasks. The current trend is to move towards ever larger models and pretraining datasets. This computational headlong rush does not seem reasonable in the long term to move toward sustainable solutions, and de facto excludes academic laboratories with limited resources. In this work, we propose a new framework, dubbed ViCHA, that efficiently exploits the input data to boost the learning by: (a) a new hierarchical cross-modal alignment loss, (b) new self-supervised scheme based on masked image mo…
