Department of Electronics, Information and Bioengineering, Politecnico di Milano（电子工程与信息学院，米兰理工学院）；Osservatorio Astronomico di Roma, INAF（罗马天文台，INAF）；AstroAI, Center for Astrophysics | | Harvard & Smithsonian（AstroAI，哈佛与史密松尼天体物理中心）；Center for Computational Astrophysics, Institute for Advanced Study/The Flatiron Institute（计算天文学中心，高级研究院/Flatiron研究所）
Nicolò Oreste Pinciroli Vago, Rocco Di Tella, Carolina Cuesta-Lázaro, Michael J. Smith, Cecilia Garraffo, Rafael Martínez-Galarza
备注：
Accepted at the 2nd Workshop on Foundation Models for Science (ICLR 2026)
Astronomers have acquired vast repositories of multimodal data, including images, spectra, and time series, complemented by decades of literature that analyzes astrophysical sources. Still, these data sources are rarely systematically integrated. This work introduces a contrastive learning framework designed to align X-ray spectra with domain knowledge extracted from scientific literature, facilitating the development of shared multimodal representations. Establishing this connection is inherently complex, as scientific texts encompass a broader and more diverse physical context than spectra. We propose a contrastive pipeline that achieves a 20% Recall@1% when retrieving texts from spectra, proving that a meaningful alignment between these modalities is not only possible but capable of accelerating the interpretation of rare or poorly understood sources. Furthermore, the resulting shared latent space effectively encodes physically significant information. By fusing spectral and textual data, we improve the estimation of 20 physical variables by 16-18% over unimodal spectral baselines. Our results indicate that a Mixture of Experts (MoE) strategy, which leverages both unimodal and shared representations, yields superior performance. Finally, outlier analysis within the multimodal latent space identifies high-priority targets for follow-up investigation, including a candidate pulsating ULX (PULX) and a gravitational lens system. Importantly, this framework can be extended to other scientific domains where aligning observational data with existing literature is possible.
NeiGAD: Augmenting Graph Anomaly Detection via Spectral Neighbor Information
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；School of Computer Science and Information Technology, Adelaide University（阿德莱德大学计算机科学与信息学院）；Guangdong Institute of Smart Education, Jinan University（暨南大学广东省智慧教育研究院）；Machine Learning Department, Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学机器学习系）
FLeW: Facet-Level and Adaptive Weighted Representation Learning of Scientific Documents
School of Computer Science, Beihang University（北航计算机学院）；Beihang University（北航）；Institute of Artificial Intelligence, Beihang University（北航人工智能研究院）；Zhongguancun Laboratory（中关村实验室）；National Computer Network Emergency Response Technical Team/Coordination Center of China（中国计算机网络应急技术攻关团队/协调中心）
FairContrast: Enhancing Fairness through Contrastive learning and Customized Augmenting Methods on Tabular Data
Department of Industrial Engineering University of Central Florida（工业工程系，中央佛罗里达大学）；Department of Computer Science University of Central Florida（计算机科学系，中央佛罗里达大学）
PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
学习良好的特征表示对于深度强化学习（RL）很重要。然而，由于经验有限，强化学习经常会遇到数据效率低下的问题。对于没有经验或经验较少的轨迹（即，状态-动作序列），数据的缺乏限制了它们用于更好的特征学习。在这项工作中，我们提出了一种新的方法，称为PlayVirtual，它增加了周期一致的虚拟轨迹，以提高数据效率的RL功能表示学习。具体而言，PlayVirtual通过动力学模型基于当前状态和动作预测潜在空间中的未来状态，然后通过后向动力学模型预测先前状态，这形成了轨迹循环。在此基础上，我们增加的行动，以产生大量的虚拟状态动作轨迹。在不受groundtruth状态监督的情况下，我们强制执行一个满足循环一致性约束的轨迹，这可以显着提高数据效率。我们在Atari和DeepMind Control Suite基准测试中验证了我们设计的有效性。我们的方法在两个基准上都达到了最先进的性能。
Agentic Literature Extraction Augments Targeted Protein Degradation Databases
Department of Computer Science and Engineering（计算机科学与工程系）；Chalmers University of Technology（楚姆勒斯技术大学）；University of Gothenburg（哥德堡大学）；Yardi School of Artificial Intelligence（Yardi人工智能学院）；Indian Institute of Technology Delhi（德里印度理工学院）
Affinity-VAE: incorporating prior knowledge in representation learning from scientific images
Alan Turing Institute（阿兰·图灵研究所）；Science and Technology Facilities Council（科学与技术设施委员会）；University of Oxford（牛津大学）；Rosalind Franklin Institute（罗莎琳德·富兰克林研究所）
STEP: Scientific Time-Series Encoder Pretraining via Cross-Domain Distillation
Shanghai Aritificial Intelligence Laboratory（上海人工智能实验室）；Tsinghua University（清华大学）；Harbin Institute of Technology（哈尔滨工业大学）；Sichuan University（四川大学）；University of Cambridge（剑桥大学）
