The paper introduces an in‑span adaptation technique for reduced‑order models, where the reduced subspace is continually updated using the model’s own predictions via an incremental singular‑value decomposition with a forgetting factor. This creates a trajectory‑informed spectral preconditioner that reweights and realigns the basis without changing the subspace, enabling the model to better absorb future out‑of‑span corrections. The authors demonstrate the method on a 3‑D spiral example and nonlinear PDEs such as viscous Burgers and Fisher–KPP, and relate the approach to in‑context learning in dynamical systems.
By Amirpasha Hedayat, Laura Balzano, Karthik Duraisamy
arXiv:2607. 02937v1 Announce Type: new Abstract: Reduced-order models compress high-dimensional dynamics into low-dimensional representations that can be evaluated rapidly, but they lose accuracy when online dynamics drift beyond the training data.
By Amirpasha Hedayat, Laura Balzano, Karthik Duraisamy
arXiv:2606. 30355v1 Announce Type: cross Abstract: As real-world prediction systems often face missing modalities at inference, incomplete multimodal learning (IML) remains a practical challenge.
By Seunghun Baek, Jihwan Park, Jaeyoon Sim, Minjae Jeong, Hoseok Lee, Won Hwa Kim
arXiv:2602. 00722v2 Announce Type: replace Abstract: Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge.
By Hao Gu, Mao-Lin Luo, Zi-Hao Zhou, Han-Chen Zhang, Min-Ling Zhang, Tong Wei
arXiv:2607. 24683v1 Announce Type: cross Abstract: Multi-modal classification leverages complementary information across diverse data sources to enhance predictive performance.
By Francisco Mena, Dino Ienco, Roberto Interdonato, Cassio F. Dantas, Simon Besnard
As real-world prediction systems often face missing modalities at inference, incomplete multimodal learning (IML) remains a practical challenge. While prior methods aim to learn representations robust to missing inputs, representations from incomplete modalities inevitably deviate from their full-modality counterparts due to missing evidence.
arXiv:2606. 15743v1 Announce Type: new Abstract: This paper addresses the missing-modality challenge in multi-modal learning by introducing Unsupervised Learning for Missing Modalities in Multi-Modal Learning (UL4M4), a flexible framework that imputes missing feature embeddings in a task-independent manner before supervised prediction.
By Hassan Ismkhan, Hamid Bouchahcia
arXiv:2607. 15094v1 Announce Type: cross Abstract: Multimodal models such as CLIP learn a shared embedding space for cross-modal retrieval, but continual adaptation to sequentially arriving data can disrupt the cross-modal alignment acquired from earlier phases.
By Sarthak Jain, Qiran Hu, Zhen Zhu, Yaoyao Liu
arXiv:2606. 09907v1 Announce Type: cross Abstract: Multimodal clinical learning is increasingly important for integrating diverse patient data, including imaging, text, and personalised health records.
By Maxx Richard Rahman, Prakhar Kumar, Wolfgang Maass
arXiv:2607. 17944v1 Announce Type: cross Abstract: We introduce CMP (Cognitive Memory Primitive), an architecture that represents inputs as sparse relational codes, stores them in a two-tier competitive memory, and learns entirely through local, gradient-free updates, with no backpropagation anywhere in the network.
By Ashmith Atmuri, Akshay Kumar, Yashaswini Rao Bhogarajula
arXiv:2606. 13657v2 Announce Type: replace Abstract: On-policy distillation (\textsc{OPD}) has recently become a prominent post-training recipe by combining two desirable ingredients: on-policy student trajectories and dense teacher supervision.
By Guo Yu, Wenlin Liu, Yulan Hu, Hao-Xuan Ma, Jun-Peng Jiang, Han-Jia Ye
arXiv:2606. 12362v1 Announce Type: cross Abstract: We study multimodal learning under missing modalities, with particular motivation from bioscience applications in which heterogeneous modalities are often only partially available when decisions need to be made.
By Hui Wang, Tianyu Ren, Joseph Butler, Christopher Baker, Karen Rafferty, Simon McDade