arXiv:2606. 25927v1 Announce Type: cross Abstract: As machine learning models and datasets continue to grow, developing complex models has become increasingly computationally demanding.
arXiv:2606. 01292v1 Announce Type: cross Abstract: Teacher-Student Knowledge Transfer (KT) is ubiquitous in modern machine learning, ranging from classical model compression via Knowledge Distillation (KD) to the emergent phenomenon of Weak-to-Strong (W2S) generalization.
arXiv:2509. 09371v2 Announce Type: replace-cross Abstract: Distributionally robust optimization (DRO) protects statistical learning against distributional shifts by optimizing the worst-case performance over a set of perturbed distributions.
arXiv:2606. 25488v1 Announce Type: new Abstract: Knowledge Distillation (KD) is widely used to obtain compact models for efficient inference in resource-constrained environments.
Large language models (LLMs) achieve strong performance across many tasks, but their high computational cost limits deployment in resource-constrained environments. Knowledge Distillation (KD) offers a practical solution by transferring knowledge from a teacher model of a larger size to a smaller student model.
arXiv:2607. 23346v1 Announce Type: new Abstract: Modern deep neural networks are potent catalysts for scientific and industrial impact, yet excessive parameter counts impede deployment in low-compute settings such as hospital equipment and energy infrastructure.
Cross-modal knowledge distillation (CMKD) studies how a (large) teacher model trained on one type of data (e. g.
arXiv:2402. 14035v4 Announce Type: replace-cross Abstract: Knowledge distillation from foundation models to compact domain models is challenging due to substantial gaps in capacity, architecture, and modality.
arXiv:2603. 01875v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones.
arXiv:2606. 10504v1 Announce Type: new Abstract: Cross-modal knowledge distillation (CMKD) studies how a (large) teacher model trained on one type of data (e.
arXiv:2608. 11937v1 Announce Type: new Abstract: Foundation models for time-dependent partial differential equations (PDEs) are trained on large and diverse collections of physical systems and can generalize effectively to new downstream tasks.
arXiv:2601. 01484v2 Announce Type: replace Abstract: Knowledge Distillation (KD) is a central paradigm for transferring knowledge from a large teacher network to a typically smaller student model, often by leveraging soft probabilistic outputs.
arXiv:2605. 03677v2 Announce Type: replace Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm for consolidating the capabilities of specialized expert models into a single student model.