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.
arXiv:2609.22566v1 Announce Type: cross Abstract: Knowledge distillation (KD) aims to compress high-performance teacher LLMs into lightweight students. However, distilled students often exhibit subst...
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:2609.13199v1 Announce Type: new Abstract: Knowledge distillation aims to improve the performance of lightweight student models by transferring knowledge from larger and more powerful teacher mo...
Interpretable AI with Local Distillation proposes a method where a black‑box teacher model guides a regularized linear student model at each query point. The teacher defines locality by upweighting training observations with similar predicted outcomes and anchors the fit with its own prediction at the query point, treated as a pseudo‑observation. By adding Gaussian randomization and refitting, the approach identifies reliable features and stable subgroups, achieving near‑teacher accuracy while producing sparse, locally interpretable linear models.
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. 12171v1 Announce Type: cross Abstract: Knowledge Distillation (KD) and mixup have proven effective at inducing smoothness in class boundaries; KD captures inherent class relationships in probability distributions, and mixup enforces them through convex combinations of inputs.
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.
The paper investigates how knowledge distillation (KD) applied at intermediate layers of a neural network can affect overfitting and model performance. While traditional KD focuses on the final output, this study explores block‑wise KD across eleven datasets, finding that on standard datasets the last block suffices, but on fine‑grained, data‑scarce settings intermediate supervision significantly improves accuracy. The authors also analyze optimal supervision granularity using attention maps, Centered Kernel Alignment, and Grad‑CAM, and examine teacher‑student fine‑tuning strategies.
arXiv:2605. 31191v2 Announce Type: replace Abstract: We investigate how teacher-student capacity relationships modulate knowledge distillation (KD) effectiveness in ResNet-based image classification on CIFAR-10.
arXiv:2606. 25488v1 Announce Type: new Abstract: Knowledge Distillation (KD) is widely used to obtain compact models for efficient inference in resource-constrained environments.
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:2503. 08038v2 Announce Type: replace-cross Abstract: In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of (1) a weighted Mean Square Error (wMSE) loss and (2) a Cross-Entropy loss incorporating soft labels.