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:2609.36734v1 Announce Type: new Abstract: Knowledge Distillation (KD) trains a smaller-capacity student model to imitate a larger-capacity teacher model by matching output distributions, implic...
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...
arXiv:2607. 25376v1 Announce Type: cross Abstract: In Bayesian neural networks (BNNs), variational inference is a widely adopted framework for modeling uncertainty in a distributional way, with the evidence lower bound (ELBO) serving as the standard objective function.
arXiv:2507. 18366v2 Announce Type: replace Abstract: Accurate uncertainty quantification remains a key challenge for standard LLMs, prompting the adoption of Bayesian and ensemble-based methods.
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: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.
The paper introduces GFD-OPD, a method for on‑policy distillation of diffusion models that addresses challenges when compressing large teachers into smaller students. It identifies that standard distillation fails due to distribution gaps and classifier‑free guidance amplification, and proposes Fixed‑State KL to measure these gaps. GFD‑OPD reduces the student‑teacher discrepancy and achieves state‑of‑the‑art performance across multiple benchmarks.
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...
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:2609.34447v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) is becoming an important component of large language model (LLM) post-training for transferring the reasoning ca...
The paper investigates on‑policy distillation (OPD) versus supervised fine‑tuning (SFT), focusing on how students learn from multiple teachers by minimizing divergence. It shows that using forward KL divergence leads to a weighted arithmetic mixture, while reverse KL produces a normalized weighted geometric aggregate. The authors develop algorithms for both off‑policy and on‑policy settings, prove logarithmic regret bounds in tabular cases, extend the analysis to function approximation, and analyze how these aggregation targets explain OPD’s benefits and fragility.
arXiv:2605.28791v2 Announce Type: replace-cross Abstract: On-policy self-distillation (SD) improves LLM reasoning by using teacher-side privileged information (PI) to turn sparse verifier outcomes in...