arXiv:2607. 15919v1 Announce Type: cross Abstract: Data-free knowledge distillation transfers the knowledge encoded in a teacher model to a student model without access to the original training data.
arXiv:2603. 15553v2 Announce Type: replace-cross Abstract: The landscape of self-supervised learning (SSL) is currently dominated by generative approaches (e.
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:2608. 09287v1 Announce Type: cross Abstract: Data-Free Knowledge Distillation (DFKD) transfers knowledge from a pretrained teacher model to a compact student model by synthesizing semantically informative data, eliminating the need for access to the original training dataset.
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:2604. 15613v4 Announce Type: replace-cross Abstract: We present Green-ELM, a non-iterative neural architecture that replaces gradient-based optimization of the output layer with a closed-form analytic solution over a fixed, high-dimensional random feature representation.
Dyna‑DINO introduces a curriculum for Vision Transformer (ViT) knowledge distillation that uses the teacher’s intermediate feature maps as progressively harder targets, enabling a student to build foundational representations before tackling higher‑level abstractions. The approach accelerates convergence and improves performance across multiple tasks: on ImageNet‑100 the distilled ViT‑S reaches 90.1% accuracy (+12.24% over baseline), while on ImageNet‑1K it yields +3.9% and +6.09% gains on Oxford and Paris retrieval, +1.93% on semantic segmentation, and notable classification improvements. Additionally, the curriculum reduces training FLOPs by 25.1% and training time by 21% on ImageNet‑100 through early‑stopping of teacher inference.
arXiv:2604. 03873v4 Announce Type: replace Abstract: Black-box knowledge distillation for large language models presents a strict trade-off.
arXiv:2601. 07155v3 Announce Type: replace-cross Abstract: Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however, conventional supervised KD often suffers from a distribution mismatch between training and inference.
CloSeR is a plug‑and‑play framework that enhances Generalized Category Discovery (GCD) by injecting closed‑set relational knowledge from a lightweight teacher model. The teacher is built by fine‑tuning adapters on labeled data while keeping the backbone frozen, preserving pretrained priors. Unified Relational Distillation then transfers both global sample‑to‑prototype and local sample‑to‑sample relations to the GCD task, reducing optimization interference and improving performance across six benchmarks with DINO and DINOv2 backbones.
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.
arXiv:2609.36099v1 Announce Type: new Abstract: Multi-step matching models, including flow and diffusion models, produce high-quality outputs but incur substantial inference costs and may reproduce u...
arXiv:2604. 07753v2 Announce Type: replace-cross Abstract: Empowering Large Multimodal Models (LMMs) with image generation often leads to catastrophic forgetting in understanding tasks due to severe gradient conflicts.