CLIP-RD introduces a relational distillation framework for efficient CLIP knowledge distillation, featuring Vertical Relational Distillation (VRD) and Cross Relational Distillation (XRD). VRD aligns intra‑modal similarity distributions between teacher and student, while XRD aligns cross‑modal similarity distributions to enforce bidirectional symmetry. This joint modeling of multidirectional relational structures improves the student’s embedding geometry, yielding a 1.8%p performance gain over CLIP‑KD across various architectures, tasks, and corruption settings with minimal training‑time overhead.
Pretrained vision-language models such as CLIP excel at zero-shot recognition but often fail at compositionality, particularly attribute-object and relational structures. Recent studies mitigate this...
MLLMCLIP introduces a heterogeneous distillation framework that transfers multimodal knowledge from a generative Multimodal Large Language Model (MLLM) teacher directly into a discriminative CLIP student, eliminating the need for synthetic hard negatives. The method uses an attention-based per-layer token selection and a CKA-based distillation loss to bridge architectural differences between the two models. As a result, MLLMCLIP achieves state‑of‑the‑art compositional accuracy and improves zero‑shot classification and image‑text retrieval performance.
Cross-modal knowledge distillation (CMKD) studies how a (large) teacher model trained on one type of data (e. g.
arXiv:2609.39657v1 Announce Type: new Abstract: Distilling pretrained foundation models into an autoencoder bottleneck improves latent diffusability, enabling diffusion models to converge faster and...
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:2511.17886v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) have achieved remarkable success across multimodal tasks, yet their substantial computational demands hinder ef...
arXiv:2604. 25693v2 Announce Type: replace Abstract: Most multi-modal knowledge graph completion (MMKGC) models use one embedding scorer to conduct both retrieval over the full entity set and final link prediction.
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:2606. 27527v1 Announce Type: cross Abstract: Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored.
arXiv:2609.37243v1 Announce Type: cross Abstract: Cross-modal knowledge distillation transfers knowledge from a teacher modality to a student modality. Existing feature-level alignment methods typica...
arXiv:2412. 01282v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks.
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.