arXiv:2602. 07768v3 Announce Type: replace-cross Abstract: Distilling knowledge from large Vision-Language Models (VLMs) into lightweight networks is crucial yet challenging in Fine-Grained Visual Classification (FGVC), due to the reliance on fixed prompts and global alignment.
arXiv:2509. 14001v5 Announce Type: replace-cross Abstract: Personalized object detection aims to adapt a general-purpose detector to recognize user-specific instances from only a few examples.
arXiv:2606. 04922v1 Announce Type: cross Abstract: Current prompt-based and adapter-based tuning of vision-language models (VLMs) is attractive for medical imaging, where clinical data sensitivity favors frozen backbones and annotations are limited.
arXiv:2607. 28967v1 Announce Type: cross Abstract: Prompt tuning adapts vision--language models with few trainable parameters, but existing approaches trade off efficiency and adaptation: static textual prompts can overfit source classes, image-conditioned prompts add per-instance computation, and multimodal tuning modifies the visual branch.
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.
The paper introduces Semantic Localization-Enhanced Teacher (SLE‑T), a knowledge‑distillation framework that aligns spatial‑scale and semantic features between a Vision Foundation Model (VFM) teacher and a student detector for cross‑domain object detection. SLE‑T employs a lightweight SLE Adapter that injects pretrained local‑texture priors into DINOv2 and reformulates its features into dense, spatially and semantically compatible representations, enabling effective pseudo‑label learning or feature alignment. Experiments on three domain‑adaptive object detection benchmarks show that SLE‑T with DINOv2‑B achieves state‑of‑the‑art performance while using only a quarter of the training time and less GPU memory compared to the larger DINOv2‑G teacher.
Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.
arXiv:2610.02117v1 Announce Type: cross Abstract: On-policy self-distillation has recently emerged as an effective approach for improving language-model reasoning by supervising students with a froze...
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.
arXiv:2610.01625v1 Announce Type: new Abstract: Federated parameter-efficient fine-tuning enables distributed clients to adapt pretrained vision-language models without sharing raw data or updating t...
arXiv:2603. 25144v2 Announce Type: replace-cross Abstract: Dataset distillation (DD) compresses a large training set into a small synthetic set, reducing storage and training cost, and has shown strong results on general benchmarks.
arXiv:2609.10321v1 Announce Type: new Abstract: Knowledge distillation offers an efficient route to transfer a task-adapted vision-language teacher to a compact student. The training target in curren...
arXiv:2609.36680v1 Announce Type: new Abstract: Visual reprogramming adapts pretrained models to downstream tasks by modifying their input and output interfaces while keeping the backbone fixed. In v...