The paper introduces CODI, a method that enhances self‑supervised Vision Transformers by mixing a small portion of the teacher’s class‑token distribution into each teacher patch‑token target. This cross distillation approach gives every masked patch an attention‑independent semantic correction without altering the architecture. Experiments demonstrate that CODI improves performance on both dense prediction and image‑level tasks under aligned pretraining settings.
Self-supervised Vision Transformers learn strong image-level representations, but their patch-level representations can be unreliable for dense prediction. We study this mismatch and find that the cla...
arXiv:2507.00754v3 Announce Type: replace Abstract: The integration of Large Language Model (LLMs) blocks with Vision Transformers (ViTs) holds immense promise for vision-only tasks by leveraging the...
arXiv:2607.09086v2 Announce Type: replace Abstract: We present Subtoken Vision Transformer (SubViT), a selective image tokenization method for fine-grained visual recognition. Standard Vision Transfo...
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:2610.16817v1 Announce Type: cross Abstract: Progressive depth growth builds large networks by starting with shallow models and inserting layers during training. Recent advances in large languag...
arXiv:2606. 01503v1 Announce Type: cross Abstract: Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expensive and largely overlooked from an efficiency perspective.
arXiv:2609.36348v1 Announce Type: cross Abstract: Generative and representation learning remain asymmetrically connected: semantic representations are used to improve diffusion generation, whereas th...
arXiv:2605.07191v2 Announce Type: replace-cross Abstract: A recent work shows that Attention Transfer, which transfers only the attention patterns from a pre-trained teacher Vision Transformer (ViT)...
arXiv:2610.15855v1 Announce Type: new Abstract: We study how to detect and mitigate visual attention sinks in vision-language models (VLMs). Visual attention sinks are image tokens that absorb a larg...
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:2605. 18740v4 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image.
The paper introduces V‑GIFT, a lightweight method that enhances visual instruction tuning for multimodal large language models by incorporating a small set of visually grounded self‑supervised tasks expressed as natural language instructions. These tasks—such as rotation prediction, color matching, and cross‑view correspondence—are reformulated into image‑instruction‑response triplets, providing supervision that cannot be solved without visual evidence. The approach requires no human annotations, architectural changes, or extra training stages, and consistently improves vision‑centric performance across various models, regimes, and benchmarks when only 3‑10% of the training data is augmented with these instructions.