arXiv:2606. 04180v1 Announce Type: new Abstract: Vision-language foundation models such as CLIP and SigLIP provide widely used representations for multimodal learning systems.
arXiv:2602. 07026v3 Announce Type: replace-cross Abstract: Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions.
arXiv:2607. 18885v1 Announce Type: new Abstract: Kernel-based alignment of CLIP toward a vision centric teacher such as DINOv2 (KUEA) improves CLIP's visual representations while preserving text-encoder compatibility, using a fixed trade-off weight tuned on curated ImageNet-1K.
arXiv:2607. 18625v1 Announce Type: cross Abstract: Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones.
arXiv:2605. 08245v4 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) increasingly power high-stakes applications, from medical imaging to autonomous systems, yet they routinely hallucinate, confidently describing content not present in the input.
Cut‑ViT introduces a task‑specific pruning pipeline for visual foundation models that uses gram anchoring matrices and subspace decomposition to align feature representations between native and pruned DINOv3 models. The method incorporates basis‑agnostic and residual constraints to preserve robustness across spatial and channel dimensions, and employs spectral entropy adaptation to tailor the pruning objective to downstream tasks. Experiments demonstrate that Cut‑ViT achieves state‑of‑the‑art performance on six tasks across nine datasets while reducing pruning time to about one minute on a single A100 GPU, using only 20.9% of the time and 45.5% of the GPU memory compared to prior methods.
Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut demonstrates that a Gated CNN block can match or exceed VMamba on image classification, questioning the necessity of SSMs for vision.
arXiv:2606. 29464v1 Announce Type: cross Abstract: Vision-language dataset distillation (VLDD) compresses a large image-text paired dataset into a small set of synthetic pairs that can efficiently train contrastive vision-language models under strict data and compute budgets.
arXiv:2609.16664v1 Announce Type: new Abstract: Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the cont...
arXiv:2609.24564v1 Announce Type: new Abstract: CLIP, a foundational vision-language model, has emerged as a powerful tool for open-vocabulary semantic segmentation. While freezing CLIP's text encode...
Leveraging Large Vision-Language Models like CLIP has recently set new benchmarks for No-Reference Image Quality Assessment (NR-IQA). However, the contrastive pretraining of CLIP inherently prioritize...
UVU is a vision-language unified autoregressive framework that integrates visual supervision directly into the pre-training stage of multimodal large language models. By using continuous visual encoding and a large-scale iterative hierarchical clustering algorithm to build a pixel-level visual codebook, UVU enables lossless representation of visual inputs and autoregressive generation of pixel-level image tokens alongside textual tokens. This approach synergizes pixel-level visual perception with semantic-level visual understanding, allowing models to internalize visual reconstruction capabilities and improve multimodal understanding performance.