arXiv Machine Learning July 22, 2026 By Micha{\l} Paw{\l}owicz

KALE: Kernel Alignment with Loss Equilibration for Stable CLIP-DINOv2 Alignment at Web Scale

Read the original on arXiv Machine Learning →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 28

Shift-Aware Calibration for Fine-Tuned CLIP: Leveraging Image-Text Alignment

arXiv:2501. 19060v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs), such as CLIP, adapt effectively to downstream tasks through prompt tuning, but fine-tuning can misalign predictive confidence and accuracy, particularly on unseen classes.

By Song-Lin Lv, Yu-Yang Chen, Zhi Zhou, Lan-Zhe Guo

llms fine-tuning multimodal safety

arXiv AI

Jul 21

A${}^2$BM: Alignment-Aware Bridge Matching for Image-to-Image Translation

arXiv:2607. 16294v1 Announce Type: cross Abstract: Paired image-to-image translation underpins a wide range of computer vision tasks, including image editing, sensor translation, and domain adaptation.

By Aimi Okabayashi (UBS Vannes), Georges Le Bellier (LIP, CEDRIC - VERTIGO), Nicolas Audebert (LaSTIG, IGN, CEDRIC - VERTIGO), Charlotte Pelletier (OBELIX), Thomas Corpetti (LETG - Rennes), Nicolas Courty (OBELIX)

llms diffusion computer-vision fine-tuning safety

arXiv AI

Jul 28

What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features

arXiv:2607. 23271v1 Announce Type: cross Abstract: Contrastive vision-language models such as CLIP map semantically opposite phrases (e.

By Chen-Yi Lu, Yueh-Shao Chen, Somali Chaterji

llms rag diffusion fine-tuning multimodal safety

arXiv AI

Jun 29

Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs

arXiv:2601. 22709v5 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) achieve strong multimodal performance but are costly to deploy, and post-training quantization often causes significant accuracy loss.

By Yanlong Chen, Amirhossein Habibian, Luca Benini, Yawei Li

llms efficiency multimodal benchmarks safety

arXiv AI

Jun 8

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

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.

By Xiaomin Yu, Yi Xin, Yuhui Zhang, Wenjie Zhang, Chonghan Liu, Hanzhen Zhao, Chen Liu, Xiaoxing Hu, Ziyue Qiao, Hao Tang, Xiaobin Hu, Chengwei Qin, Hui Xiong, Yu Qiao, Shuicheng Yan

llms rag fine-tuning multimodal safety

arXiv Machine Learning

Jul 23

SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation

arXiv:2605. 30116v2 Announce Type: replace-cross Abstract: Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models.

By Zhuguanyu Wu, Ruihao Gong, Yang Yong, Yushi Huang, Xiangyu Fan, Lei Yang, Dahua Lin, Xianglong Liu

diffusion efficiency safety

Related stories

Shift-Aware Calibration for Fine-Tuned CLIP: Leveraging Image-Text Alignment

A${}^2$BM: Alignment-Aware Bridge Matching for Image-to-Image Translation

What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features

Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models

SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion Distillation