arXiv Computer Vision

Flow-Guided Target-Space Alignment via Path Consistency

FlowAlign is a flow‑guided target‑space alignment method that uses conditional flow matching as a training‑time signal to map source modality representations into a fixed target space. It preserves both the global structure of the target distribution and instance‑level correspondence in paired source–target data, unlike existing contrastive, distribution‑matching, or pointwise regression objectives. The authors provide theoretical analysis and demonstrate improved instance‑level alignment while maintaining target‑space structure on synthetic data, single‑cell multiome benchmarks, and image–text alignment tasks.

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)
arXiv Machine Learning
Oct 16

Semantic Latent Alignment for Flow Matching with Invertible Bi-Lipschitz Adapters

The paper proposes a method for adapting pretrained latent spaces without retraining the encoder or decoder by inserting an invertible bi‑Lipschitz adapter that aligns the latent coordinates to a semantic teacher. This offline alignment preserves the compression and reconstruction properties of the original autoencoder while improving semantic organization. Experiments on two medical imaging datasets show that constrained adaptation enhances feature metrics, seed stability, and counterfactual edit strength, and remains competitive on downstream classification tasks.

By Felix N\"utzel, Mischa Dombrowski, Luca Hagen, Bernhard Kainz
arXiv Machine Learning
Sep 30

Alignment-Guided Flow Transformer for Efficient Vision-Language-Action Policy Learning

The paper introduces Alignment‑Guided Flow Transformer (AGFT), a framework for Vision‑Language‑Action (VLA) models that explicitly enforces tri‑modal alignment among vision, language, and action through a dedicated alignment loss. AGFT bridges representational gaps across modalities, improving task adaptation and robustness, and employs a flow‑matching objective to reduce inference steps compared to diffusion‑based policies. Experiments on a large benchmark demonstrate that AGFT achieves higher success rates and lower inference latency than state‑of‑the‑art baselines, highlighting tri‑modal alignment as crucial for scalable VLA manipulation.

By Shengchao Hu, Peng Wang, Qiyang Zhou, Guodong Zheng, Yuqi Huang, Li Shen, Ya Zhang, Dacheng Tao
arXiv Computer Vision
Oct 12

Destination-Conditioned Adaptation with Semantic-Geometric Alignment for Generative Inbetweening

The paper introduces DSG‑GI, a method that adapts pretrained latent video diffusion models for generative inbetweening by using Destination‑Conditioned Adaptation and Semantic‑Geometric Alignment. Destination‑Conditioned Adaptation treats the target frame as the sequence’s endpoint, providing progressive guidance along the generated trajectory. Semantic‑Geometric Alignment aligns token‑wise spatio‑temporal geometry of backbone features with a frozen video encoder and enforces a flow‑matching latent flow constraint near the data endpoint, thereby improving temporal stability, target‑frame faithfulness, and perceptual quality on large‑motion benchmarks.

By Zhiyu Xu (Tianjin University), Wei Shang (Singapore Management University), Yushen Xu (Tianjin University), Wenwen Li (Tianjin Medical University), Zhiyan Xu (Southeast University), Pengfei Zhu (Tianjin University), Dongwei Ren (Tianjin University)
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
arXiv Machine Learning
Oct 2

A Flow Matching Algorithm for Many-Shot Adaptation to Unseen Distributions

The paper introduces Function Projection for Flow Matching (FP‑FM), an algorithm that conditions generative models directly on samples from a target distribution. FP‑FM learns basis functions spanning velocity fields for training distributions and adapts to new distributions via a simple least‑squares projection, enabling efficient sample generation without additional training at inference time. Variants of the method trade expressivity for computational cost by enriching coefficient calculations, and the approach shows markedly better precision and recall than baselines, especially on unseen distributions.

By Tyler Ingebrand, Ruihan Zhao, Kushagra Gupta, David Fridovich-Keil, Sandeep P. Chinchali, Ufuk Topcu
arXiv Computer Vision
Oct 16

Flow-CLIP: Image-Conditioned Residual Scoring for CompositionalImage-Text Matching

Flow-CLIP introduces a method to improve compositional image-text matching by refining global image-text alignment with image-conditioned changes in token–patch evidence. It combines Global Compatibility Calibration (GCC) for sentence-level similarity, Image-Conditioned Evidence Refinement (ICER) to incorporate visual patch context, and Cross-Image Margin Ranking (CIMR) to enhance ranking margins when images support correct descriptions. Experiments demonstrate that Flow-CLIP outperforms pretrained CLIP and other global alignment approaches on binding accuracy and reduces reliance on language priors.

By Minghong Wei, Enguang Zhu, Pu Cao, Lu Yang, Qing Song
arXiv AI
Aug 20

From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model

arXiv:2608. 18339v1 Announce Type: cross Abstract: Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference.

By Qi Yu, Zhichen Zeng, Katherine Tieu, Xiyuan Yang, Ruizhong Qiu, Yuchen Yan, Lihui Liu, Yanjun Zhao, Lingjie Chen, Jingrui He, Hanghang Tong