"representation alignment" Papers

14 papers found

Aligning Visual Contrastive learning models via Preference Optimization

Amirabbas Afzali, Borna khodabandeh, Ali Rasekh et al.

ICLR 2025arXiv:2411.08923
3
citations

ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks

Prakash Chandra Chhipa, Gautam Vashishtha, Jithamanyu Settur et al.

ICLR 2025

CG-SSL: Concept-Guided Self-Supervised Learning

Sara Atito, Josef Kittler, Imran Razzak et al.

NEURIPS 2025

Formation of Representations in Neural Networks

Liu Ziyin, Isaac Chuang, Tomer Galanti et al.

ICLR 2025arXiv:2410.03006
12
citations

Global Minimizers of Sigmoid Contrastive Loss

Kiril Bangachev, Guy Bresler, Iliyas Noman et al.

NEURIPS 2025arXiv:2509.18552

NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval

Zengrong Lin, Zheng Wang, Tianwen Qian et al.

CVPR 2025arXiv:2503.10526
2
citations

REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

Ziqiao Wang, Wangbo Zhao, Yuhao Zhou et al.

NEURIPS 2025
8
citations

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Sihyun Yu, Sangkyung Kwak, Huiwon Jang et al.

ICLR 2025arXiv:2410.06940
342
citations

Towards a learning theory of representation alignment

Francesco Maria Gabriele Insulla, Shuo Huang, Lorenzo Rosasco

ICLR 2025arXiv:2502.14047
2
citations

YOLO-Count: Differentiable Object Counting for Text-to-Image Generation

Guanning Zeng, Xiang Zhang, Zirui Wang et al.

ICCV 2025arXiv:2508.00728
6
citations

COMMA: Co-articulated Multi-Modal Learning

Authors: Lianyu Hu, Liqing Gao, Zekang Liu et al.

AAAI 2024paperarXiv:2401.00268
7
citations

Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model

Mingxin Li, Richong Zhang, Zhijie Nie et al.

AAAI 2024paperarXiv:2309.06453
1
citations

Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models

Shouwei Ruan, Yinpeng Dong, Liu Hanqing et al.

ECCV 2024arXiv:2404.12139
4
citations

TrajPrompt: Aligning Color Trajectory with Vision-Language Representations

Li-Wu Tsao, Hao-Tang Tsui, Yu-Rou Tuan et al.

ECCV 2024