Missing papers

[boyuh]

Request to add several recent works to the Image Representation Learning section. They employ generative feedback to perform self-supervised learning for image representation.

2025

• Reconstructive Visual Instruction Tuning
  [pdf]
  [code]
  • Haochen Wang, Anlin Zheng, Yucheng Zhao, Tiancai Wang, Zheng Ge, Xiangyu Zhang, Zhaoxiang Zhang. ICLR 2025
• Diffusion Feedback Helps CLIP See Better
  [pdf]
  [code]
  • Wenxuan Wang, Quan Sun, Fan Zhang, Yepeng Tang, Jing Liu, Xinlong Wang. ICLR 2025
• GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers
  [pdf]
  [code]
  • Shijie Ma, Yuying Ge, Teng Wang, Yuxin Guo, Yixiao Ge, Ying Shan. ICCV 2025
• un$^2$CLIP: Improving CLIP's Visual Detail Capturing Ability via Inverting unCLIP
  [pdf]
  [code]
  • Yinqi Li, Jiahe Zhao, Hong Chang, Ruibing Hou, Shiguang Shan, Xilin Chen. NeurIPS 2025

2026

• Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation
  [pdf]
  [code]
  • Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Ruochen Cui, Xilin Zhao, Qingming Huang. CVPR 2026