📝 Publications

Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language Models
Enguang Wang, Qiang Wang, Yuanchen Wu, Ke Yan, Xinbin Yuan, Shouhong Ding, Xialei Liu, Ming-Ming Cheng

• This paper conducts a systematic diagnosis to unveil the visual representation degradation phenomenon in MLLMs, identifying this phenomenon as a visual sacrifice driven by the singular text-generation objective.
• It introduces Predictive Regularization (PRe), a lightweight self-supervised framework that preserves core visual competence by forcing degraded intermediate features to predict initial visual anchors.

GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
Enguang Wang, Zhimao Peng, Zhengyuan Xie, Fei Yang, Xialei Liu, Ming-Ming Cheng

• This paper introduces textual information for the GCD task. By projecting visual features into the input space of the CLIP’s text encoder, it solves the problem that unlabeled data cannot be processed by the text encoder.
• Through cross-modal distillation and multi-modal joint training, GET achieves state-of-the-art results on multiple benchmarks, providing GCD a multi-modal paradigm.

GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
Enguang Wang, Zhimao Peng, Zhengyuan Xie, Fei Yang, Xialei Liu, Ming-Ming Cheng

• This paper introduces textual information for the GCD task. By projecting visual features into the input space of the CLIP’s text encoder, it solves the problem that unlabeled data cannot be processed by the text encoder.
• Through cross-modal distillation and multi-modal joint training, GET achieves state-of-the-art results on multiple benchmarks, providing GCD a multi-modal paradigm.

GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
Enguang Wang, Zhimao Peng, Zhengyuan Xie, Fei Yang, Xialei Liu, Ming-Ming Cheng

• This paper introduces textual information for the GCD task. By projecting visual features into the input space of the CLIP’s text encoder, it solves the problem that unlabeled data cannot be processed by the text encoder.
• Through cross-modal distillation and multi-modal joint training, GET achieves state-of-the-art results on multiple benchmarks, providing GCD a multi-modal paradigm.

GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
Enguang Wang, Zhimao Peng, Zhengyuan Xie, Fei Yang, Xialei Liu, Ming-Ming Cheng

• This paper introduces textual information for the GCD task. By projecting visual features into the input space of the CLIP’s text encoder, it solves the problem that unlabeled data cannot be processed by the text encoder.
• Through cross-modal distillation and multi-modal joint training, GET achieves state-of-the-art results on multiple benchmarks, providing GCD a multi-modal paradigm.