3 papers
cs.CV2026
The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment
Hongyuan Liu, Qinli Yang, Wen Li +6
Vision-Language Models (VLMs) such as CLIP learn a shared embedding space for images and text, yet their representations remain geometrically separated, a phenomenon known as the m…
cs.LG2024
Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learning
Jiaming Liu, Hongyuan Liu, Zhili Qin +4
The dynamic nature of open-world scenarios has attracted more attention to class incremental learning (CIL). However, existing CIL methods typically presume the availability of com…
cs.LG2022
An Interpretable Neuron Embedding for Static Knowledge Distillation
Wei Han, Yangqiming Wang, Christian Böhm +1
Although deep neural networks have shown well-performance in various tasks, the poor interpretability of the models is always criticized. In the paper, we propose a new interpretab…