4 papers
ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs
Yuhao Wang, Mu Qiao, Haiwen Diao +5
Multimodal Large Language Models (MLLMs) incur prohibitive inference costs due to long visual token sequences. Training-free visual token reduction provides an efficient solution.…
Understanding Transformers through the Lens of Pavlovian Conditioning
Mu Qiao
Transformer architectures have revolutionized artificial intelligence (AI) through their attention mechanisms, yet the computational principles underlying their success remain opaq…
Unsupervised Evolutionary Cell Type Matching via Entropy-Minimized Optimal Transport
Mu Qiao
Identifying evolutionary correspondences between cell types across species is a fundamental challenge in comparative genomics and evolutionary biology. Existing approaches often re…
OCSU: Optical Chemical Structure Understanding for Molecule-centric Scientific Discovery
Siqi Fan, Yuguang Xie, Bowen Cai +5
Understanding the chemical structure from a graphical representation of a molecule is a challenging image caption task that would greatly benefit molecule-centric scientific discov…