3 papers
cs.CL2026
Lens: Bringing the Right Semantic Perspective into Focus for Training-Free Multimodal Representation Learning
Xinran Liu, Shouqian Shi, Yixian Chen +3
High-quality representations are essential for a wide range of downstream tasks. Dedicated embedding models are explicitly optimized for representation learning, yet their training…
cs.CV2026
TraceCLIP: Recovering Local Semantics from Patch-to-CLS Contributions
Xinran Liu, Shouqian Shi, Yutong Chen +3
Dense vision-language understanding, including object localization, region recognition, and open-vocabulary semantic segmentation, requires associating language concepts with spati…
cs.CL2026
IRIS: Reusable Identity Representations from Frozen LLMs for Entity Alignment
Xinran Liu, Shengtao Li, Shouqian Shi +2
Entity alignment (EA) identifies entities across knowledge graphs (KGs) that refer to the same real-world object. Conventional EA methods mainly exploit explicit graph structures a…