3 papers
cs.IR2026
Rethinking Semantic Collaborative Integration: Why Alignment Is Not Enough
Maolin Wang, Dongze Wu, Jianing Zhou +7
Large language models (LLMs) have become an important semantic infrastructure for modern recommender systems. A prevailing paradigm integrates LLM-derived semantic embeddings with…
cs.CL2026
HyperGVL: Benchmarking and Improving Large Vision-Language Models in Hypergraph Understanding and Reasoning
Yanbin Wei, Chun Kang, Siwei Li +11
Large Vision-Language Models (LVLMs) consistently require new arenas to guide their expanding boundaries, yet their capabilities with hypergraphs remain unexplored. In the real wor…
cs.LG2023
Text Attribute Control via Closed-Loop Disentanglement
Lei Sha, Thomas Lukasiewicz
Changing an attribute of a text without changing the content usually requires to first disentangle the text into irrelevant attributes and content representations. After that, in t…