3 papers
cs.AI2026
GTR-CoT: Graph Traversal as Visual Chain of Thought for Molecular Structure Recognition
Jingchao Wang, Yifan He, Haote Yang +10
Optical Chemical Structure Recognition (OCSR) is essential for converting molecular images into machine-readable formats. While recent vision-language models (VLMs) have shown prom…
cs.CV2025
DynCIM: Dynamic Curriculum for Imbalanced Multimodal Learning
Chengxuan Qian, Kai Han, Jiaxin Liu +6
Multimodal learning integrates complementary information from diverse modalities to enhance the decision-making process. However, the potential of multimodal collaboration remains…
cs.CL2025
OpenHuEval: Evaluating Large Language Model on Hungarian Specifics
Haote Yang, Xingjian Wei, Jiang Wu +18
We introduce OpenHuEval, the first benchmark for LLMs focusing on the Hungarian language and specifics. OpenHuEval is constructed from a vast collection of Hungarian-specific mater…