3 papers
cs.CV2026
MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models
Yuncheng Yang, Feiyang Ye, Shixian Luo +7
Vision-Language Models (VLMs) have achieved success using homogeneous Transformers to process multimedia data. Recent studies show that heterogeneous structures interleaving effici…
cs.AI2026
GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMs
Shixian Luo, Zezhou Zhu, Yu Yuan +3
Geometric spatial reasoning forms the foundation of many applications in artificial intelligence, yet the ability of large language models (LLMs) to operate over geometric spatial…
cs.CV2024
Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models
Yulei Qin, Yuncheng Yang, Pengcheng Guo +7
Instruction tuning plays a critical role in aligning large language models (LLMs) with human preference. Despite the vast amount of open instruction datasets, naively training a LL…