2 papers
cs.CV2026
A More Word-like Image Tokenization for MLLMs
Hyun Lee, Hyemin Jeong, Yejin Kim +4
Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding…
cs.LG2025
Scalability Matters: Overcoming Challenges in InstructGLM with Similarity-Degree-Based Sampling
Hyun Lee, Chris Yi, Maminur Islam +1
Large Language Models (LLMs) have demonstrated strong capabilities in various natural language processing tasks; however, their application to graph-related problems remains limite…