4 papers
Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMs
Yahan Yu, Yuyang Dong, Masafumi Oyamada
Reasoning is essential for large language models (LLMs), especially in complex tasks such as mathematical problem solving. However, multimodal reasoning still faces challenges in m…
Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference
Rei Taniguchi, Yuyang Dong, Makoto Onizuka +1
Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among numerous works that have been propo…
SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation
Nobuhiro Ueda, Yuyang Dong, Krisztián Boros +3
With the increasing adoption of Large Language Models (LLMs) and Vision-Language Models (VLMs), rich document analysis technologies for applications like Retrieval-Augmented Genera…
Towards Principled Design of Mixture-of-Experts Language Models under Memory and Inference Constraints
Seng Pei Liew, Kenta Shinzato, Yuyang Dong
Modern Mixture-of-Experts (MoE) language models are designed based on total parameters (memory footprint) and active parameters (inference cost). However, we find these two factors…