4 papers
CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
Gyuwan Kim, Cheoneum Park, Tao Yang
Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for higher efficiency, whi…
Global Optimization and Inference-Time Region Grafting for Agentic Workflows
Donghyeok Koh, Gyuwan Kim, Jinyeong Bak +4
Recent advances in agentic workflow optimization automate workflow design through task-specific workflow search or input-conditioned architecture selection. However, they determine…
ELO: Efficient Layer-Specific Optimization for Continual Pretraining of Multilingual LLMs
HanGyeol Yoo, ChangSu Choi, Minjun Kim +6
We propose an efficient layer-specific optimization (ELO) method designed to enhance continual pretraining (CP) for specific languages in multilingual large language models (MLLMs)…
ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contexts
Dongwon Noh, Donghyeok Koh, Junghun Yuk +4
Prior benchmarks for evaluating the domain-specific knowledge of large language models (LLMs) lack the scalability to handle complex academic tasks. To address this, we introduce \…