Hoseung Kim — accepted AI-conference papers

2026

ICaRus: Identical Cache Reuse for Efficient Multi-Model Inference

Sunghyeon Woo, Jaeeun Kil, Hoseung Kim, Minsub Kim, Joonghoon Kim, Ahreum Seo +6

ICLR 2026poster

Multi model inference, where multiple task-specialized models collaborate to solve complex real-world problems, has recently emerged as a prominent paradigm, particularly in the development of agentic AI systems. However, in such scenarios, each model must maintain its own Key-Value (KV) cache for t…

Cited by 0 Source ↗Scholar ↗

2025

CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs

Gunho Park, Jeongin Bae, Byeongwook Kim, Baeseong park, Jiwon Ryu, Hoseung Kim +2

NeurIPS 2025poster

Weight-only quantization is widely used to mitigate the memory-bound nature of LLM inference. Codebook-based methods extend this trend by achieving strong accuracy in the extremely low-bit regime (e.g., 2-bit). However, current kernels rely on dequantization, which repeatedly fetches centroids and r…

Cited by 0 Source ↗Scholar ↗