Members only

Please connect to SKKU VPN to access.

Efficient & Intelligent Computing (EIC) Lab

Welcome to EIC Lab at Sungkyunkwan University.

With the mission of making AI more efficient and leveraging AI to solve real-world problems, our research focuses on three key areas: Efficient AI, Computer Architecture, and Electronic Design Automation (EDA).

News & Updates

All news →
  • Paper Accepted to NeurIPS 2026

    Seungmin Kim’s paper, “AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding,” has been accepted to NeurIPS 2026. Congratulations to Seungmin, Mingun, and Yuna!

  • Welcome, Mingun Kim and Seoyoon Chae!

    Please welcome Mingun Kim and Seoyoon Chae, who joined EIC Lab in September 2026!

  • Poster Accepted to ITC 2026

    Soonwon Jeong’s poster has been accepted to ITC 2026. Congratulations, Soonwon!

  • Paper Accepted to ICML 2026

    Kanghyun Noh’s paper, “QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs” has been accepted to ICML 2026. Congratulations to Kanghyun Noh and Jinheon Choi!

Recent Publications

All publications →
  • Jungmin Lee, Gwangeun Byeon, Yulhwa Kim, Seokin Hong⁺. “Token Filtering: Online Attention Pruning via KV Similarity for Efficient LLM Inference.” Conference on Neural Information Processing Systems (NeurIPS), 2026.NeurIPS

  • Seungmin Kim, Mingun Kim, Yuna Lee, Yulhwa Kim⁺. “AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding.” Conference on Neural Information Processing Systems (NeurIPS), 2026.NeurIPS

  • Yuna Lee, Kyoungho Min, Yulhwa Kim⁺. “ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning.” arXiv preprint arXiv:2605.09982, 2026.arXiv