Heejun Lee

5 papers · 2022–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird

Venues

ICLR (4) COLING (1)

Top co-authors

Sung Ju Hwang (4) Youngwan Lee (3) Jeffrey Willette (2) Jina Kim (2) Myeongjae Jeon (2) Soyeon Caren Han (1) Bumsik Kim (1) Minki Kang (1) Wonyong Jeong (1) Jean Lee (1)

Research topics

Machine Learning (4) Artificial Intelligence (3) Application Areas (3) Core AI (3) Deep Learning (2) Natural Language Processing (2) Architectures (2) Resources & Methods (2) Techniques (2) Interdisciplinary (1) Applications (1) Core Methods (1) Learning Types (1) Social (1)

Keywords

transformer architecture (2) attention mechanism (2) text classification (1) knowledge distillation (1) language modeling (1) offensive language detection (1) multi-label classification (1) sparse model (1) memory optimization (1) inference optimization (1) token pruning (1) inference efficiency (1) context window (1) sparse attention (1) kv cache (1) linear attention (1) key-value cache (1) hate speech detection (1) korean language (1) long-context modeling (1)

Papers

A Training-Free Sub-quadratic Cost Transformer Model Serving Framework with Hierarchically Pruned Attention ICLR 2025 Training Free Exponential Context Extension via Cascading KV Cache ICLR 2025 SEA: Sparse Linear Attention with Estimated Attention Mask ICLR 2024 Sparse Token Transformer with Attention Back Tracking ICLR 2023 K-MHaS: A Multi-label Hate Speech Detection Dataset in Korean Online News Comment COLING 2022