You can also find my articles on my Google Scholar profile

Rotation-Aligned Key Channel Pruning for Efficient Vision-Language Model Inference

• Beomseok Kang, Dongwon Jo, Jiwon Song, Donghwee Son, Jae-Joon Kim

• Arxiv preprint 2026

CompactAttention: Accelerating Chunked Prefill with Block-Union KV Selection

• Jiwon Song, Dongwon Jo, Beomseok Kang, Jae-Joon Kim

• Arxiv preprint 2026

Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection

• Dongwon Jo, Beomseok Kang†, Jiwon Song, Jae-Joon Kim† (†: corresponding author)

• International Conference on Machine Learning (ICML) 2026

QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models

• Hyesung Jeon, Seojune Lee, Beomseok Kang, Yulwha Kim, Jae-Joon Kim

• International Conference on Learning Representations (ICLR) 2026

Retrospective Sparse Attention for Efficient Long-Context Generation

• Seonghwan Choi*, Beomseok Kang*, Dongwon Jo, Jae-Joon Kim (*: equal contribution)

• International Conference on Learning Representations (ICLR) 2026

DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentation

• Beomseok Kang, Niluthpol Chowdhury Mithun, Abhinav Rajvanshi, Han-Pang Chiu, Supun Samarasekera

• Winter Conference on Applications of Computer Vision (WACV) 2026