Seunghyuk Oh

According to our database, Seunghyuk Oh authored at least 8 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation.

Wonjun Kang, Byeongkeun Ahn, Minjae Lee, Kevin Galim, Seunghyuk Oh, Hyung Il Koo, Nam Ik Cho

IEEE Access, 2026

TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs.

Minjae Lee, Wonjun Kang, Byeongkeun Ahn, Christian Classen, Kevin Galim, Seunghyuk Oh, Minghao Yan, Hyung Il Koo, Kangwook Lee

Proceedings of the Findings of the Association for Computational Linguistics: EACL 2026, 2026

2025

ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMs.

Wonjun Kang, Kevin Galim, Seunghyuk Oh, Minjae Lee, Yuchen Zeng, Shuibai Zhang, Coleman Hooper, Yuezhou Hu, Hyung Il Koo, Nam Ik Cho, Kangwook Lee

CoRR, October, 2025

Sparsified State-Space Models are Efficient Highway Networks.

Woomin Song, Jihoon Tack, Sangwoo Mo, Seunghyuk Oh, Jinwoo Shin

Trans. Mach. Learn. Res., 2025

ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification.

Hyunseok Lee, Seunghyuk Oh, Jaehyung Kim, Jinwoo Shin, Jihoon Tack

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Mamba Drafters for Speculative Decoding.

Daewon Choi, Seunghyuk Oh, Saket Dingliwal, Jihoon Tack, Kyuyoung Kim, Woomin Song, Seojin Kim, Insu Han, Jinwoo Shin, Aram Galstyan, Shubham Katiyar, Sravan Babu Bodapati

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024

Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning.

Jaehyun Nam, Kyuyoung Kim, Seunghyuk Oh, Jihoon Tack, Jaehyung Kim, Jinwoo Shin

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs.

Woomin Song, Seunghyuk Oh, Sangwoo Mo, Jaehyung Kim, Sukmin Yun, Jung-Woo Ha, Jinwoo Shin

Proceedings of the Twelfth International Conference on Learning Representations, 2024