Gyunyeop Kim

According to our database, Gyunyeop Kim authored at least 6 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2026

Transformer-CTP: Current token prediction using cross-attention of queries with current position information.

Gyunyeop Kim, Sangwoo Kang

Knowl. Based Syst., 2026

AG-GRPO: Answer-Guided GRPO for Masked Diffusion Language Models.

Juhyeong Kim, Gyunyeop Kim, Sangwoo Kang

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs.

Gyunyeop Kim, Sangwoo Kang

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025

FractalLLM: Lossless Self-Speculative Decoding with Layer Embedded Self-Compression.

Juhyeong Kim, Sangyeon Yu, Gyunyeop Kim, Sangwoo Kang

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

Exploration-Driven Reinforcement Learning for Expert Routing Improvement in Mixture-of-Experts Language Models.

Gyunyeop Kim, Sangwoo Kang

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

2022

Effective Transfer Learning with Label-Based Discriminative Feature Learning.

Gyunyeop Kim, Sangwoo Kang

Sensors, 2022