Author

Heuiseok Lim

Observed name: Lim, Heuiseok

Institutions: Korea University, Korea University

Observed institutions: Korea University, Korea University

OpenAlex ID: A5133512074

CoME: An Unlearning-based Approach to Conflict-free Model Editing

2025 · Dahyun Jung, Jaehyung Seo, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 1

PDF

Vision Is Not Overhead: One-Pass Block Drafting for Lossless Speculative Decoding in Vision-Language Models

2026 · Lee, Jungseob, Hong, Seongtae, et al. · arXiv (Cornell University)

PDF

Funnel of Thoughts: Efficient Test-Time Scaling via Early Voting and Rollout Pruning

2026 · Park, Chanhee, Han, Sungbin, et al. · arXiv (Cornell University)

PDF

To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG

2026 · Lee, Jungseob, Park, Chanjun, et al. · arXiv (Cornell University)

PDF

Skin-Deep: A Geometric Diagnostic for Alignment Fragility in Large Language Model Representations

2026 · Lee, Dongyub Jude, Lee, Jungseob, et al. · arXiv (Cornell University)

PDF

Beyond Penalizing Mistakes: Stabilizing Efficiency Training in Large Reasoning Models via Adaptive Correct-Only Rewards

2026 · Lee, Jungseob, Lee, Seungyoon, et al. · arXiv (Cornell University)

PDF

Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation

2026 · Chun, Yongchan, Park, Chanhee, et al. · arXiv (Cornell University)

PDF

DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models

2026 · Jungseob Lee, Seongtae Hong, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

PDF

CoME: An Unlearning-based Approach to Conflict-free Model Editing

2025 · Jung, Dahyun, Seo, Jaehyung, et al. · arXiv (Cornell University)

PDF

Works count: 9

Citation count: 1

H-index: 1

I10-index: