Get started
Author

Dongyoon Han

Observed name: Han, Dongyoon
ORCID: 0000-0002-9130-8195
Observed ORCID: 0000-0002-9130-8195
OpenAlex ID: A5123889606
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs
2024 · Donghyun Kim, Byeongho Heo, et al. · Lecture notes in computer science · 54
PDF
Model Stock: All We Need Is Just a Few Fine-Tuned Models
2024 · Dong-Hwan Jang, Sangdoo Yun, et al. · Lecture notes in computer science · 10
PDF
On-Policy Distillation with Negative-Policy Rollouts
2026 · Hwang, Jaehui, Han, Dongyoon, et al. · arXiv (Cornell University)
PDF
DLoop: Looped Speculative Decoding
2026 · Gu, Geonmo, Heo, Byeongho, et al. · arXiv (Cornell University)
PDF
Action-incrementer: Action-incremental learning for temporal action segmentation
2026 · Gyeong-hyeon Kim, Hyundong Jin, et al. · Computer Vision and Image Understanding
Verification-Aware Training for Speculative Decoding
2026 · Gu, Geonmo, Heo, Byeongho, et al. · arXiv (Cornell University)
PDF
Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs
2026 · Lee, Seunghyun, Han, Dongyoon, et al. · arXiv (Cornell University)
PDF
On-Policy Delta Distillation
2026 · Heo, Byeongho, Hwang, Jaehui, et al. · arXiv (Cornell University)
PDF
Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time
2026 · Park, Jeongeun, Park, Juhan, et al. · arXiv (Cornell University)
PDF
StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation
2026 · Association for Computational Linguistics 2026, Han, Dongyoon, et al. · Underline Science Inc.
Gaze Attention: Query-Adaptive Visual Routing for Efficient Multimodal LLMs
2026 · Song, Junha, Heo, Byeongho, et al. · arXiv (Cornell University)
PDF
Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance
2026 · Kwon, Minchan, Baek, Sunghyun, et al. · arXiv (Cornell University)
PDF
StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation
2026 · Jang, Geonhui, Han, Dongyoon, et al. · arXiv (Cornell University)
PDF
Which Concepts to Forget and How to Refuse? Decomposing Concepts for Continual Unlearning in Large Vision-Language Models
2026 · Jin, Hyundong, Han, Dongyoon, et al. · arXiv (Cornell University)
PDF
Grounding World Simulation Models in a Real-World Metropolis
2026 · Seo, Junyoung, Choi, Hyunwook, et al. · arXiv (Cornell University)
PDF
VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models
2026 · Lim, Hyesu, Choi, Jinho, et al. · arXiv (Cornell University)
PDF
MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model
2026 · Gu, Geonmo, Heo, Byeongho, et al. · arXiv (Cornell University)
PDF
Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction
2026 · Kim, Jang-Hyun, Han, Dongyoon, et al. · arXiv (Cornell University)
PDF
Oops, Wait: Discourse Tokens Matter in Reasoning Model
2026 · Hwang, Jaehui, Heo, Byeongho, et al. · arXiv (Cornell University)
PDF
On the Reliability of Cue Conflict and Beyond
2026 · Pum Jun Kim, Seung-Ah Lee, et al. · Lecture notes in computer science
PDF
StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation
2026 · Geonhui Jang, Dongyoon Han, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
On-Policy Delta Distillation for Multilingual Math Reasoning
2026 · Byeongho Heo, Jaehui Hwang, et al.
PDF
Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs
2026 · Seogyeong Jeong, Jaehui Hwang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Revisiting Complete Reasoning Traces for Post-Training
2026 · Jaehui Hwang, Sangdoo Yun, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Router Prior Bias: Preserving Base Routing Structure in MoE Post-Training
2026 · Jaedeok Lee, Keonwoo Kim, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)
PDF
Works count: 28
Citation count: 64
H-index: 2
I10-index: 2
Year
Topic
Type