연세대 첨단컴퓨팅학부, ICLR 2026에서 21편의 논문 채택

연세대학교 첨단컴퓨팅학부 소속 교수진이 세계 최고 수준의 인공지능학회인 ICLR 2026(International Conference on Learning Representations)에 다수의 논문을 게재하는 성과를 이루었습니다.

ICLR은 머신러닝 및 딥러닝 분야에서 가장 영향력 있는 국제 학회 중 하나로, 본 학부 교수진의 우수한 연구 역량을 다시 한번 입증하는 계기가 되었습니다.

이번 성과는 인공지능 이론과 응용 전반의 연구 결과를 반영하며, 글로벌 AI 경쟁력 강화를 목표로 합니다.

첨단컴퓨팅학부는 앞으로도 세계 수준의 연구 성과 창출을 위해 지속적으로 노력하겠습니다.

✍️ 논문 제목 및 저자

1. A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models

- Wonje Jeung*, Sangyeon Yoon*, Yoonjun Cho, Dongjae Jeon, Sangwoo Shin, Hyesoo Hong, and Albert No

2. Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM Judges

- Hamin Koo, Minseon Kim, and Jaehyung Kim

3. CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction

- Jisu Shin, Richard Shaw, Seunghyun Shin, Zhensong Zhang, Hae-Gon Jeon* and Eduardo Pérez-Pellitero*

4. CompMarkGS: Robust Watermarking for Compression 3D Gaussian Splatting

- Sumin In, Youngdong Jang, Utae Jeong, MinHyuk Jang, Hyeongcheol Park, Eunbyung Park, Sangpil Kim

5. Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

- Su Ho Han, Jeongseok Hyun, Pilhyeon Lee, Minho Shim, Dongyoon Wee, Seon Joo Kim

6. Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization

- Taeyoon Kwon*, Dongwook Choi*, Hyojun Kim, Sunghwan Kim, Seungjun Moon, Beong-woo Kwak, Kuan-Hao Huang, Jinyoung Yeo

7. Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection

- Minjae Kang and Jaehyung Kim

8. Hierarchical Prototype Learning for Semantic Segmentation

- Seoha Lim*, Jinmyeong Kim*, Jieun Kim, Sung-Bae Cho

9. Identifying Robust Neural Pathways: Few-Shot Adversarial Mask Tuning for Vision-Language Models

- Wonjeong Choi, Sejong Ryu, Jungmoon Lee, Dong-Jun Han*, Jaekyun Moon

10. Motion Prior Distillation in Time Reversal Sampling for Generative Inbetweening

- Wooseok Jeon, Seunghyun Shin, Dongmin Shin and Hae-Gon Jeon

11. Multi-Feature Quantized Self-Attention for Fair Large Language Models

- Jaeil Park and Sung-Bae Cho

12. Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models

- Lujain Ibrahim, Canfer Akbulut, Rasmi Elasmar, Charvi Rastogi, Minsuk Kahng, Meredith Ringel Morris, Kevin R. McKee, Verena Rieser, Murray Shanahan, and Laura Weidinger

13. Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments

- Junwoo Chang, Minwoo Park, Joohwan Seo, Roberto Horowitz, Jongmin Lee*, Jongeun Choi*

14. Prior-based Noisy Text Data Filtering: Fast and Strong Alternative for Perplexity

- Youngbin Seo, Gayoung Kim, Jaehyung Kim*, and Jinyoung Yeo*

15. Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs

- Bumjun Kim*, Dongjae Jeon*, Dueun Kim*, Wonje Jeung, and Albert No

16. Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures

- Sangyeon Yoon, Hyesoo Hong, Wonje Jeung, and Albert No

17. RPM: Reasoning-Level Personalization for Black-Box Large Language Models

- Jieyong Kim*, Tongyoung Kim*, Soojin Yoon, Jaehyung Kim, and Dongha Lee

18. Scalable Offline Model-Based RL with Action Chunks

- Kwanyoung Park, Seohong Park, Youngwoon Lee, Sergey Levine

19. TiTok: Transfer Token-level Knowledge via Contrastive Excess to Transplant LoRA

- Chanjoo Jung and Jaehyung Kim

20. TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models

- Hokyun Im, Euijin Jeong, Andrey Kolobov, Jianlong Fu, Youngwoon Lee

21. Video Scene Segmentation with Genre and Duration Signals

- Jungu Cho, Seong Jong Ha and Hae-Gon Jeon

Image Source: ICLR Official Website (https://iclr.cc)