Publications

* equal contribution · † corresponding author

Conference papers

[C14]

Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR

Yongjin Yang, Jiarui Liu, Yinghui He, Lechen Zhang, Bernhard Schölkopf, Zhijing Jin†

NeurIPS 2026 · ICML 2026 RLxF Workshop, Oral (4 of 222 submissions) [paper][code]

[C13]

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Yinghui He, Ling Yang, Jiarui Liu, Yongjin Yang, et al.

NeurIPS 2026 [paper][code]

[C12]

LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL

Yujin Kim*, Namgyu Ho*, Sangmin Hwang*, Joonkee Kim, Yongjin Yang, Sangmin Bae, Seungone Kim, Jaehun Jung, Se-Young Yun†, Hwanjun Song†

NeurIPS 2026 [paper]

[C11]

Entropy-Aware On-Policy Distillation of Language Models

Woogyeol Jin, Taywon Min, Yongjin Yang, Dennis Wei, Yi Zhou, Swanand Ravindra Kadhe, Nathalie Baracaldo, Kimin Lee

ICML 2026 [paper][code]

[C10]

Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models

Younwoo Choi*, Changling Li*, Yongjin Yang, Zhijing Jin

EMNLP 2025 Main [paper][code]

[C9]

Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games

David Guzman Piedrahita, Yongjin Yang, Mrinmaya Sachan, Giorgia Ramponi, Bernhard Schölkopf, Zhijing Jin

COLM 2025 [paper][code]

[C8]

Self-Training Elicits Concise Reasoning in Large Language Models

Tergel Munkhbat*, Namgyu Ho*, Seo Hyun Kim*, Yongjin Yang, Yujin Kim, Se-Young Yun

ACL 2025 Findings [paper][code]

[C7]

Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding

Haneul Yoo, Yongjin Yang, Hwaran Lee

ACL 2025 Main [paper][code]

[C6]

Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models

Yongjin Yang*, Sihyeon Kim*, Hojung Jung, Sangmin Bae, SangMook Kim, Se-Young Yun†, Kimin Lee†

ICLR 2025 [paper][code][project]

[C5]

MAQA: Evaluating Uncertainty Quantification in LLMs Regarding Data Uncertainty

Yongjin Yang, Haneul Yoo, Hwaran Lee

NAACL 2025 Findings [paper][code]

[C4]

Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models

Yongjin Yang*, Jongwoo Ko*, Se-Young Yun

EMNLP 2024 Main [paper][code]

[C3]

Leveraging Normalization Layer in Adapters with Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning

Yongjin Yang, Taehyeon Kim, Se-Young Yun

AAAI 2024 [paper]

[C2]

HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning

Yongjin Yang*, Joonkee Kim*, Yujin Kim*, Namgyu Ho, James Thorne†, Se-Young Yun†

EMNLP 2023 Findings [paper][code]

[C1]

Meta-Learning with Adaptive Weighted Loss for Imbalanced Cold-Start Recommendation

Minchang Kim*, Yongjin Yang*, Jung Hyun Ryu, Taesup Kim

CIKM 2023 · Oral [paper][code]

Preprints

[P5]

Learning from Evolving Prompts: Adaptive Prompt Teaching for Reinforcement Learning

Yongjin Yang, Lechen Zhang, Jiarui Liu, Yinghui He, Christopher Pal, Alexandre Drouin, Zhijing Jin

Under review

[P4]

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision

Yinghui He, Simran Kaur, Adithya Bhaskar, Yongjin Yang, Jiarui Liu, Narutatsu Ri, Liam Fowl, Abhishek Panigrahi, Danqi Chen, Sanjeev Arora

Preprint · ICML 2026 RLxF Workshop, Oral [paper][code]

[P3]

Making Complex Reasoning Student-Friendly: A Hybrid Distillation Framework for Small Language Models

Yongjin Yang, Yinghui He, Jiarui Liu, Zhijing Jin

Preprint · ICLR 2026 Workshop on Scaling Post-Training for LLMs [paper]

[P2]

Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback

Yongjin Yang*, Sinjae Kang*, Juyong Lee, Dongjun Lee, Se-Young Yun†, Kimin Lee†

Preprint [paper]

[P1]

Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness

Yongjin Yang*, Euiin Yi*, Jongwoo Ko, Kimin Lee†, Zhijing Jin†, Se-Young Yun†

Preprint · ICML 2025 Multi-Agent Systems Workshop [paper][code]