π¦ Publications
Recent
All
A selection of work that represents his recent research style.
Language Models are Symbolic Learners in Arithmetic
Chunyuan Deng , Zhiqi Li, Roy Xie, Ruidi Chang, Hanjie Chen
Transactions on Machine Learning Research (TMLR ), 2026.
Steering Information Utility in Key-Value Memory for Language Model Post-Training
Chunyuan Deng , Ruidi Chang, Hanjie Chen
Advances in Neural Information Processing System (NeurIPS ), 2025.
Language Models (Mostly) Know When to Stop Reading
Chunyuan Deng , Bolun Sun, Zihao Lin, Bhuwan Dhingra
Advances in Neural Information Processing System (NeurIPS ), 2025.
Learning Distribution-wise Control in Representation Space for Language Models
Chunyuan Deng , Ruidi Chang, Hanjie Chen
International Conference on Machine Learning (ICML ), 2025.
ByteFlow: Language Modeling through Adaptive Byte Compression without a Tokenizer
Chunyuan Deng , Sanket Lokegaonkar, Colin Lockard, Besnik Fetahu, Nasser Zalmout, Xian Li
International Conference on Learning Representations (ICLR ), 2026.
Language Models are Symbolic Learners in Arithmetic
Chunyuan Deng , Zhiqi Li, Roy Xie, Ruidi Chang, Hanjie Chen
Transactions on Machine Learning Research (TMLR ), 2026.
Steering Information Utility in Key-Value Memory for Language Model Post-Training
Chunyuan Deng , Ruidi Chang, Hanjie Chen
Advances in Neural Information Processing System (NeurIPS ), 2025.
Language Models (Mostly) Know When to Stop Reading
Chunyuan Deng , Bolun Sun, Zihao Lin, Bhuwan Dhingra
Advances in Neural Information Processing System (NeurIPS ), 2025.
The Generalization Ridge: Information Flow in Natural Language Generation
Chunyuan Deng , Hanjie Chen
Preprint , 2025.
Rethinking Diverse Human Preference Learning through Principal Component Analysis
Chunyuan Deng , Jiarui Yao, Jingyan Shen, Huan Zhang, Hanjie Chen
Findings of the Association for Computational Linguistics (ACL ), 2025.
Learning Distribution-wise Control in Representation Space for Language Models
Chunyuan Deng , Ruidi Chang, Hanjie Chen
International Conference on Machine Learning (ICML ), 2025.
SAFR: Neuron Redistribution for Interpretability
Chunyuan Deng , Hanjie Chen
Findings of the North American Chapter of the Association for Computational Linguistics (NAACL ), 2025 (short paper).
ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models
Chunyuan Deng , Yitong Li, Yue Yu, Yinghao Li, Rongzhi Zhang, Chao Zhang
Findings of the Association for Computational Linguistics (ACL ), 2024.
Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation
Chunyuan Deng β , Yilun Zhaoβ , Yuzhao Heng, Yitong Li, Jiannan Cao, Xiangru Tang, Arman Cohan
Findings of the Association for Computational Linguistics (ACL ), 2024. (β Equal contribution)
Investigating Data Contamination in Modern Benchmarks for Large Language Models
Chunyuan Deng , Yilun Zhao, Xiangru Tang, Mark Gerstein, Arman Cohan
North American Chapter of the Association for Computational Linguistics (NAACL ), 2024.
π οΈ Service
Program Committee/Reviewer : ICML 2026, ICLR 2025-2026, NeurIPS 2024-2025, COLM 2024-2025, ACL ARR(2023 - now), AISTATS 2025-2026, EMNLP 2024 BlackboxNLP Workshop, NAACL 2024 Student Research Workshop.
π Miscellaneous
In his free time, he enjoys walking around the city photographing magnificent architecture, gorgeous scenery, and lovely interactions between human beings. π
