Chunyuan Deng

A selection of work that represents his recent research style.

Language Modeling

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.

Controllability of LMs

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.

Learning Distribution-wise Control in Representation Space for Language Models
Chunyuan Deng, Ruidi Chang, Hanjie Chen
International Conference on Machine Learning (ICML), 2025.

Mechanisms & Limitations of LMs

Language Models are Symbolic Learners in Arithmetic
Chunyuan Deng, Zhiqi Li, Roy Xie, Ruidi Chang, Hanjie Chen
Transactions on Machine Learning Research (TMLR), 2026.

Language Models (Mostly) Know When to Stop Reading
Roy Xie, Junlin Wang, Paul Rosu, Chunyuan Deng, Bolun Sun, Zihao Lin, Bhuwan Dhingra
Advances in Neural Information Processing System (NeurIPS), 2025.

2026

Spherical Steering: Geometry-Aware Activation Rotation for Language Models
Zejia You, Chunyuan Deng, Hanjie Chen
Preprint, 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.

2025

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.

The Generalization Ridge: Information Flow in Natural Language Generation
Ruidi Chang, Chunyuan Deng, Hanjie Chen
Preprint, 2025.

Rethinking Diverse Human Preference Learning through Principal Component Analysis
Feng Luo, Rui Yang, Hao Sun, 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
Ruidi Chang, Chunyuan Deng, Hanjie Chen
Findings of the North American Chapter of the Association for Computational Linguistics (NAACL), 2025 (short paper).

2024

ProgGen: Generating Named Entity Recognition Datasets Step-by-step with Self-Reflexive Large Language Models
Yuzhao Heng, 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^†, Yilun Zhao^†, Yuzhao Heng, Yitong Li, Jiannan Cao, Xiangru Tang, Arman Cohan
Findings of the Association for Computational Linguistics (ACL), 2024. (^†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.