publications

2025

1. NeurIPS

   LLM Interpretability with Identifiable Temporal-Instantaneous Representation

   Xiangchen Song^*, Jiaqi Sun^*, Zijian Li, Yujia Zheng, and Kun Zhang

   In The Thirty-ninth Annual Conference on Neural Information Processing Systems, Dec 2025

   arXiv HTML PDF Code
2. NeurIPS MechInterp

   Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs

   Xiangchen Song^*, Aashiq Muhamed^*, Yujia Zheng, Lingjing Kong, Zeyu Tang, Mona T. Diab, Virginia Smith, and Kun Zhang

   In Mechanistic Interpretability Workshop at NeurIPS (Spotlight), Dec 2025

   arXiv HTML PDF Code
3. NeurIPS MechInterp

   Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality

   Lingjing Kong, Shaoan Xie, Guangyi Chen, Yuewen Sun, Xiangchen Song, Eric P. Xing, and Kun Zhang

   In Mechanistic Interpretability Workshop at NeurIPS, Dec 2025

   HTML
4. NeurIPS ER

   Accelerating Speculative Reasoning with Internal Probing

   Xiangchen Song, Saket Dingliwal, Sai Muralidhar Jayanthi, Vivek Govindan, Khiem Pham, Shobha Vasudevan, Beidi Chen, Sravan Babu Bodapati, and Aram Galstyan

   In NeurIPS 2025 Workshop on Efficient Reasoning, Dec 2025
5. NeurIPS ER

   Internal Value Functions: Leveraging Hidden States for Efficient Test-Time Scaling in Large Reasoning Models

   Khiem Pham, Sai Muralidhar Jayanthi, Saket Dingliwal, Bhavana Ganesh, Karthik Valmeekam, Xiangchen Song, Vivek Govindan, Beidi Chen, Sravan Babu Bodapati, and Aram Galstyan

   In NeurIPS 2025 Workshop on Efficient Reasoning, Dec 2025
6. ICML

   Reflection-Window Decoding: Text Generation with Selective Refinement

   Zeyu Tang, Zhenhao Chen, Xiangchen Song, Loka Li, Yunlong Deng, Yifan Shen, Guangyi Chen, Peter Spirtes, and Kun Zhang

   In Forty-second International Conference on Machine Learning, Jul 2025

   HTML
7. ICLR

   On the Identification of Temporal Causal Representation with Instantaneous Dependence

   Zijian Li, Yifan Shen, Kaitao Zheng, Ruichu Cai, Xiangchen Song, Mingming Gong, Guangyi Chen, and Kun Zhang

   In The Thirteenth International Conference on Learning Representations, May 2025

   HTML
8. arXiv

   Nonstationary Time Series Forecasting via Unknown Distribution Adaptation

   Zijian Li, Ruichu Cai, Zhenhui Yang, Haiqin Huang, Guangyi Chen, Yifan Shen, Zhengming Chen, Xiangchen Song, and Kun Zhang

   Mar 2025

   arXiv HTML

2024

1. NeurIPS

   Causal Temporal Representation Learning with Nonstationary Sparse Transition

   Xiangchen Song, Zijian Li, Guangyi Chen, Yujia Zheng, Yewen Fan, Xinshuai Dong, and Kun Zhang

   In The Thirty-eighth Annual Conference on Neural Information Processing Systems, Dec 2024

   arXiv HTML PDF Code
2. PLOS ONE

   A randomized controlled trial on anonymizing reviewers to each other in peer review discussions

   Charvi Rastogi, Xiangchen Song, Zhijing Jin, Ivan Stelmakh, Hal Daumé, Kun Zhang, and Nihar B. Shah

   PLOS ONE, Dec 2024

   Abs DOI

   Many peer-review processes involve reviewers submitting their independent reviews, followed by a discussion between the reviewers of each paper. A common question among policymakers is whether the reviewers of a paper should be anonymous to each other during the discussion. We shed light on this question by conducting a randomized controlled trial at the Conference on Uncertainty in Artificial Intelligence (UAI) 2022 conference where reviewer discussions were conducted over a typed forum. We randomly split the reviewers and papers into two conditions–one with anonymous discussions and the other with non-anonymous discussions. We also conduct an anonymous survey of all reviewers to understand their experience and opinions. We compare the two conditions in terms of the amount of discussion, influence of seniority on the final decisions, politeness, reviewers’ self-reported experiences and preferences. Overall, this experiment finds small, significant differences favoring the anonymous discussion setup based on the evaluation criteria considered in this work.

3. ICML

   CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process

   Guangyi Chen, Yifan Shen, Zhenhao Chen, Xiangchen Song, Yuewen Sun, Weiran Yao, Xiao Liu, and Kun Zhang

   In Forty-first International Conference on Machine Learning, Jul 2024

   HTML
4. ICLR

   A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables

   Xinshuai Dong, Biwei Huang, Ignavier Ng, Xiangchen Song, Yujia Zheng, Songyao Jin, Roberto Legaspi, Peter Spirtes, and Kun Zhang

   In The Twelfth International Conference on Learning Representations, May 2024

   HTML

2023

1. NeurIPS

   Temporally Disentangled Representation Learning under Unknown Nonstationarity

   Xiangchen Song, Weiran Yao, Yewen Fan, Xinshuai Dong, Guangyi Chen, Juan Carlos Niebles, Eric Xing, and Kun Zhang

   In Thirty-seventh Conference on Neural Information Processing Systems, Dec 2023

   arXiv HTML PDF Code
2. ICLR

   PLOT: Prompt Learning with Optimal Transport for Vision-Language Models

   Guangyi Chen, Weiran Yao, Xiangchen Song, Xinyue Li, Yongming Rao, and Kun Zhang

   In The Eleventh International Conference on Learning Representations, May 2023

   HTML
3. AAAI

   Estimating treatment effects from irregular time series observations with hidden confounders

   Defu Cao, James Enouen, Yujing Wang, Xiangchen Song, Chuizheng Meng, Hao Niu, and Yan Liu

   In Proceedings of the AAAI Conference on Artificial Intelligence, Feb 2023

   HTML
4. ISBI

   Deep Dag Learning of Effective Brain Connectivity for FMRI Analysis

   Yue Yu, Xuan Kan, Hejie Cui, Ran Xu, Yujia Zheng, Xiangchen Song, Yanqiao Zhu, Kun Zhang, Razieh Nabi, Ying Guo, Chao Zhang, and Carl Yang

   In IEEE 20th International Symposium on Biomedical Imaging (ISBI), Apr 2023

   HTML

2022

1. ICDE

   Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Personalized Recommendation

   Yankai Chen, Yaming Yang, Yujing Wang, Jing Bai, Xiangchen Song, and Irwin King

   In IEEE 38th International Conference on Data Engineering (ICDE), May 2022

   HTML
2. ICLR

   Creating Training Sets via Weak Indirect Supervision

   Jieyu Zhang, Bohan Wang, Xiangchen Song, Yujing Wang, Yaming Yang, Jing Bai, and Alexander Ratner

   In International Conference on Learning Representations, Apr 2022

   HTML
3. WWW

   TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations

   Minhao Jiang, Xiangchen Song, Jieyu Zhang, and Jiawei Han

   In Proceedings of the ACM Web Conference, Apr 2022

   HTML
4. IEEE TWC

   When Aloha and CSMA Coexist: Modeling, Fairness, and Throughput Optimization

   Yayu Gao, Shuangfeng Fang, Xiangchen Song, and Lin Dai

   Apr 2022

   HTML
5. WSDM

   Learning Multi-granularity Consecutive User Intent Unit for Session-based Recommendation

   Jiayan Guo, Yaming Yang, Xiangchen Song, Yuan Zhang, Yujing Wang, Jing Bai, and Yan Zhang

   In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, Mar 2022

   HTML

2021

1. WSDM

   BiTe-GCN: A New GCN Architecture via Bidirectional Convolution of Topology and Features on Text-Rich Networks

   Di Jin^*, Xiangchen Song^*, Zhizhi Yu, Ziyang Liu, Heling Zhang, Zhaomeng Cheng, and Jiawei Han

   In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, Mar 2021

   HTML
2. EMNLP

   ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant Supervision

   Xuan Wang, Vivian Hu, Xiangchen Song, Shweta Garg, Jinfeng Xiao, and Jiawei Han

   In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Nov 2021

   HTML
3. NAACL

   COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation

   Qingyun Wang, Manling Li, Xuan Wang, Nikolaus Parulian, Guangxing Han, Jiawei Ma, Jingxuan Tu, Ying Lin, Ranran Haoran Zhang, Weili Liu, Aabhas Chauhan, Yingjun Guan, Bangzheng Li, Ruisong Li, Xiangchen Song, Yi Fung, Heng Ji, Jiawei Han, Shih-Fu Chang, James Pustejovsky, Jasmine Rah, David Liem, Ahmed ELsayed, Martha Palmer, Clare Voss, Cynthia Schneider, and Boyan Onyshkevych

   In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations, Jun 2021

   HTML
4. WWW SSL

   Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion

   Xiangchen Song, Jiaming Shen, Jieyu Zhang, and Jiawei Han

   In Workshop on Self-Supervised Learning for the Web (SSL@WWW’21), Apr 2021

   HTML
5. AAAI

   Taxonomy Completion via Triplet Matching Network

   Jieyu Zhang, Xiangchen Song, Ying Zeng, Jiaze Chen, Jiaming Shen, Yuning Mao, and Lei Li

   In AAAI Conference on Artificial Intelligence, Feb 2021

   HTML

2020

1. BIBM

   Fine-Grained Named Entity Recognition with Distant Supervision in COVID-19 Literature

   Xuan Wang, Xiangchen Song, Bangzheng Li, Kang Zhou, Qi Li, and Jiawei Han

   In 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Dec 2020

   HTML
2. arXiv

   Comprehensive Named Entity Recognition on CORD-19 with Distant or Weak Supervision

   Xuan Wang, Xiangchen Song, Bangzheng Li, Yingjun Guan, and Jiawei Han

   Apr 2020

   arXiv HTML