Publications

Google Scholar DBLP Semantic Scholar

2025

• Xiangchen Song*, Jiaqi Sun*, Zijian Li, Yujia Zheng, Kun Zhang, “LLM Interpretability with Identifiable Temporal-Instantaneous Representation”, to appear The Thirty-ninth Conference on Neural Information Processing Systems (NeurIPS’25), Dec. 2025.

• Xiangchen Song*, Aashiq Muhamed*, Yujia Zheng, Lingjing Kong, Zeyu Tang, Mona T. Diab, Virginia Smith, Kun Zhang, “Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs”, to appear Mechanistic Interpretability Workshop at NeurIPS 2025 (MechInterp@NeurIPS’25). Spotlight

• Lingjing Kong, Shaoan Xie, Guangyi Chen, Yuewen Sun, Xiangchen Song, Eric P. Xing, Kun Zhang, “Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality”, to appear Mechanistic Interpretability Workshop at NeurIPS 2025 (MechInterp@NeurIPS’25).

• Xiangchen Song, Saket Dingliwal, Sai Muralidhar Jayanthi, Vivek Govindan, Khiem Pham, Shobha Vasudevan, Beidi Chen, Sravan Babu Bodapati, Aram Galstyan, “Accelerating Speculative Reasoning with Internal Probing”, to appear NeurIPS 2025 Workshop on Efficient Reasoning (ER@NeurIPS’25).

• Khiem Pham, Sai Muralidhar Jayanthi, Saket Dingliwal, Bhavana Ganesh, Karthik Valmeekam, Xiangchen Song, Vivek Govindan, Beidi Chen, Sravan Babu Bodapati, Aram Galstyan, “Internal Value Functions: Leveraging Hidden States for Efficient Test-Time Scaling in Large Reasoning Models”, to appear NeurIPS 2025 Workshop on Efficient Reasoning (ER@NeurIPS’25).

• Zeyu Tang, Zhenhao Chen,Xiangchen Song, Loka Li, Yunlong Deng, Yifan Shen, Guangyi Chen, Peter Spirtes, Kun Zhang , “Reflection-Window Decoding: Text Generation with Selective Refinement”, in Proc. of The Forty-Second International Conference on Machine Learning (ICML’25), Jul. 2025.

• Zijian Li, Yifan Shen, Kaitao Zheng, Ruichu Cai, Xiangchen Song, Mingming Gong, Guangyi Chen, Kun Zhang, “On the Identification of Temporal Causal Representation with Instantaneous Dependence”, in Proc. of The Thirteenth International Conference on Learning Representations (ICLR’25), May 2025. Oral

2024

• Xiangchen Song, Zijian Li, Guangyi Chen, Yujia Zheng, Yewen Fan, Xinshuai Dong, Kun Zhang, “Causal Temporal Representation Learning with Nonstationary Sparse Transition”, to appear The Thirty-eighth Conference on Neural Information Processing Systems (NeurIPS’24), Dec. 2024.

• Guangyi Chen, Yifan Shen, Zhenhao Chen, Xiangchen Song, Yuewen Sun, Weiran Yao, Xiao Liu, Kun Zhang, “CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process”, in Proc. of Forty-first International Conference on Machine Learning (ICML’24), Jul. 2024.
• Xinshuai Dong, Biwei Huang, Ignavier Ng, Xiangchen Song, Yujia Zheng, Songyao Jin, Roberto Legaspi, Peter Spirtes, Kun Zhang, “A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables”, in Proc. of The Twelfth International Conference on Learning Representations (ICLR’24), May 2024.

2023

• Xiangchen Song, Weiran Yao, Yewen Fan, Xinshuai Dong, Guangyi Chen, Juan Carlos Niebles, Eric Xing, Kun Zhang, “Temporally Disentangled Representation Learning under Unknown Nonstationarity”, in Proc. 2023 Conf. on Neural Information Processing Systems (NeurIPS’23), New Orlean, LA, Dec. 2023.
• Guangyi Chen, Weiran Yao, Xiangchen Song, Xinyue Li, Yongming Rao, Kun Zhang, “Prompt Learning with Optimal Transport for Vision-Language Models”, in Proc. of The Eleventh International Conference on Learning Representations (ICLR’23), Spotlight, May 2023.
• Defu Cao, James Enouen, Yujing Wang, Xiangchen Song, Chuizheng Meng, Hao Niu, Yan Liu, “Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders”, in Proc. of 2023 AAAI Conf. on Artificial Intelligence (AAAI’23), Feb. 2023.
• Yue Yu, Xuan Kan, Hejie Cui, Ran Xu, Yujia Zheng, Xiangchen Song, Yanqiao Zhu, Kun Zhang, Razieh Nabi, Ying Guo, Chao Zhang, Carl Yang, “Deep DAG Learning on Brain Networks for fMRI Analysis”, in Proc. of the IEEE International Symposium on Biomedical Imaging (ISBI’23), Apr. 2023. BigData-BrainNN 2022 Version

2022

• Yankai Chen, Yaming Yang, Yujing Wang, Jing Bai, Xiangchen Song, Irwin King, “Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Recommendation”, in Proc. of 38th IEEE International Conference on Data Engineering (ICDE’22), May. 2022.
• Jieyu Zhang, Bohan Wang, Xiangchen Song, Yujing Wang, Yaming Yang, Jing Bai, Alexander Ratner, “Creating Training Sets via Weak Indirect Supervision”, in Proc. of The Tenth International Conference on Learning Representations (ICLR’22), Apr. 2022.
• Minhao Jiang, Xiangchen Song, Jieyu Zhang, Jiawei Han, “TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic Representations”, in Proc. of The Web Conference 2022 (WWW’22), Apr. 2022.
• Yayu Gao, Shuangfeng Fang, Xiangchen Song, and Lin Dai, “When Aloha and CSMA Coexist: Modeling, Fairness and Throughput Optimization”, in IEEE Transactions on Wireless Communications, Apr. 2022.
• Jiayan Guo, Yaming Yang, Xiangchen Song, Yuan Zhang, Yujing Wang, Jing Bai, Yan Zhang, “Learning Multi-granularity Consecutive User Intent Unit for Session-based Recommendation”, in Proc. 2022 ACM Int. Conf. on Web Search and Data Mining (WSDM’22), Feb. 2022.

2021

• Xuan Wang, Vivian Hu, Xiangchen Song, Shweta Garg, Jinfeng Xiao and Jiawei Han, “ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-guided Distant Supervision”, in Proc. 2021 Conf. on Empirical Methods in Natural Language Processing (EMNLP’21), Nov. 2021.
• Xuan Wang, Vivian Hu, Xiangchen Song, Qi Li and Jiawei Han, “EvidenceMiner: Textual Evidence Mining in Scientific Literature”, TrueFact Workshop: Making a Credible Web for Tomorrow at 2021 ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining (TrueFact@KDD’21), Aug. 2021, online.
• Qingyun Wang, Manling Li, Xuan Wang, [and 22 others, including Xiangchen Song]. “COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation”. in Proc. of 2021 Annual Conf. of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT’21), (System demo), Jun. 2021. Best Demo Award
• Xiangchen Song, Jiaming Shen, Jieyu Zhang, and Jiawei Han. “Who Should Go First? A Self-Supervised Concept Sorting Model for Improving Taxonomy Expansion”. 2021 WWW workshop on Self-Supervised Learning for the Web (SSL@WWW’21), Apr. 2021.
• Di Jin*, Xiangchen Song*, Zhizhi Yu, Ziyang Liu, Heling Zhang, Zhaomeng Cheng and Jiawei Han. “BiTe-GCN: A New GCN Architecture via Bidirectional Convolution of Topology and Features on Text-Rich Networks”. in Proc. 2021 ACM Int. Conf. on Web Search and Data Mining (WSDM’21), Feb. 2021.
• Jieyu Zhang, Xiangchen Song, Ying Zeng, Jiaze Chen, Yuning Mao, Jiaming Shen and Lei Li. “Taxonomy Completion via Triplet Matching Network”. in Proc. of 2021 AAAI Conf. on Artificial Intelligence (AAAI’21), Feb. 2021.

2020

• Xuan Wang, Xiangchen Song, Bangzheng Li, Yingjun Guan and Jiawei Han, “Fine-Grained Named Entity Recognition with Distant Supervision in COVID-19 Literature”. in Proc. of 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM’20), Dec, 2020.
• Xuan Wang, Xiangchen Song, Bangzheng Li, Yingjun Guan and Jiawei Han, “Comprehensive Named Entity Recognition on CORD-19 with Distant or Weak Supervision”, 2020 Intelligent Systems for Molecular Biology (ISMB’20), Abstracts (oral and poster), Jul. 2020.