Publications

[arXiv] MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories [Paper]

Guangzhi Xiong, Xinyuan Zhang, Xiao Yang, Hyokun Yun, Kai Zhang, Shiun-Zu Kuo, Hyeonjeong Ha, Xilun Chen, Kai Sun, Lucas Liang, Guangqiang Dong, Ejaz Ahmed, Ahmed A Aly, Anuj Kumar, Raffay Hamid, Aidong Zhang, Xin Luna Dong

[NeurIPS] Capturing In-Context Learning Dynamics with Task Operators [Paper] [Code]

Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Wenqian Ye, Aidong Zhang

[NeurIPS] Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models [Paper] [Code]

Guangzhi Xiong, Qiao Jin, Sanchit Sinha, Zhiyong Lu, Aidong Zhang

[NeurIPS] CASL: Concept-Aligned Sparse Latents for Interpreting Diffusion Models [Paper]

Zhenghao He, Guangzhi Xiong, Boyang Wang, Sanchit Sinha, Aidong Zhang

[Nature Communications] Supervising the search process produces reliable and generalizable information-seeking agents [Paper] [Code] [Homepage]

Guangzhi Xiong*, Qiao Jin*, Xiao Wang, Yin Fang, Haolin Liu, Yifan Yang, Fangyuan Chen, Zhixing Song, Dengyu Wang, Minjia Zhang, Zhiyong Lu, Aidong Zhang

[EMNLP] Triggering Chain-of-Thought via Latent Feature Interventions in Large Language Models [Paper] [Code]

Zhenghao He, Guangzhi Xiong, Bohan Liu, Sanchit Sinha, Aidong Zhang

[ECCV] Towards Robustness against Typographic Attack with Training-free Concept Localization [Paper] [Code]

Bohan Liu, Wenqian Ye, Guangzhi Xiong, Zhenghao He, Sanchit Sinha, Aidong Zhang

[KDD] Concept-Residual Representation Expansion for Robustness to Spurious Correlations [Paper]

Eric Xie, Guangzhi Xiong, Wenqian Ye, Aidong Zhang

[CVPR] Retrieving Counterfactuals Improves Visual In-Context Learning [Paper] [Code] [Homepage]

Guangzhi Xiong, Sanchit Sinha, Zhenghao He, Aidong Zhang

[AISTATS] Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity [Paper] [Code]

Guangzhi Xiong, Sanchit Sinha, Aidong Zhang

[Bioinformatics] Cell-o1: training LLMs to solve single-cell reasoning puzzles with reinforcement learning [Paper] [Code]

Yin Fang, Qiao Jin, Guangzhi Xiong, Bowen Jin, Xianrui Zhong, Siru Ouyang, Yifan Yang, Aidong Zhang, Jiawei Han, Zhiyong Lu

[ICLR] Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders [Paper] [Code] [Homepage]

Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Aidong Zhang

[AAAI (Oral)] Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models [Paper]

Sanchit Sinha, Guangzhi Xiong, Zhenghao He, Aidong Zhang

[EMNLP] COCO-Tree: Compositional Hierarchical Concept Trees for Enhanced Reasoning in Vision Language Models [Paper] [Code]

Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

[ICCV] GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability [Paper] [Code]

Zhenghao He, Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

[TKDD] ProtoNAM: Prototypical Neural Additive Models for Interpretable Deep Tabular Learning [Paper] [Code]

Guangzhi Xiong, Sanchit Sinha, Aidong Zhang

[IJCAI] Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models [Paper] [Code]

Guangzhi Xiong, Eric Xie, Corey Williams, Myles Kim, Amir Hassan Shariatmadari, Sikun Guo, Stefan Bekiranov, Aidong Zhang

[IJCAI] ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers [Paper] [Code]

Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

[KDD] IdeaBench: Benchmarking Large Language Models for Research Idea Generation [Paper]

Sikun Guo, Amir Hassan Shariatmadari, Guangzhi Xiong, Albert Huang, Myles Kim, Corey M. Williams, Stefan Bekiranov, Aidong Zhang

[ACL (Findings)] MedCite: Can Language Models Generate Verifiable Text for Medicine? [Paper]

Xiao Wang, Mengjue Tan, Qiao Jin, Guangzhi Xiong, Yu Hu, Aidong Zhang, Zhiyong Lu, Minjia Zhang

[PSB] Improving Retrieval-Augmented Generation in Medicine with Iterative Follow-up Questions [Paper] [Code]

Guangzhi Xiong*, Qiao Jin*, Xiao Wang, Minjia Zhang, Zhiyong Lu, Aidong Zhang

[NeurIPS (Oral)] MedCalc-Bench: Evaluating Large Language Models for Medical Calculations [Paper] [Code]

Nikhil Khandekar*, Qiao Jin*, Guangzhi Xiong*, Soren Dunn, Serina S. Applebaum, Zain Anwar, Maame Sarfo-Gyamfi, Conrad W. Safranek, Abid A. Anwar, Andrew Zhang, Aidan Gilson, Maxwell B. Singer, Amisha Dave, Andrew Taylor, Aidong Zhang, Qingyu Chen, Zhiyong Lu

[KDD] CoLiDR: Concept Learning using Aggregated Disentangled Representations [Paper]

Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

[ACL (Findings)] Benchmarking retrieval-augmented generation for medicine [Paper] [Code] [Homepage]

Guangzhi Xiong*, Qiao Jin*, Zhiyong Lu, Aidong Zhang

[IJCAI] A Self-explaining Neural Architecture for Generalizable Concept Learning [Paper]

Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

[Bioinformatics] DeepGSEA: Explainable Deep Gene Set Enrichment Analysis for Single-cell Transcriptomic Data [Paper] [Code]

Guangzhi Xiong, Nathan J. LeRoy, Stefan Bekiranov, Nathan C. Sheffield, Aidong Zhang

[Bioinformatics] ProtoCell4P: an explainable prototype-based neural network for patient classification using single-cell RNA-seq [Paper] [Code]

Guangzhi Xiong, Stefan Bekiranov, Aidong Zhang

[ACM Computing Surveys] Biomedical question answering: a survey of approaches and challenges [Paper]

Qiao Jin, Zheng Yuan, Guangzhi Xiong, Qianlan Yu, Huaiyuan Ying, Chuanqi Tan, Mosha Chen, Songfang Huang, Xiaozhong Liu, Sheng Yu