Johns Hopkins researchers, including several affiliated with the Department of Computer Science, will present their research in poster sessions and workshops during the 2025 Conference on Neural Information Processing Systems, to be held December 2–7 in San Diego.
NeurIPS is an interdisciplinary annual event that highlights advancements in machine learning, artificial intelligence, and computational neuroscience through talks, demonstrations, symposia, and oral and poster presentations. The conference is organized by the Neural Information Processing Systems Foundation.
JHU CS-affiliated researchers will present the following research:
Spotlight Posters
- “AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling” by Zhining Zhang, Chuanyang Jin, Mung Yao Jia, Engr ’25 (MS), Shunchi Zhang, and Tianmin Shu
- “ESCA: Contextualizing Embodied Agents via Scene-Graph Generation” by Jiani Huang, Mayank Keoliya, Matthew Kuo, Neelay Velingker, Amish Sethi, JungHo Jung, Ser-Nam Lim, Ziyang Li, and Mayur Naik
- “SimWorld: An Open-ended Simulator for Agents in Physical and Social Worlds” by Xiaokang Ye, Jiawei Ren, Yan Zhuang, Xuhong He, Yiming Liang, Yiqing Yang, Mrinaal Dogra, Xianrui Zhong, Eric Liu, Kevin Benavente, Rajiv Mandya Nagaraju, Dhruv Sharma, Ziqiao Ma, Tianmin Shu, Zhiting Hu, and Lianhui Qin
Posters
- “A Generalized Binary Tree Mechanism for Differentially Private Approximation of All-Pair Distances” by Michael Dinitz, Chenglin Fan, Jingcheng Liu, Jalaj Upadhyay, and Zongrui Zou
- “Are Pixel-Wise Metrics Reliable for Sparse-View Computed Tomography Reconstruction?” by Tianyu Lin, Engr ’25 (MS), Xinran Li, Chuntung Zhuang, Qi Chen, Yuanhao Cai, Kai Ding, Alan Yuille, and Zongwei Zhou
- “Beyond Scores: Proximal Diffusion Models” by Zhenghan Fang, Mateo Diaz, Samuel Buchanan, and Jeremias Sulam
- “Characterization and Learning of Causal Graphs from Hard Interventions” by Zihan Zhou, Muhammed Qasim Elahi, and Murat Kocaoglu
- “Conformal Linguistic Calibration: Trading-off between Factuality and Specificity” by Zhengping Jiang, Anqi Liu, and Benjamin Van Durme
- “Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models” by Taha Entesari, Arman Hatami, Rinat Khaziev, Anil Ramakrishna, and Mahyar Fazlyab
- “Differentiable Constraint-Based Causal Discovery” by Jincheng Zhou, Mengbo Wang, Anqi He, Yumeng Zhou, Hessam Olya, Murat Kocaoglu, and Bruno Ribeiro
- “Extragradient Method for (L0, L1)-Lipschitz Variational Inequalities” by Sayantan Choudhury and Nicolas Loizou
- “Monitoring Risks in Test-Time Adaptation” by Mona Schirmer, Metod Jazbec, Christian Naesseth, and Eric Nalisnick
- “Multiplayer Federated Learning: Reaching Equilibrium with Less Communication” by TaeHo Yoon, Sayantan Choudhury, and Nicolas Loizou
- “OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions” by Yuanhao Cai, He Zhang, Xi Chen, Jinbo Xing, Yiwei Hu, Yuqian Zhou, Kai Zhang, Zhifei Zhang, Soo Ye Kim, Tianyu Wang, Yulun Zhang, Xiaokang Yang, Zhe Lin, and Alan Yuille
- “Optical Coherence Tomography Harmonization with Anatomy-Guided Latent Metric Schrödinger Bridges” by Shuwen Wei, Samuel W. Remedios, Blake E. Dewey, Zhangxing Bian, Shimeng Wang, Junyu Chen, Bruno Michel Jedynak, Shiv Saidha, Peter A. Calabresi, Aaron Carass, and Jerry L. Prince
- “PanTS: The Pancreatic Tumor Segmentation Dataset” by Wenxuan Li, Xinze Zhou, Qi Chen, Tianyu Lin, Engr ’25 (MS), Pedro R. A. S. Bassi, Xiaoxi Chen, Chen Ye, Zheren Zhu, Kai Ding, Heng Li, Kang Wang, Yang Yang, Yucheng Tang, Daguang Xu, Alan Yuille, and Zongwei Zhou
- “SimWorld-Robotics: Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration” by Yan Zhuang, Jiawei Ren, Xiaokang Ye, Jianzhi Shen, Ruixuan Zhang, Tianai Yue, Muhammad Faayez, Xuhong He, Xiyan Zhang, Ziqiao Ma, Lianhui Qin, Zhiting Hu, and Tianmin Shu
- “SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning” by Wufei Ma, Yu-Cheng Chou, Qihao Liu, Xingrui Wang, Celso M. de Melo, Jianwen Xie, and Alan Yuille
- “Vision‑Language‑Vision Auto‑Encoder: Scalable Knowledge Distillation from Diffusion Models” by Tiezheng Zhang, Yitong Li, Yu-Cheng Chou, Jieneng Chen, Alan Yuille, Chen Wei, Engr ’24 (PhD), and Junfei Xiao
- “Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting” by Anand Bhattad, Konpat Preechakul, and Alexei A. Efros
- “When Does Curriculum Learning Help? A Theoretical Perspective” by Kaibo Zhang, Yunjuan Wang, Engr ’25 (PhD), and Raman Arora
Workshop Papers
- “AttentiveGRUAE: An Attention-Based GRU Autoencoder for Temporal Clustering and Behavioral Characterization of Depression from Wearable Data” by Nidhi Soley, Vishal M. Patel, and Casey O. Taylor
- “Causal Masking on Spatial Data: An Information-Theoretic Case for Learning Spatial Datasets with Unimodal Language Models” by Jared Junkin and Samuel Nathanson, Engr ’23 (MSE)
- “Re-envisioning Euclid Galaxy Morphology: Identifying and Interpreting Features with Sparse Autoencoders” by John F. Wu and Michael Walmsley
- “The Platonic Universe: Do Foundation Models See the Same Sky?” by Kshitij Duraphe, Michael J. Smith, Shashwat Sourav, and John F. Wu