Johns Hopkins researchers, including several affiliated with the Johns Hopkins Data Science and AI Institute, will present their research at tutorials, poster presentations, and workshops during the 2024 Neural Information Processing Systems (NeurIPS) conference, to be held Tuesday, Dec. 10 through Sunday, Dec. 15 in Vancouver, Canada.
Managed by the Neural Information Processing Systems Foundation, NeurIPS is an interdisciplinary annual event that showcases advancements in machine learning and computational neuroscience through talks, demonstrations, symposia, and oral and poster presentations.
Johns Hopkins-affiliated researchers will present the following:
Tutorial
Cross-disciplinary insights into alignment in humans and machines
Rakshit Trivedi, Gillian Hadfield, Joel Leibo, Dylan Hadfield-Menell
Spotlight Posters
Compositional Generalization Across Distributional Shifts with Sparse Tree Operations
Paul Soulos, Henry Conklin, Mattia Opper, Paul Smolensky, Jianfeng Gao, Roland Fernandez
Identifying Equivalent Training Dynamics
William Redman, Juan Bello-Rivas, Maria Fonoberova, Ryan Mohr, Yannis Kevrekidis, Igor Mezic
Posters
Adversarially Robust Multi-Task Representation Learning
Austin Watkins, Thanh Nguyen-Tang, Enayat Ullah, Raman Arora
Binary Search Tree with Distributional Predictions
Michael Dinitz, Sungjin Im, Thomas Lavastida, Ben Moseley, Aidin Niaparast, Sergei Vassilvitskii
CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
Yen-Ju Lu, Jing Liu, Thomas Thebaud, Laureano Moro-Velazquez, Ariya Rastrow, Najim Dehak, Jesus Villalba
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
Weihua Du, Qiushi Lyu, Jiaming Shan, Zhenting Qi, Hongxin Zhang, Sunli Chen, Andi Peng, Tianmin Shu, Kwonjoon Lee, Behzad Dariush, Chuang Gan
DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
Weiting Tan, Jingyu Zhang, Lingfeng Shen, Daniel Khashabi, Philipp Koehn
Efficient Multi-modal Models via Stage-wise Visual Context Compression
Jieneng Chen, Luoxin Ye, Ju He, Zhaoyang Wang, Daniel Khashabi, Alan Yuille
Enhancing vision-language models for medical imaging: bridging the 3D gap with innovative slice selection
Yuli Wang, Peng jian, Yuwei Dai, Craig Jones, Haris Sair, Jinglai Shen, Nicolas Loizou, jing wu, Wen-Chi Hsu, Maliha Imami, Zhicheng Jiao, Paul Zhang, Harrison Bai
Federated Black-Box Adaptation for Semantic Segmentation
Jay Paranjape, Shameema Sikder, S. Vedula, Vishal Patel
Few-Shot Task Learning Through Inverse Generative Modeling
Aviv Netanyahu, Yilun Du, Jyothish Pari, Josh Tenenbaum, Tianmin Shu, Pulkit Agrawal
FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
Xing Han, Huy Nguyen, Carl Harris, Nhat Ho, Suchi Saria
Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems
Francisco Acosta, Fatih Dinc, William Redman, Manu Madhav, David Klindt, Nina Miolane
Graph neural networks and non-commuting operators
Mauricio Velasco, Kaiying O’Hare, Bernardo Rychtenberg, Soledad Villar
HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting
Yuanhao Cai, Zihao Xiao, Yixun Liang, Minghan Qin, Yulun Zhang, Xiaokang Yang, Yaoyao Liu, Alan Yuille
ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
Wufei Ma, Guanning Zeng, Guofeng Zhang, Qihao Liu, Letian Zhang, Adam Kortylewski, Yaoyao Liu, Alan Yuille
Improving Context-Aware Preference Modeling for Language Models
Silviu Pitis, Ziang Xiao, Nicolas Le Roux, Alessandro Sordoni
Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
Thanh Nguyen-Tang, Raman Arora
Learning to Reason via Program Generation, Emulation, and Search
Nathaniel Weir, Muhammad Khalifa, Linlu Qiu, Orion Weller, Peter Clark
Not so Griddy: Internal Representations of RNNs Path Integrating More Than One Agent
William Redman, Francisco Acosta, Santiago Acosta-Mendoza, Nina Miolane
Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
Yihong Guo, Yixuan Wang, Yuanyuan Shi, Pan Xu, Anqi Liu
Offline Multitask Representation Learning for Reinforcement Learning
Haque Ishfaq, Thanh Nguyen-Tang, Songtao Feng, Raman Arora, Mengdi Wang, Ming Yin, Doina Precup
On the Stability and Generalization of Meta-Learning
Yunjuan Wang, Raman Arora
Oracle-Efficient Reinforcement Learning for Max Value Ensembles
Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Sengupta, Jessica Sorrell
Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics
Yenho Chen, Noga Mudrik, Kyle A. Johnsen, Sankaraleengam Alagapan, Adam Charles, Christopher Rozell
Prospective Learning: Learning for a Dynamic Future
Ashwin De Silva, Rahul Ramesh, Rubing Yang, Joshua T Vogelstein, Pratik Chaudhari
Public-data Assisted Private Stochastic Optimization: Power and Limitations
Enayat Ullah, Michael Menart, Raef Bassily, Cristóbal Guzmán, Raman Arora
R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction
Ruyi Zha, Tao Jun Lin, Yuanhao Cai, Jiwen Cao, Yanhao Zhang, Hongdong Li
realSEUDO for real-time calcium imaging analysis
Iuliia Dmitrieva, Sergey Babkin, Adam Charles
ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting
Yiqun Mei, Jiacong Xu, Vishal Patel
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
Sayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou, Samuel Horváth, Martin Takac, Eduard Gorbunov
SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
Shraman Pramanick, Rama Chellappa, Subhashini Venugopalan
Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
Kaibo Zhang, Yunjuan Wang, Raman Arora
SurgicAI: A Fine-grained Platform for Data Collection and Benchmarking in Surgical Policy Learning
Jin Wu, Haoying Zhou, Peter Kazanzides, Adnan Munawar, Anqi Liu
Testing Semantic Importance via Betting
Jacopo Teneggi, Jeremias Sulam
Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?
Pedro R. A. S. Bassi, Wenxuan Li, Yucheng Tang, Fabian Isensee, Zifu Wang, Jieneng Chen, Yu-Cheng Chou, Tassilo Wald, Constantin Ulrich, Michael Baumgartner, Saikat Roy, Klaus Maier-Hein, Paul Jaeger, Yiwen Ye, Yutong Xie, Jianpeng Zhang, Ziyang Chen, Yong Xia, Yannick Kirchhoff, Maximilian R. Rokuss, Pengcheng Shi, Ting Ma, Yuxin Du, Fan BAI, Tiejun Huang, Bo Zhao, Zhaohu Xing, Lei Zhu, Saumya Gupta, Haonan Wang, Xiaomeng Li, Ziyan Huang, Jin Ye, Junjun He, Yousef Sadegheih, Afshin Bozorgpour, Pratibha Kumari, Reza Azad, Dorit Merhof, Hanxue Gu, Haoyu Dong, Jichen Yang, Maciej Mazurowski, Linshan Wu, Jia-Xin Zhuang, Hao CHEN, Holger Roth, Daguang Xu, Matthew Blaschko, Sergio Decherchi, Andrea Cavalli, Alan Yuille, Zongwei Zhou
What does guidance do? A fine-grained analysis in a simple setting
Muthu Chidambaram, Khashayar Gatmiry, Sitan Chen, Holden Lee, Jianfeng Lu
Where does In-context Learning \\ Happen in Large Language Models?
Suzanna Sia, David Mueller, Kevin Duh
Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections
Jiacong Xu, Yiqun Mei, Vishal Patel
Workshops
Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation
Anurag Kumar, Zhaoheng Ni, Shinji Watanabe, Wenwu Wang, Yapeng Tian, Berrak Sisman
Bayesian Decision-making and Uncertainty: from probabilistic and spatiotemporal modeling to sequential experiment design*
* Poster presentation by I-Jeng Wang
Decision-Driven Calibration for Cost-Sensitive Uncertainty Quantification
Gregory Canal, Vladimir Leung, John J. Guerrerio, Philip Sage, I-Jeng Wang
Generative AI and Creativity: A dialogue between machine learning researchers and creative professionals
Y Cooper, Holden Lee, and Hugo Berard
Optimization for ML Workshop*
* Plenary by Benjamin Grimmer
Machine Learning and the Physical Sciences*
* Talk by Wilson G. Gregory, David W. Hogg, Kaze W. K. Wong, and Soledad Villar
Statistical Frontiers in LLMs and Foundation Models*
* Poster presentation by Sophia Hager and Nicholas Andrews
Workshop on Behavioral Machine Learning*
* Poster presentation by Ritwik Bos, Mattson Ogg, Michael Wolmetz, Christopher Ratto
