AI and Machine Learning are rapidly evolving, driven by advances in data, computing, and algorithms. Research for 2023-2024 focuses on enhancing large language and foundation models, with efforts to improve their efficiency, automation, and integration into real-world tasks. Key areas include fine-tuning models for enterprise applications, advancing AI safety and trust, and exploring deep learning theories like self-supervised learning, reinforcement learning, and generative AI. These innovations are shaping the future of AI across industries, from natural language processing to ethical considerations.
AI Algorithms
Projects
2025
| Project | RPI Principal Investigators | IBM Principal Investigators |
|---|---|---|
| Theoretical and Algorithmic Foundations of In-Context Learning and Chain of Thought Using Properly Trained Transformer Models | Meng Wang | Songtao Lu, Pin-Yu Chen, Xiaodong Cui |
| Key-Value Cache Compression for Memory-Efficient Large Language Model Inference | Mohammad Mohammadi Amiri | Pin-Yu Chen, Tejaswini Pedapati, Subhajit Chaudhury |
| Associative Energy-based Diffusion Models for Generative AI | Mohammed J. Zaki | Dmitry Krotov, Rogerio S. Feris |
| Fast Inference and Alignment for Large Multi-modal Models | Koushik Kar, Tianyi Chen | Parikshit Ram, Nathalie Baracaldo, Yi Zhou, Horst Samulowitz, Ken Wong |
| Meta-Transfer-Learning for Tabular Data Distillation, Generation, and Predictive Modeling | Oshani Seneviratne | Horst Samulowitz, Yi Zhou, Parikshit Ram |
| Interpretable Foundation Models for General-Purpose Time Series Analysis | Agung Julius | Lam Nguyen |
| Strategic AI: Enhancing Large Language Model Agents with Decision-Making Algorithms for Advanced Reasoning and Planning | Santiago Paternain | Dharmashankar Subramanian |
| Large Language Models as Planning Domain Model Generators | Selmer Bringsjord | Kavitha Srinivas, Harsha Kokel Michael Katz, Shirin Sohrabi |
2026
| Project | RPI Principal Investigators | IBM Principal Investigators |
|---|---|---|
| Communicating Generative Models: Multi-Agent Causal Representation Learning for Coordinated Decision-Making | Ali Tajer, Mohammad Mohammadi Amiri | Horst Samulowitz, Debarun Bhattacharjya |
| Novel Diffusion and Flow-based Generative Language Models via Associative Memories | Mohammed J. Zaki | Dmitry Krotov |
| Time Series Data Agent: Enabling Multipurpose Foundation Models for Multimodal Data | Agung Julius | Lam Nguyen, Chandra Reddy |
| Latent Representation and Tiered Indexing for Scalable and Efficient Data Product Creation from Large Data Lakes | Oshani Seneviratne | Horst Samulowitz |
| Advancing LLM Reasoning via Intrinsic and Integrative Capabilities | Yao Ma, Meng Wang | Ching-Yun (Irene) Ko, Keerthiram Murugesan |
| Systematic Failure Analysis for LLM Agents: Taxonomy, Attribution, and Reflection | Lei Yu | Subhajit Chaudhury, Tejaswini Pedapati, Keerthiram Murugesan |
| Holistic Alignment of Agentic LLM Systems via Lightweight System-Level Objectives | Alex Gittens | Karthikeyan Natesan Ramamurthy, Nathalie Baracaldo, Momin Abbas, Raya Horesh |
| Automated Design and Optimization of Enterprise-Scale AI Agent Systems | Jianxi Gao, Shaowu Pan | Pin-Yu Chen, Irene Ko |
| Rethinking Retrieval Signals via Hybrid Retrieval Heads | Stacy Patterson, Ana Milanova | Wei Sun, Radu Florian, Yulong Li |
| AI Safeguards Using Agentic AI | Mohammad Mohammadi Amiri | Momin Abbas, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri |
2024
| Project | RPI Principal Investigators | IBM Principal Investigators |
|---|---|---|
| Testing LLM Safety via Causal Reasoning | Ali Tajer | Prasanna Sattigeri, Dennis Wei, Dmitrity Katz-Rogozhnikov |
| Theoretical and Algorithmic Foundations of In-Context Learning Using Properly Trained Transformer Models | Meng Wang | Songtao Lu, Pin-Yu Chen |
| Unlearning: Dynamics of Membership Privacy and Inference Attacks Against Large Language Models | Lei Yu | Magdon Ismail, Nathalie Baracaldo, Ling Cai |
| Control-Based Reinforcement Learning | Santiago Paternain | Mark Squillante; Chai Wah Wu |
| Correctors and Selectors: Building An Ecosystem for LLM Alignment | Alex Gittens | Mikhail Yurochkin, Mayank Agarwal |
| Data Distillation in Tabular Date: A Foundation Model Approach | Oshani Seneviratne, Inwon Kang | Horst Samulowitz, Parikshit Ram, Yi Zhou |
| Energy Transformer for Foundational Models | Mohammed Zaki | Dmitry Krotov, Benjamin Hoover, Hendrik Strobelt |
| FIT: Fast Inference using Transformer models | Koushik Kar, Tianyi Chen | Parikshit Ram, Nathalie Baracaldo, Yi Zhou, Soham Dan, Horst Samulowitz |
| Foundational Models for Understanding Tabular Data Through AI Automation | Jianxi Gao | Kavitha Srinivas, Tejsawini Pedapati, Horst Samulowitz, Pin-Yu Chen |
| Multi-Objective Training of Foundation Acoustic Models for Automatic Speech Recognition | Tianyi Chen, Mei Si | Xiaodong Cui, Brian Kingsbury, Songtao Lu |
| Resource-Effective Fine-Tuning of Large Language Models | Mohammad Mohammadi Amiri | Pin-Yu Chen, Tejaswini Pedapati, Subhajit Chaudhury |
2023
| Project | RPI Principal Investigators | IBM Principal Investigators |
|---|---|---|
| A Framework for Automating Decentralized Training of Foundation Models | Koushik Kar, Tianyi Chen | Theodoros Salonidis, Parikshit Ram, Nathalie Baracaldo, Yi Zhou |
| Deep Causal Representation Learning Towards Generalizable, Explainable, and Fair AI Systems | Qiang Ji | Tian Gao, Amit Dhurandhar |
| Enhancing Efficiency and Robustness Simultaneously in Processing Deep Neural Networks | Liu Liu | Swagath Venkataramani |
| Explainable Transfer Learning | Christopher Sims, James Hendler | Keerthiram Murugesan, Amit Dhurandhar, Ronny Luss, Pin-Yu Chen |
| Fairness Auditor: Stress-testing AI Fairness Methodologies using Synthetic Data | Kristin Bennett | Ioana Baldini, Dennis Wei, Jiaming Zeng |
| Large-Scale Foundation Acoustic Modeling for Automatic Speech Recognition | Tianyi Chen, Mei Si | Xiaodong Cui, Brian Kingsbury, Songtao Lu |
| Provably Efficient Reinforcement Learning via Neuro-Symbolic Representations | Meng Wang, Tianyi Chen | Miao Liu, Pin-Yu Chen, Songtao Lu, Keerthiram Murugesa, Subhajit Chaudhury |
| Quickest Failure Prediction Algorithm for High Dimensional Time Series Data | Bulent Yener, Ali Tajer | Kyongmin Yeo, Wesley Gifford |
| Robustness of Causal Bandits | Ali Tajer | Prasanna Sattigeri, Dennis Wei, Dmitriy Katz-Rogozhnikov |
| SafeR: Automating Safe Reinforcement Learning | Sandipan Mishra, Santiago Paternain, Koushik Kar | Long Vu, Lan Hoany, Dharmashankar Subramanian |
2022
| Project | RPI Principal Investigators | IBM Principal Investigators |
|---|---|---|
| AutoDML: A Framework for Automating Decentralized Machine Learning | Koushik Kar, Tianyi Chen | Theodoros Salonidis, Parikshit Ram, Nathalie Baracaldo, Yi Zhou |
| Fairness Auditor Stress-Testing AI Fairness Methodologies Using Synthetic Data | Kristin Bennett | Yoonyoung Park, Ioana Baldini, Dennis Wei |
| Interpretable Failure Prediction Algorithm for Time Series Data | Bulent Yener | Kyongmin Yeo, Wesley Gifford |
| Joint Domain Generalization and Algorithm Robustness for Trusted AI | Pingkun Yan, Ali Tajer, Yangyang Xu | Karthikeyan Shanmugam, Richard Chen, Pin-Yu Chen, Amit Dhurandhar |
| Secure and Robust Cross-Silo Vertical Federated Learning | Stacy Patterson | Shiqiang Wang |
| Signal Temporal Logic Neural Network (STL-NN): A Neuro-Symbolic Framework for Human-Interpretable Machine Learning | Julius Agung | Achille Fokoue |
| Sufficiently Accurate Model Based Reinforcement Learning | Santiago Paternain | Dharmashankar Subramanian |
| Training Neural Network with Few-Shot Data & Applications to AI Automation | Jianxi Gao | Pin-Yu Chen, Tejaswini Pedapati |
| Accelerated and Compressed Distributed Stochastic Optimization for Deep Learning | Yangyang Xu | Jie Chen, Chia-Yu Chen, Songtao Lu |
| GATOR: The Goal-oriented Autonomous Dialogue System | Tomek Strzalkowski | Dakou Wang |
| Anomaly Detection on Knowledge Graphs | Alex Gittens, Mohammed Zaki | Charu Aggarwal |
2021
| Project | RPI Principal Investigators | IBM Principal Investigators |
|---|---|---|
| Interpretable Similarity Metric Learning | Derya Malak, Ali Tajer, Bulent Yener | Karthikeyan Natesan Ramanurthy, Dennis Wei, Amit Dhurandhar |
| Towards a General Framework | Stacy Patterson | Shiqiang Wang |
| Active Learning for Automated Decision-Making | Ali Tajer | Payel Das |
| Combining Learning and Reasoning for Embedding Ethical Properties in AI Group Decision Making | Lirong Xia | Francesca Rossi |
| Deep Learning for Trust in Cybersecurity | Nidhi Rastogi, Alex Gittens, Mohammed Zaki | Charu Aggarwal |
| Extracting Types from Python Machine Learning Libraries | Ana Milanova | Martin Hirzel, Julian Dolby |
| Fast Learning of Neural Network Models with Provable Generalizability | Meng Wang | Jinjun Xiong, Sijia Liu, Pin-Yu Chen |
| Manifold-Structured Latent Space for Deep Generative Modeling | Rongjie Lai | Jie Chen |
| Self-Supervision Method for Natural Language Processing and Applications | Sibel Adali | Pin-Yu Chen |
| Composable Systems | Christopher Carothers | Kailash Gopalakrishnan |
2020
| Project | RPI Principal Investigators | IBM Principal Investigators |
|---|---|---|
| A Code Knowledge Graph for Planning Data Science Experiments | Jamie McCusker, Deborah McGuinness | Kavitha Srinivas, Julian Dolby, Michael Katz, Octavian Udrea, Shirin Sohrabi Araghi |
| Active Learning of Adversarial Attack Boudaries | Ali Tajer | Payel Das |
| AI Models for Curation of Threat Intelligence | Nidhi Rastogi | Charu Aggarwal |
| Asynchronous and adaptive stochastic approximation methods for accelerating deep learning | Yangyang Xu | Jie Chen |
| Improving Generalization and Abstraction in Deep Reinforcement Learning | Chris R. Sims | Tim Klinger |
| Learning and Embedding Ethical Guidelines in Group Decision-Making AI | Lirong Xia | Francesca Rossi, Michael Hind, Pin-Yu Chen |
| Neural Memories for Text and Knowledge Graphs | Mohammed J. Zaki | Dimitry Krotov |
| Semantic shift as measure of bias with applications to detection, explanation and mitigation of misinformation | Sibel Adali | Pin-Yu Chen |
2019
| Project | RPI Principal Investigators | IBM Principal Investigators |
|---|---|---|
| Capacity Limited Reinforcement Learning in Minds and Machines | Chris Sims | Gerald Tesauro |
| Data Recovery and Subspace Clustering from Quantized and Corrupted Measurements | Meng Wang | Jinjung Xiong |
| Exploration of Artificial Intelligence Approaches to Earth Observing Remote Sensing | Kevin Rose, Peter Fox | Harry Kolar |
| Neural Memories: Distributed Representations and Associative Retrieval | Mohammed Zaki | Dmitry Krotov |
| Smart Contracts Augmented with Learning and Semantics | Oshani Seneviratne, Lirong Xia | Geeth De Mel |
| Tentacular AI (TAI) | Selmer Bringsjord, Naveen Govindarajulu | Karthik Talamadupula |
