Publications

Papers

Selected publications from our research.

2025

1. Zhang, Tianyi and Lin, Hongyi and Chen, Yuhan and Viswanathan, Venkatasubramanian. SALSA: A low-cost self-driving lab for salt solubility assessment for battery electrolytes. Preprint. (2025).
2. Wadell, Alexius and Bhutani, Anoushka and Azumah, Victor and Ellis-Mohr, Austin R. and Kelly, Celia, et al. Foundation Models for Discovery and Exploration in Chemical Space. Preprint. (2025).
3. Gozeten, Halil Alperen and Ildiz, M. Emrullah and Zhang, Xuechen and Harutyunyan, Hrayr and Rawat, Ankit Singh, et al. Continuous Chain of Thought Enables Parallel Exploration and Reasoning. Preprint. (2025).
4. Chang, Xiangyu and Ahmed, Sk Miraj and Krishnamurthy, Srikanth V. and Guler, Basak and Swami, Ananthram, et al. FLASH: Federated Learning Across Simultaneous Heterogeneities. Preprint. (2025).
5. Chen, Yuhan and Lin, Hongyi and Zhang, Tianyi and Dave, Adarsh and Mitchell, Jared, et al. ElyteOS: Software for Automated Electrolyte Preparation, Measurement, and Data Management. Preprint. (2025).
6. Duraisamy, Karthik. Active Inference AI Systems for Scientific Discovery. Preprint. (2025).
7. Wadell, Alexius and Bhutani, Anoushka and Viswanathan, Venkatasubramanian. Tokenization for Molecular Foundation Models. Preprint. (2025).
8. Wang, Ziqi and Huang, Hongshuo and Zhao, Hancheng and Xu, Changwen and Zhu, Shang, et al. DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation. Preprint. (2025).
9. Li, Yingcong and Chang, Xiangyu and Kara, Muti and Liu, Xiaofeng and Roy-Chowdhury, Amit, et al. When and How Unlabeled Data Provably Improve In-Context Learning. Preprint. (2025).
10. Sharma, Vansh and Raman, Venkat. Steering Conceptual Bias via Transformer Latent-Subspace Activation. Preprint. (2025).
11. Zhuang, Yilin and Duraisamy, Karthik. LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting. Preprint. (2025).
12. Xu, Changwen and Zhu, Shang and Viswanathan, Venkatasubramanian. CLOUD: A Scalable and Physics-Informed Foundation Model for Crystal Representation Learning. Preprint. (2025).
13. Zhang, Xuechen and Huang, Zijian and Li, Yingcong and Ni, Chenshun and Chen, Jiasi, et al. BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning. Preprint. (2025).
14. Wu, Diyuan and Shevchenko, Aleksandr and Oymak, Samet and Mondelli, Marco. Attention with Trained Embeddings Provably Selects Important Tokens. Preprint. (2025).
15. Chang, Xiangyu and Niloy, Fahim Faisal and Ahmed, Sk Miraj and Krishnamurthy, Srikanth V. and Guler, Basak, et al. AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments. Preprint. (2025).
16. Lim, Jasmin Y. and Pylorof, Dimitrios and Garcia, Humberto E. and Duraisamy, Karthik. A Digital Twin Framework for Generation-IV Reactors with Reinforcement Learning-Enabled Health-Aware Supervisory Control. Preprint. (2025).
17. Wadell, Alexius and Bhutani, Anoushka and Viswanathan, Venkatasubramanian. Scaling Foundation Models for Molecular Chemistry. Preprint. (2025).
18. Gozeten, Halil Alperen and Ildiz, M. Emrullah and Zhang, Xuechen and Soltanolkotabi, Mahdi and Mondelli, Marco, et al. Test-Time Training Provably Improves Transformers as In-context Learners. Preprint. (2025).
19. Chang, Xiangyu and Li, Yingcong and Kara, Muti and Oymak, Samet and Roy-Chowdhury, Amit K.. Provable Benefits of Task-Specific Prompts for In-context Learning. Preprint. (2025).
20. Zhuang, Yilin and Cheng, Sibo and Duraisamy, Karthik. Spatially-Aware Diffusion Models with Cross-Attention for Global Field Reconstruction with Sparse Observations. Computer Methods in Applied Mechanics and Engineering. (2025).
21. Yingcong Li and Xiangyu Chang and Muti Kara and Xiaofeng Liu and Amit Roy-Chowdhury, et al. When and How Unlabeled Data Provably Improve In-Context Learning. Preprint. (2025).
22. Chenhui Zhao and Yiwei Lyu and Asadur Chowdury and Edward Harake and Akhil Kondepudi, et al. Towards Scalable Language-Image Pre-training for 3D Medical Imaging. Preprint. (2025).
23. Vansh Sharma and Venkat Raman. Steering Conceptual Bias via Transformer Latent-Subspace Activation. Preprint. (2025).
24. Xiaofeng Liu and Xiaobo Xia and Xuechen Zhang and Mohna Chakraborty and Xiyuan Chang, et al. Self-Imputation and Cross-Variable Learning Improve Water Quality Prediction with Sparse Data. Preprint. (2025).
25. Xiangyu Chang and Manyi Yao and Srikanth V. Krishnamurthy and Christian R. Shelton and Anirban Chakraborty, et al. Mitigating Participation Imbalance Bias in Asynchronous Federated Learning. Preprint. (2025).
26. Kondepudi, Akhil and Pekmezci, Melike and Hou, Xinhai and Scotford, Katie and Jiang, Cheng, et al. Foundation Models for Fast, Label-Free Detection of Glioma Infiltration. Nature. (2025).
27. Xiangyu Chang and Sk Miraj Ahmed and Srikanth V. Krishnamurthy and Basak Guler and Ananthram Swami, et al. FLASH: Federated Learning Across Simultaneous Heterogeneities. Preprint. (2025).
28. Ege Onur Taga and Halil Alperen Gozeten and Kutay Tire and Rahul Dalvi and Reinhard Heckel, et al. Filter, Augment, Forecast: Online Data Selection for Robust Time Series Forecasting. Preprint. (2025).
29. Ziyang Cai and Nayoung Lee and Avi Schwarzschild and Samet Oymak and Dimitris Papailiopoulos. Extrapolation by Association: Length Generalization Transfer in Transformers. Preprint. (2025).
30. Halil Alperen Gozeten and M. Emrullah Ildiz and Xuechen Zhang and Hrayr Harutyunyan and Ankit Singh Rawat, et al. Continuous Chain of Thought Enables Parallel Exploration and Reasoning. Preprint. (2025).
31. Xinhai Hou and Shaoyuan Xu and Manan Biyani and Moyan Li and Jia Liu, et al. CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization. Preprint. (2025).
32. Anton Alyakin and Jaden Stryker and Daniel Alexander Alber and Jin Vivian Lee and Karl L. Sangwon, et al. CNS-Obsidian: A Neurosurgical Vision-Language Model Built From Scientific Publications. Preprint. (2025).
33. Vansh Sharma and Venkat Raman. Chain of Unit-Physics: A Primitive-Centric Approach to Scientific Code Synthesis. Preprint. (2025).
34. Xuechen Zhang and Zijian Huang and Yingcong Li and Chenshun Ni and Jiasi Chen, et al. BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning. Preprint. (2025).
35. Anthony Carreon and Vansh Sharma and Venkat Raman. Automated Design Optimization via Strategic Search with Large Language Models. Preprint. (2025).
36. Diyuan Wu and Aleksandr Shevchenko and Samet Oymak and Marco Mondelli. Attention with Trained Embeddings Provably Selects Important Tokens. Preprint. (2025).
37. Chang, Xiangyu and Niloy, Fahim Faisal and Ahmed, Sk Miraj and Krishnamurthy, Srikanth V. and Guler, Basak, et al. AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments. Preprint. (2025).

2024

1. Zhu, Shang and Ramsundar, Bharath and Annevelink, Emil and Lin, Hongyi and Dave, Adarsh, et al. Differentiable modeling and optimization of non-aqueous Li-based battery electrolyte solutions using geometric deep learning. Nature Communications. (2024).
2. Madhavan, Varun and Sebastian, Amal S. and Ramsundar, Bharath and Viswanathan, Venkatasubramanian. Self-Supervised Pretraining for Partial Differential Equations. Preprint. (2024).
3. Vansh Sharma and Venkat Raman. A reliable knowledge processing framework for combustion science using foundation models. Energy and AI. (2024).

2023

1. Barwey, Shivam and Shankar, Varun and Viswanathan, Venkatasubramanian and Maulik, Romit. Multiscale Graph Neural Network Autoencoders for Interpretable Scientific Machine Learning. Journal of Computational Physics. (2023).

2022

1. Dave, Adarsh and Mitchell, Jared and Burke, Sven and Lin, Hongyi and Whitacre, Jay, et al. Autonomous optimization of non-aqueous Li-ion battery electrolytes via robotic experimentation and machine learning coupling. Nature Communications. (2022).