🧑🏫 Rensselaer Polytechnic Institute (RPI). Invited lecture for the Frontiers in Network Science course.
📜 L. Yue, K. R. Bhandari, C.-Y. Ko, D. Patel, S. Lin, N. Zhou, J. Gao, P.-Y. Chen, and S. Pan, From Static Templates to Dynamic Runtime Graphs – A Survey of Workflow Optimization for LLM Agents, Findings of ACL, EMNLP. 2026.
📜 K. R. Bhandari, R. Sinha, H. Kokel, N. D. Souza, and S. Kashyap, Selective Escalation from Deterministic to Generative Compliance Validation, IEEE BigData 2026 Industry Track. 2026.
🎖️Received the RPI Graduate Student Research Excellence Honorary Mention at Rensselaer Polytechnic Institute.
📝 Served as a Reviewer for ICLR 2027, the International Conference on Learning Representations.
🧑🏫 FCRC Seminar Series, IBM. Invited presentation on EvoFlux – Inference-Time Evolution of Executable Tool Workflows for Compact Agents.
📜 K. R. Bhandari, P.-Y. Chen, S. Havlin, and J. Gao, Boosting Reinforcement Learning for Network Analysis with Data Augmentation Strategies, Nature Communications. 2026.
🧑🏫 Chief Information Office, IBM. Invited presentation on summer research, Selective Escalation from Deterministic to Generative Compliance Validation.
📝 Served as a Reviewer for AAAI 2027, the AAAI Conference on Artificial Intelligence.
🧑🏫 Software Innovation Lab, IBM. Invited presentation on summer research, Selective Escalation from Deterministic to Generative Compliance Validation.
🗂️ Selective Escalation from Deterministic to Generative Compliance Validation. Patent application under review.
🚀 Visiting Research Scholar, IBM Research, San Jose, California. Developed and evaluated selective LLM-based compliance validation, benchmarking deterministic policy engines against generative models and investigating routing strategies for ambiguous compliance cases.
📃 A. Singh*, A. Singh*, K. R. Bhandari*, S. Dan, A. Kumar, and V. Gupta, EKLAV – Elicited Key CoT Learning via Answer only superVision, arXiv preprint. 2026.
🗂️ EvoFlux – Inference-Time Evolution of Executable Tool Workflows for Compact Agents. Patent application under review.
📃 K. R. Bhandari, L. Yue, C.-Y. Ko, D. Patel, S. Pan, P.-Y. Chen, and J. Gao, EvoFlux – Inference-Time Evolution of Executable Tool Workflows for Compact Agents, arXiv preprint. 2026.
🎓 Completed a Master of Science in Computer Science at Rensselaer Polytechnic Institute, focusing on tabular question answering and retrieval systems under Prof. Jianxi Gao.
📜 A. Singh*, K. R. Bhandari*, J. Gao, S. Dan, and V. Gupta, CRAFT – Training-Free Cascaded Retrieval for Tabular QA, Annual Meeting of the Association for Computational Linguistics, ACL. 2026.
📃 K. R. Bhandari*, A. Singh*, J. Gao, S. Dan, and V. Gupta, Improving Robustness of Tabular Retrieval via Representational Stability, arXiv preprint. 2026.
🧑🏫 Rensselaer Polytechnic Institute (RPI). Invited lecture for the Network Resilience course.
📝 Served as a Reviewer for Complex Networks & Their Applications XIV, the 14th International Conference on Complex Networks and Their Applications.
📜 K. R. Bhandari, P.-Y. Chen, and J. Gao, Unraveling the Cognitive Patterns of Large Language Models Through Module Communities, NeurIPS 2025 CogInterp Workshop and UniReps Workshop. 2025.
📝 Served as a Reviewer for CogInterp at NeurIPS 2025, the Workshop on Interpreting Cognition in Deep Learning Models.
📝 Served as a Reviewer for UniReps at NeurIPS 2025, the Workshop on Unifying Representations in Neural Models.
📜 K. R. Bhandari, S. Xing, S. Dan, and J. Gao, Exploring the Robustness of Language Models for Tabular Question Answering via Attention Analysis, Transactions on Machine Learning Research. 2025.
📚 Attended the Deep Learning for Science School, Berkeley, California.
📜 K. R. Bhandari, P.-Y. Chen, and J. Gao, Forecasting Open-Weight AI Model Growth on HuggingFace, ICLR 2025 Workshop on Open Science for Foundation Models. 2025.
🧑🏫 Ploutos. Invited talk on Forecasting Open-Weight AI Model Growth on Hugging Face.
📝 Served as a Reviewer for Complex Networks & Their Applications XIII, the 13th International Conference on Complex Networks and Their Applications.
📃 E. Z. Kuang*, K. R. Bhandari*, and J. Gao, Optimizing Waste Management with Advanced Object Detection for Garbage Classification, arXiv preprint. 2024.
🚀 Visiting Research Scholar, IBM Research, Yorktown Heights, New York. Investigated faithful and robust constrained text generation from structured data, posterior regularization for large language models, and graph-based representations for table-to-text generation.
📚 Attended AI for Global Goals, Oxford Machine Learning (OxML) Summer School.
Began a Ph.D. in Computer Science at Rensselaer Polytechnic Institute under Prof. Jianxi Gao, specializing in complex networks and machine learning. Expected completion in May 2027.
🎓 Graduated from Caldwell University with a Bachelor of Science in Computer Science and Mathematics through the Honors Program.
📜 K. R. Bhandari and J. G. Sigurjonsson, Convolutional Neural Network-based EEG Emotion Classification with the Forward Selection Wrapper Technique for Channel Selection, Listed in CV as JSTOR. 2020.
⚛️ Member of the Honors Program at Caldwell University.
🎖️ Recipient of the Presidential Scholarship at Caldwell University (Total: $100,000).
🎖️ Recipient of the Catholic Highschool Scholarship at Caldwell University (Total: $8000).