Bhavya Kailkhura

Research Staff, CASC, Lawrence Livermore National Laboratory

Joined

December 2017

Names

Bhavya Kailkhura

Emails

****@llnl.gov (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Research Staff

CASC, Lawrence Livermore National Laboratory (llnl.gov)

2016 – Present

PhD student

ECE, Syracuse University (syr.edu)

2012 – 2016

MS student

ECE, Syracuse University (syr.edu)

2010 – 2012

Advisors, Relations & Conflicts

PhD Advisor

Pramod K Varshney

2012 – 2016

Expertise

Uncertainty in machine learning

2016 – Present

Statistical signal processing

2010 – Present

Adversarial machine learning

2010 – Present

AI Safety and Security

2010 – Present

Publications

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
Sean Michael McLeish, Ang Li, John Kirchenbauer, Dayal Singh Kalra, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Jonas Geiping, Micah Goldblum, Tom Goldstein
- NeurIPS 2025 ER Workshop Spotlight
- Readers: Everyone
AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security
Zikui Cai, Shayan Shabihi, Bang An, Zora Che, Brian R. Bartoldson, Bhavya Kailkhura, Tom Goldstein, Furong Huang
- Submitted to ICLR 2026
- Readers: Everyone
Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
Tavish Malcolm McDonald, Bo Lei, Stanislav Fort, Bhavya Kailkhura, Brian R. Bartoldson
- ICLR 2026 Poster
- Readers: Everyone
A Comedy of Estimators: On KL Regularization in RL Training of LLMs
Vedant Shah, Johan Obando-Ceron, Vineet Jain, Brian R. Bartoldson, Bhavya Kailkhura, Sarthak Mittal, Glen Berseth, Pablo Samuel Castro, Yoshua Bengio, Nikolay Malkin, Moksh Jain, Siddarth Venkatraman, Aaron Courville
- Submitted to ICLR 2026
- Readers: Everyone
UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Decision-Making
Jinhao Duan, James Diffenderfer, Sandeep Madireddy, Tianlong Chen, Bhavya Kailkhura, Kaidi Xu
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Scalable Pretraining of Retrieval Models
Khalid Saifullah, John Kirchenbauer, Rifaa Qadri, Abhimanyu Hans, Neel Jain, Yuxin Wen, Siddharth Singh, Brian R. Bartoldson, Bhavya Kailkhura, Abhinav Bhatele, Tom Goldstein
- Submitted to ICLR 2026
- Readers: Everyone
Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models
Siddarth Venkatraman, Vineet Jain, Sarthak Mittal, Vedant Shah, Johan Obando-Ceron, Yoshua Bengio, Brian R. Bartoldson, Bhavya Kailkhura, Guillaume Lajoie, Glen Berseth, Nikolay Malkin, Moksh Jain
- Submitted to ICLR 2026
- Readers: Everyone
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
Sean Michael McLeish, Ang Li, John Kirchenbauer, Dayal Singh Kalra, Brian R. Bartoldson, Bhavya Kailkhura, Avi Schwarzschild, Jonas Geiping, Tom Goldstein, Micah Goldblum
- Submitted to ICLR 2026
- Readers: Everyone
Deep Thinking via Recursive Self-Aggregation
Siddarth Venkatraman, Vineet Jain, Sarthak Mittal, Moksh Jain, Vedant Shah, Johan Obando-Ceron, Yoshua Bengio, Brian R. Bartoldson, Bhavya Kailkhura, Guillaume Lajoie, Glen Berseth, Nikolay Malkin
- FoRLM 2025
- Readers: Everyone
Benchmarking Biomolecular Foundation Models for Cross-Modal Genomics-Proteomics
Joseph G. Wakim, Vinayak Gupta, Jose Manuel Marti, Jonathan E Allen, Brian R. Bartoldson, Bhavya Kailkhura
- NeurIPS 2025 2nd Workshop FM4LS Poster
- Readers: Everyone

View all 206 publications

Co-Authors

View all 380 co-authors