Sapana Chaudhary
Scholar

Sapana Chaudhary

Google Scholar ID: dsb5VjkAAAAJ
AWS AI
Reinforcement LearningPost-TrainingOnline Optimization
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
143
 
H-index
7
 
i10-index
4
 
Publications
12
 
Co-authors
2
list available
Contact
Emailsapanac@tamu.eduTwitterOpen ↗GitHubOpen ↗
Publications
6 items
Generating Data-Driven Reasoning Rubrics for Domain-Adaptive Reward Modeling
2026
Cited
0
MaxCode: A Max-Reward Reinforcement Learning Framework for Automated Code Optimization
arXiv.org · 2026
Cited
2
VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks
2025
Cited
0
Teaching Large Language Models to Reason through Learning and Forgetting
2025
Cited
0
Risk-Averse Finetuning of Large Language Models
2025
Cited
0
AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents
International Conference on Learning Representations · 2024
Cited
18
Resume (English only)
Academic Achievements
  • Paper on reasoning distillation out on arxiv! (Mar 2025)
  • AgentOccam accepted to ICLR 2025! (Jan 2025)
  • Paper on Risk Averse RLHF accepted to Neurips 2024! (Sep 2024)
  • Paper on Pedagogical Alignment of LLMs accepted to EMNLP 2024! (Sep 2024)
  • Paper on Safe distributed OCO accepted to TMLR! (Aug 2023)
  • Paper on meta-RL in sparse reward environments accepted to NeurIPS 2022! (Sep 2022)
  • Paper on Safe online convex optimization accepted to AAAI 2022! (Dec 2021)
Background
  • Applied Scientist at Amazon, specializing in reinforcement learning (RL) Post-training. Research interests include safety in online learning, RL, and reinforcement learning from human feedback (RLHF).
Miscellany
  • Hobbies include hiking, cooking, painting, and photography.
Co-authors
2 total
Dileep Kalathil
Dileep Kalathil
Texas A&M University
Balaraman Ravindran
Balaraman Ravindran
Professor of Data Science and AI, Wadhwani School of Data Science and AI, IIT Madras