Parameswaran Kamalaruban

Venues

Frequent coauthors

Papers

1. Corruption Robust Offline Reinforcement Learning with Human Feedback
   AISTATS 2025 ·

   Debmalya Mandal

   DBLP profile ↗ORCID search ↗
2. Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs
   NeurIPS 2025 ·

   Georgios Tzannetos

   DBLP profile ↗ORCID search ↗
3. Inference-Time Personalized Alignment with a Few User Preference Queries
   NeurIPS 2025 ·

   Victor-Alexandru Padurean

   DBLP profile ↗ORCID search ↗
4. Learning Personalized Decision Support Policies
   AAAI 2025 ·

   Umang Bhatt

   DBLP profile ↗ORCID search ↗
5. Policy Teaching via Data Poisoning in Learning from Human Preferences
   AISTATS 2025 ·

   Andi Nika

   DBLP profile ↗ORCID search ↗
6. Adversarially Robust Decision Transformer
   NeurIPS 2024 ·

   Xiaohang Tang

   DBLP profile ↗ORCID search ↗
7. Informativeness of Reward Functions in Reinforcement Learning
   AAMAS 2024 ·

   Rati Devidze

   DBLP profile ↗ORCID search ↗
8. Proximal Curriculum with Task Correlations for Deep Reinforcement Learning
   IJCAI 2024 ·

   Georgios Tzannetos

   DBLP profile ↗ORCID search ↗
9. Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
   ICML 2024 ·

   Andi Nika

   DBLP profile ↗ORCID search ↗