Kishan Panaganti
Scholar

Kishan Panaganti

Google Scholar ID: yTCoJdsAAAAJ
Tencent AI Lab
Large Reasoning ModelsReinforcement LearningRobust OptimizationStatistical Learning
Citations & Impact
All-time
Citations
442
 
H-index
8
 
i10-index
5
 
Publications
20
 
Co-authors
11
list available
Resume (English only)
Academic Achievements
  • Recipient of the PIMCO Postdoctoral Fellow in Data Science award
  • ML and Systems Rising Stars 2025 award, one of 38 awardees among 150+ applications
  • Theoretical framework bridging robust reinforcement learning and offline reinforcement learning via pessimism accepted to L4DC 2025
  • Undergraduate mentee's work on a theoretical framework addressing transfer setup in reinforcement learning accepted as an oral presentation at AISTATS 2025 (acceptance rate ~2%)
  • New fundamental result on game-theoretic equilibria explaining human behaviors in multi-agent scenarios accepted as an oral presentation at ICLR 2025 (acceptance rate 1.8%)
Background
  • Research interests include machine learning, theoretical foundations of reinforcement learning algorithms, addressing the gap between simulation and real-world performance. Future research will focus on broader domains like multi-agent systems, imitation learning, human feedback, and more. Additional expertise spans optimization, high-dimensional probability, multi-armed bandits, online learning, and stochastic theory.
Miscellany
  • In the job market for full-time faculty positions and core industrial research positions starting in 2025.