Tajwar, Fahim

1. Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
   2022/10/20 by Lee, Yoonho, Chen, Annie S., Tajwar, Fahim +4 · 19 citations
   #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)
2. Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data
   2024/04/22 by Fahim Tajwar, Anikait Singh, Tajwar, Fahim +15 · 25 citations
   Decision Sciences · Economics, Econometrics and Finance · #Efficiency Analysis Using DEA #Healthcare Policy and Management #Auction Theory and Applications
3. No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets
   2021/09/12 by Tajwar, Fahim, Kumar, Ananya, Xie, Sang Michael +1 · 4 citations
   #FOS: Computer and information sciences #Machine Learning (cs.LG)
4. When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning
   2022/10/19 by Xie, Annie, Tajwar, Fahim, Sharma, Archit +1 · 4 citations
   #FOS: Computer and information sciences #Machine Learning (cs.LG)
5. Can Large Reasoning Models Self-Train?
   2025/05/27 by Shafayat, Sheikh, Tajwar, Fahim, Salakhutdinov, Ruslan +2 · 15 citations
   #FOS: Computer and information sciences #Machine Learning (cs.LG)
6. Training a Generally Curious Agent
   2025/02/24 by Fahim Tajwar, Yiding Jiang, Tajwar, Fahim +10 · 8 citations
   Computer Science · #AI in Service Interactions #Artificial Intelligence (cs.AI) #Artificial Intelligence in Games #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG)
7. Reasoning as an Adaptive Defense for Safety
   2025/07/01 by Taeyoun Kim, Fahim Tajwar, Kim, Taeyoun +5 · 9 citations
   Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Security and Verification in Computing #Software Testing and Debugging Techniques