Fahim Tajwar

Identifiers

• name variant Fahim Tajwar 0.60 · backfill

Papers (7)

1. Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data cs.LG · 2024 · author #1
2. Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias cs.LG · 2023 · author #3
3. Conservative Prediction via Data-Driven Confidence Minimization cs.LG · 2023 · author #2
4. Surgical Fine-Tuning Improves Adaptation to Distribution Shifts cs.LG · 2022 · author #3
5. When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning cs.LG · 2022 · author #2
6. Do Deep Networks Transfer Invariances Across Classes? cs.CV · 2022 · author #2
7. No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets cs.LG · 2021 · author #1

Mentions

• 2404.14367 #1 · arxiv_oai · confidence 0.70 Fahim Tajwar
• 2306.04974 #2 · arxiv_oai · confidence 0.70 Fahim Tajwar
• 2310.08558 #3 · arxiv_oai · confidence 0.70 Fahim Tajwar
• 2210.11466 #3 · arxiv_oai · confidence 0.70 Fahim Tajwar
• 2210.10765 #2 · arxiv_oai · confidence 0.70 Fahim Tajwar
• 2203.09739 #2 · arxiv_oai · confidence 0.70 Fahim Tajwar
• 2109.05554 #1 · arxiv_oai · confidence 0.70 Fahim Tajwar

Frequent Coauthors

• Chelsea Finn 6 shared papers
• Ananya Kumar 3 shared papers
• Archit Sharma 3 shared papers
• Huaxiu Yao 2 shared papers
• Percy Liang 2 shared papers
• Rafael Rafailov 2 shared papers
• Yoonho Lee 2 shared papers
• Alexander Robey 1 shared papers
• Allan Zhou 1 shared papers
• Anikait Singh 1 shared papers
• Annie S. Chen 1 shared papers
• Annie Xie 1 shared papers
• Aviral Kumar 1 shared papers
• Caroline Choi 1 shared papers
• George J. Pappas 1 shared papers
• Hamed Hassani 1 shared papers
• Jeff Schneider 1 shared papers
• Max Sobol Mark 1 shared papers
• Sang Michael Xie 1 shared papers
• Sergey Levine 1 shared papers