FT
Fahim Tajwar
cs.LGcs.AIcs.CLair pollutionBangladeshcs.CVcs.ROdeep learningenvironmental regulationssatellite imagery
On Valency
published · living versionsW_s6bdne4e·v1 · currentpublished
Training Foundation Models with a Single Algorithm
with Yuda Song, Alvin Zhang, Daman Arora, Jeff Schneider +5
1 version
Preprints & journals
20 papers in the corpus · 2021–2026Training Language Models to Fail Gracefully2610.20401v1 · Daman Arora, Xuecheng Liu, Himanshu Gaurav Singh et al.2026 · 0 citationsarXiv
Harness Learning Enables Generalizable Test-Time Adaptation2609.35738v1 · Alvin Zhang, Xuecheng Liu, Zixuan Wang et al.2026 · 0 citationsarXiv
Tail-Likelihood Reinforcement Learning2609.02987v2 · Shrinivas Ramasubramanian, Daman Arora, Fahim Tajwar et al.2026 · 0 citationsarXiv
Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models2602.17497v1 · Wen-Tse Chen, Jiayu Chen, Fahim Tajwar et al.2026 · 0 citationsarXiv
Expanding the Capabilities of Reinforcement Learning via Text Feedback2602.02482v2 · Yuda Song, Lili Chen, Fahim Tajwar et al.2026 · 0 citationsarXiv
Maximum Likelihood Reinforcement Learning2602.02710v3 · Fahim Tajwar, Guanning Zeng, Yueer Zhou et al.2026 · 0 citationsarXiv
Reasoning as an Adaptive Defense for Safety2507.00971v2 · Taeyoun Kim, Fahim Tajwar, Aditi Raghunathan et al.2025 · 0 citationsarXiv
Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation2506.07822v3 · Xintong Duan, Yutong He, Fahim Tajwar et al.2025 · 0 citationsarXiv
Can Large Reasoning Models Self-Train?2505.21444v2 · Sheikh Shafayat, Fahim Tajwar, Ruslan Salakhutdinov et al.2025 · 0 citationsarXiv
Training a Generally Curious Agent2502.17543v4 · Fahim Tajwar, Yiding Jiang, Abitha Thankaraj et al.2025 · 0 citationsarXiv
Self-Regulation and Requesting Interventions2502.04576v1 · So Yeon Min, Yue Wu, Jimin Sun et al.2025 · 1 citationarXiv
State Combinatorial Generalization In Decision Making With Conditional Diffusion Models2501.13241v2 · Xintong Duan, Yutong He, Fahim Tajwar et al.2025 · 0 citationsarXiv
Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data2404.14367v3 · Fahim Tajwar, Anikait Singh, Archit Sharma et al.2024 · 4 citationsarXiv
Offline Retraining for Online RL: Decoupled Policy Learning to Mitigate Exploration Bias2310.08558v1 · Max Sobol Mark, Archit Sharma, Fahim Tajwar et al.2023 · 1 citationarXiv
Conservative Prediction via Data-Driven Confidence Minimization2306.04974v2 · Caroline Choi, Fahim Tajwar, Yoonho Lee et al.2023 · 1 citationarXiv
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts2210.11466v3 · Yoonho Lee, Annie S. Chen, Fahim Tajwar et al.2022 · 72 citationsarXiv
When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning2210.10765v1 · Annie Xie, Fahim Tajwar, Archit Sharma et al.2022 · 6 citationsarXiv
Do Deep Networks Transfer Invariances Across Classes?2203.09739v1 · Allan Zhou, Fahim Tajwar, Alexander Robey et al.2022 · 4 citationsarXiv
No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets2109.05554v1 · Fahim Tajwar, Ananya Kumar, Sang Michael Xie et al.2021 · 11 citationsarXiv
Scalable deep learning to identify brick kilns and aid regulatory capacity.33888583 · Lee, Jihyeon, Brooks, Nina R, Tajwar, Fahim et al.2021 · 45 citationsProceedings of the National Academy of Sciences of the United States of America. 2021;118(17)
Career total: 22 works. 20 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.