Sohrab Andaz

RS at @Amazon tackling real world problems wth RL. #UW Husky. I am a seawolf. Go #knicks.

[Sohrab Andaz @SohrabAndaz]

@thucnhi21 @JoeVeyera ANDDDD we’re rollin’!!!!!!!

[Sohrab Andaz @SohrabAndaz]

@ChShersh Don't forget about awk!!

[Akhil Bagaria @akhil_bagaria]

My RL team at @amazon NYC is looking for summer 2026 PhD interns! We apply RL to Amazon's supply chain and do publishable, open-ended research in meta learning, multi-agent RL, constrained RL, exploration, and LLMs+RL. Interested? Email your CV to [email protected] by Nov 30th!

[Chloe H. Su @Huangyu58589918]

Will be at NY-RL & be working from NYC for Sep 11 - Sep 16
Happy to chat/grab coffee 🥳

[Sohrab Andaz @SohrabAndaz]

There's 1 more day!! If you're in the NYC area, work on RL, and haven't submitted your extended abstract yet, you should now!!

https://t.co/Awin1QZt97

[Akhil Bagaria @akhil_bagaria]

The deadline for submitting your extended abstracts is fast approaching (Aug 21)! Having a poster will guarantee attendance and you don't want to miss out on what promises to be a really fun day with keynotes from @JohnCLangford @criticalneuro @ben_eysenbach and Ludovic Righetti!

[Akhil Bagaria @akhil_bagaria]

🚨New workshop alert 🚨

Calling all RL researchers in the New York area 🧠🗽

Present your work at the first-ever New York Reinforcement Learning Workshop (NYRL), co-organized by Amazon, Columbia Business School & NYU Tandon School of Engineering.

https://t.co/v7MropcLcz

[Akhil Bagaria @akhil_bagaria]

🚨 My RL team at Amazon is looking for PhD interns for this summer! We apply RL to the Amazon supply chain, and do open-ended research in topics such as exploration, multi-agent RL, OPE, and use RL with LLMs for problems such as theorem proving. DM if interested!

[Udaya Ghai @udayaghai]

Excited to share our NeurIPS paper: "Sample-Efficient Agnostic Boosting" (link: https://t.co/fgXQhipeuQ)

This work advances agnostic boosting by proposing a more sample-efficient algorithm without compromising computational complexity. Here's a quick breakdown! (1/6)

[Yuda Song @yus167]

LLM self-improvement has critical implications in synthetic data, post-training and test-time inference. To understand LLMs' true capability of self-improvement, we perform large-scale experiments with multiple families of LLMs, tasks and mechanisms. Here is what we found: (1/9)