Vashisth Tiwari

PhD @ Carnegie Mellon | Previously- SR @ Google

prof_pic_2.jpg
Hi! 👋

I'm a first-year PhD student at Carnegie Mellon University's Language Technologies Institute, advised by Emma Strubell and Zico Kolter.

My research focuses on making better and more efficient smaller models through improvements to both training and data. I'm particularly interested in distillation, synthetic data generation, and reinforcement learning for post-training.

I’ve been fortunate to learn from wonderful mentors, including Giulia DeSalvo (DeepMind), Beidi Chen (CMU), Lucio Dery (CMU/DeepMind), and Clara Na (CMU).

Before the PhD, I completed my Masters in ECE at CMU and a B.S. in Physics and Mathematics at the University of Rochester. I was a Rhodes Scholarship Semi-Finalist (India) and received the Harry W. Fulbright Prize for experimental physics. In my past life, I worked on quantum sensing and computational astrophysics.

I am looking for summer 2026 internships—feel free to reach out if you see a good fit :).


Outside of work, I love photography—check out my portfolio and Instagram. I spent much of my life playing badminton, including on the team at the University of Rochester, and now I'm playing tennis.

I love food and coffee, perhaps a bit too much. I'm always on the lookout for new spots—so if you have recommendations, send them my way :).


news

May 19, 2025 Student Researcher @GoogleResearch (📍Seattle) w/ Giulia DeSalvo on synthetic data for post-training
May 15, 2025 ACL Main (Energy considerations on LLM inference)
Apr 14, 2025 Will be joining CMU-LTI PhD Fall’25 cohort
Jan 23, 2025 ICLR'25 (MagicDec)
Aug 19, 2024 Released MagicDec: Breaking Throughput-Latency Trade-off for Long Context Generation with Speculative Decoding. Blog
Feel free to reach out at vashistt [at] cs [dot] cmu [dot] edu.