Scholar
Kumar Shridhar
Google Scholar ID: rR2qicwAAAAJ
ETH Zurich
Citations & Impact
Citations
3,622
H-index
18
i10-index
19
Publications
20
Co-authors
19
list available
Publications
Resume (English only)
Academic Achievements
- No specific academic achievements like publications, awards, or patents are mentioned.
Research Experience
- During his Ph.D., interned at Meta FAIR with Asli Celikyilmaz on agent-based reasoning; at Microsoft Research with Patrick Xia and Jason Eisner to improve the reasoning capabilities of LLMs by revising their output; and at Amazon Alexa AI on setting constraints on the output space of a neural network. Experienced in fine-tuning LLMs at scale (up to Llama 70B), distilling reasoning capabilities from larger models (GPT-4, Claude, Llama 70B) to smaller ones (Llama, Mistral, T5, GPT-2), and aligning LLMs to generate more accurate and contextually appropriate responses (PPO, DPO, RLHF).
Education
- Pursuing a Ph.D. at ETH Zürich, Switzerland, under the supervision of Prof. Mrinmaya Sachan (ETH) and Nicholas Monath (Google DeepMind).
Background
- Research interests include exploring the reasoning capabilities of large language models and enhancing the reasoning skills of smaller models through effective distillation techniques. Additionally, he is interested in areas such as alignment, autonomous agents, and multimodal models.
Miscellany
- In his free time, enjoys playing tennis, reading about conspiracy theories, and collecting sneakers.
