Anmol Kabra

I am a Computer Science PhD student at Cornell University, working on LLM post-training and AI for Science. I am fortunate to be advised by Kilian Weinberger and affiliated with AI Materials Institute.

Scientific discovery requires LLM agents to generalize beyond their training distribution, which demands two things: transferable reasoning skills and specialized domain knowledge. Because curating training data for either is expensive and hard to scale, I train LLMs on synthetic data and RL environments that teach transferable skills such as knowledge composition, question decomposition, and retrieval. Along the second axis of specializing agents, I study fine-tuning and context engineering to ground LLMs in scientific domains underrepresented in general pretraining.

Recently as an intern at Snorkel AI, I worked on Terminal-Bench-Science and synthetic RL training environments for scientific AI agents. Previously, I was an AI/ML Quant Intern at Bloomberg’s AI Engineering team, where I prototyped tool-use agents for the ASKB<GO> function. I was also a Research Engineer at ASAPP, working on LLMs, privacy, and anomaly detection with Ethan Elenberg and Kilian Weinberger.

I received my BS in Computer Science from Cornell University and MS from Toyota Technological Institute at Chicago (TTIC). At Cornell, I was named a Merrill Presidential Scholar for my undergraduate research with Carla Gomes and Kilian Weinberger. I was generously supported by the Tata Scholarship and Telluride Scholarship.

Fun fact: I juggle more hobbies than I can juggle number of balls 🤹‍♂️

news

May 2026

Blog post about my collaboration with NVIDIA on LLM RL fine-tuning: Putting the NVIDIA DGX Station to Work at Cornell.
Joined Snorkel AI as an AI Research Intern in San Francisco.

Mar 2026

ICLR 2026 paper invited for Spotlight talk at the NSF-NAIRR annual meeting.
Recognized with Outstanding Reviewer Award at the ICLR DATA-FM Workshop.
3 papers accepted to ICLR 2026 Workshops:
- Learning from Synthetic Data Improves Multi-Hop Reasoning: DATA-FM and VerifAI.
- The Reliability Gap in Agentic Evidence Verification for Materials Science: FM4Science and AI-WILD
- Large Multimodal Models Enable Scalable Monitoring of Aquaculture Ponds: ML for Remote Sensing

Jan 2026

Paper accepted to ICLR 2026: Learning from Synthetic Data Improves Multi-Hop Reasoning with code on github.

2025

Paper accepted to ICML 2025: PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation with code on github.
ICML 2025 paper recognized with Oral award at the ICML Workshop on Long-Context Foundation Models.

2024

Paper released on arxiv: AiSciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification with code on github.
Started PhD at Cornell Computer Science.
Paper accepted to ICML Workshop on Humans, Algorithmic Decision-Making and Society: The Limitations of Model Retraining in the Face of Performativity.
Joined Bloomberg as an AI/ML Quant Intern in New York City.
Paper accepted to Foundations of Responsible Computing (FORC) 2024: Score Design for Multi-Criteria Incentivization, presented a poster.
Talk at TTIC’s Annual Student Workshop: Surrogate score design to incentivize behavior in rating systems.

2023

Paper accepted to Findings of EMNLP 2023: Domain Private Transformers for Multi-Domain Dialog Systems.
Presented at IDEAL Institute’s Workshop on Machine Learning, Interpretability, and Logic: Reasonable modeling assumptions for real-world Principal-Agent games.

2022

Received the Best Poster Award at TTIC’s Annual Student Workshop.
Paper accepted to NeurIPS 2022 and recognized with Oral award: Exponential Family Model-Based Reinforcement Learning via Score Matching.
Joined ASAPP as a Research Intern.
Attended Deep Learning Theory Workshop and Summer School at the Simons Institute at Berkeley.
Visited the Simons Institute at Berkeley for the summer cluster on Interpretable ML.
Attended the ML Theory summer school at Princeton.

2021

Started graduate studies at Toyota Technological Institute at Chicago (TTIC).
Paper accepted to AAAI 2021: Characterizing the Loss Landscape in Non-Negative Matrix Factorization.

2020

Joined ASAPP as a Research Engineer in Ithaca, NY.
Graduated from Cornell!
- Recognized as a 2020 Merrill Presidential Scholar (top 1% of graduating class).
- Received the 2020 Computer Science Prize for Academic Excellence (highest undergraduate honor in the CS department).

2019

Featured among 10 out of 200 young researchers at the 2019 Heidelberg Laureate Forum.
Recognized for outstanding performance (top-10%) at 2019 ACM Summer School on HPC Architectures for AI and Dedicated Applications, Barcelona.
Recognized as an Outstanding Teaching Assistant for CS 4850: Math Foundations of the Info Age.
Paper accepted to ACM COMPASS 2019: GPU-accelerated Principal-Agent Game for Scalable Citizen Science.
- 2 awards at Cornell CIS’s BOOM 2019 project symposium (Sponsor Award by Air Liquide and Statistics Award by Cornell’s Statistics Department).
Joined ASAPP as a Research Engineer Intern.

selected papers

* equal contributions

Learning from Synthetic Data Improves Multi-hop Reasoning

Anmol Kabra, Yilun Yin, Albert Gong, Kamilė Stankevičiūtė, Dongyoung Go, Johann Lee, Katie Z. Luo, Carla P. Gomes, and Kilian Q. Weinberger

In ICLR (2026). (Spotlight talk at NSF-NAIRR annual meeting).

paper bibtex code

@inproceedings{2026kabra_phantomreasoning,
  title = {{Learning from Synthetic Data Improves Multi-hop Reasoning}},
  author = {Kabra, Anmol and Yin, Yilun and Gong, Albert and Stankevičiūtė, Kamilė and Go, Dongyoung and Lee, Johann and Luo, Katie Z. and Gomes, Carla P. and Weinberger, Kilian Q.},
  year = {2026},
  booktitle = {The Fourteenth International Conference on Learning Representations},
}

PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation

Albert Gong*, Kamilė Stankevičiūtė*, Chao Wan*, Anmol Kabra*, Raphael Thesmar, Johann Lee, Julius Klenke, Carla P. Gomes, and Kilian Q. Weinberger

In ICML (2025). (Oral presentation at ICML Workshop on Long Context Foundation Models).

paper bibtex code poster

@inproceedings{2025gong_phantomwiki,
  title = {{PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation}},
  author = {Gong*, Albert and Stankevičiūtė*, Kamilė and Wan*, Chao and Kabra*, Anmol and Thesmar, Raphael and Lee, Johann and Klenke, Julius and Gomes, Carla P. and Weinberger, Kilian Q.},
  year = {2025},
  booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
}

Score Design for Multi-Criteria Incentivization

Anmol Kabra, Mina Karzand, Tosca Lechner, Nathan Srebro, and Serena Wang

In Foundations of Responsible Computing (FORC) (2024).

paper bibtex poster

@inproceedings{2024kabra_FORC_score_design,
  title = {Score Design for Multi-Criteria Incentivization},
  author = {Kabra, Anmol and Karzand, Mina and Lechner, Tosca and Srebro, Nathan and Wang, Serena},
  booktitle = {5th Symposium on Foundations of Responsible Computing (FORC)},
  year = {2024},
}

The Limitations of Model Retraining in the Face of Performativity

Anmol Kabra*, and Kumar Kshitij Patel*

In ICML Workshop on Humans, Algorithmic Decision-Making and Society (2024).

paper bibtex

@inproceedings{2024kabra_limitations_retraining,
  title = {The Limitations of Model Retraining in the Face of Performativity},
  author = {Kabra*, Anmol and Patel*, Kumar Kshitij},
  booktitle = {ICML Workshop on Humans, Algorithmic Decision-Making and Society},
  year = {2024},
}

AISciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification

Brendan Hogan, Anmol Kabra, Felipe Siqueira Pacheco, Laura Greenstreet, Joshua Fan, Aaron Ferber, Marta Ummus, Alecsander Brito, Olivia Graham, Lillian Aoki, Drew Harvell, Alex Flecker, and Carla Gomes

Preprint (2024).

paper bibtex code

@unpublished{2024hogan_aiscivision,
  title = {{AISciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification}},
  author = {Hogan, Brendan and Kabra, Anmol and Pacheco, Felipe Siqueira and Greenstreet, Laura and Fan, Joshua and Ferber, Aaron and Ummus, Marta and Brito, Alecsander and Graham, Olivia and Aoki, Lillian and Harvell, Drew and Flecker, Alex and Gomes, Carla},
  year = {2024},
  note = {Preprint},
}

Domain Private Transformers for Multi-Domain Dialog Systems

Anmol Kabra, and Ethan R. Elenberg

In Findings-EMNLP (2023).

paper bibtex poster

@inproceedings{2023kabra_domain_privacy,
  title = {Domain Private Transformers for Multi-Domain Dialog Systems},
  author = {Kabra, Anmol and Elenberg, Ethan R.},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP},
  year = {2023},
}

Exponential Family Model-Based Reinforcement Learning via Score Matching

Gene Li, Junbo Li, Anmol Kabra, Nathan Srebro, Zhaoran Wang, and Zhuoran Yang

In NeurIPS (2022). (Oral presentation).

paper bibtex code poster

@inproceedings{2022li_score_matching,
  title = {Exponential Family Model-Based Reinforcement Learning via Score Matching},
  author = {Li, Gene and Li, Junbo and Kabra, Anmol and Srebro, Nathan and Wang, Zhaoran and Yang, Zhuoran},
  booktitle = {Advances in Neural Information Processing Systems},
  volume = {35},
  pages = {28474--28487},
  year = {2022},
}

Characterizing the Loss Landscape in Non-Negative Matrix Factorization

Johan Bjorck, Anmol Kabra, Kilian Q. Weinberger, and Carla P. Gomes

In AAAI (2021).

paper bibtex

@inproceedings{2021bjorck_nmf,
  title = {Characterizing the Loss Landscape in Non-Negative Matrix Factorization},
  author = {Bjorck, Johan and Kabra, Anmol and Weinberger, Kilian Q. and Gomes, Carla P.},
  booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
  volume = {35},
  number = {8},
  pages = {6768--6776},
  year = {2021},
  doi = {10.1609/aaai.v35i8.16836},
  url = {https://doi.org/10.1609/aaai.v35i8.16836},
}

for fun beyond research, I like

(sorted ascending by number of characters per item)

biking
cooking
running
juggling
being outdoors
playing Table Tennis
following Formula 1 and motorsports
walking fast so that my legs heat up
reading books, newspapers, and research papers — mostly high-fantasy and non-fiction these days