Scholar
Lovish Madaan
Google Scholar ID: zc2WyXkAAAAJ
AI at Meta & University College London
Citations & Impact
Citations
10,904
H-index
8
i10-index
7
Publications
16
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Publications:
- - 'The Art of Scaling Reinforcement Learning Compute for LLMs' and other arXiv Preprints
- - 'MLGym: A New Framework and Benchmark for Advancing AI Research Agents' (COLM 2025)
- - 'HARP: A challenging human-annotated math reasoning benchmark' (arXiv Preprint)
- - 'Lost in Inference: Rediscovering the Role of Natural Language Inference for Large Language Models' (NAACL 2025)
- - 'Quantifying Variance in Evaluation Benchmarks' (Regulatable ML, NeurIPS 2024)
- - 'Treeformer: Dense Gradient Trees for Efficient Attention Computation' (ICLR 2023)
- - 'Field Study in Deploying Restless Multi-Armed Bandits: Assisting Non-profits in Improving Maternal and Child Health' (AAAI 2022), Best Paper Award.
Research Experience
- Worked at Google Research India in the Machine Learning and Optimization Team with Prateek Jain and Srinadh Bhojanapalli on inference-efficient machine learning and natural language processing.
Education
- Indian Institute of Technology, Delhi, B.Tech and M.Tech in Computer Science and Engineering; Advisors: Parag Singla, Sayan Ranu, and Aaditeshwar Seth.
Background
- Research Interests: Thinking models, self-improvement, and better evaluations. Currently pursuing a PhD at Meta AI and UCL NLP.
Co-authors