Scholar
Aniket Didolkar
Google Scholar ID: ekvl5o0AAAAJ
MILA - Quebec AI Institute
Citations & Impact
Citations
643
H-index
12
i10-index
14
Publications
20
Co-authors
18
list available
Publications
Resume (English only)
Academic Achievements
- Published papers: 'Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving' (NeurIPS 2024), 'On the Transfer of Object-Centric Representation Learning' (ICLR 2025), 'CTRL-O: Language-Controllable Object-Centric Visual Representation Learning' (CVPR 2025), etc.
Research Experience
- Worked with Dr. Anirudh Goyal and Prof. Yoshua Bengio on cognitive science-inspired deep learning projects at Mila; Research intern at Valence Labs, working with Dr. Jason Hartford; Intern at Microsoft Research NYC, working with Dr. Alex Lamb on reinforcement learning; Google Summer of Code student developer, contributed CUDA-optimized implementations of RNNs, GRUs, and LSTMs to the ChainerX deep learning library; Collaborated with Prof. Rajiv Ratn Shah at IIIT Delhi on NLP projects; Worked with Prof. Aditya Gopalan at IISc Bangalore on time-series forecasting models for urban pollution.
Education
- Ph.D. student at the University of Montreal, advised by Prof. Yoshua Bengio, Dr. Anirudh Goyal, and Prof. Michael Mozer.
Background
- Research interests include building deep learning techniques inspired by cognitive science, designing models that learn and reason like humans. Recently, his research has focused on the metacognitive abilities of large language models (LLMs) in the context of mathematical problem solving.
Miscellany
- Personal interests not mentioned.
