Aniket Didolkar

I am a Ph.D. Student at Mila, Montreal and The University of Montreal advised by Prof. Yoshua Bengio and Dr. Anirudh Goyal . Prior to joining my Ph.D., I was a masters student at Mila.

I received my bachelors degree in computer science from Manipal Institute of Technology, India . During my bachelors, I worked as a researcher at MIDAS Lab at IIIT Delhi advised by Professor Rajiv Ratn Shah . I have also interned at IISc Bangalore advised by Prof. Aditya Gopalan and Prof. Himanshu Tyagi for my bachelor's thesis on air quality monitoring and prediction.

I have also spent some time in the industry at Microsoft Research - NYC (Fall 2022), Ubisoft (Summer 2019) and Symbl.ai (summer 2018). I also spent the summer of 2019 building ChainerX -- an open source deep learning library -- as a part of Google Summer of Code.

CV  /  Email  /  Google Scholar  /  Twitter  /  Github

I am interested in building models inspired by human inductive biases that can build on prior knowledge to solve various out-of-distribution scenarios.

A framework is presented for extracting Metacognitive knowledge from LLMs and using it to improve reasoning in LLMs.

Introduced auxillary objectives based on cycle consistency for unsupervised object discovery.

Utilized the multi-step inverse dynamics objective for learning robust RL policies in noisy environments.

Utilized discrete bottlenecks such as VQVAE to learn robust RL policies in noisy RL environments.

Introducing a recurrent stream into the Transformer architecture.

Algorithm for discovery of the minimal controllable latent state that has all the information for controlling an agent while learning to discard all other irrelevant information

Facilitating communication between modules using limited-capacity bottleneck.

Dynamically constructing sparse graphs for modulating communication between objects.

A new and highly-flexible benchmark for evaluation of causal discovery in model-based RL.

Proposed a new formulation of mixup for NLP.

Applied mixup in the domain of speech processing.

Leveraging social media connectivity through a graph for profiling hate speech on twitter.

Reproduced the paper h-detach: Modifying the LSTM gradient towards better optimization as a part of the ICLR 2019 reproducibility challenge.