Follow
Aniket Didolkar
Aniket Didolkar
MILA - Quebec AI Institute
Verified email at mila.quebec - Homepage
Title
Cited by
Cited by
Year
Coordination among neural modules through a shared global workspace
A Goyal, A Didolkar, A Lamb, K Badola, NR Ke, N Rahaman, J Binas, ...
arXiv preprint arXiv:2103.01197, 2021
922021
Neural Production Systems
A Goyal, A Didolkar, NR Ke, C Blundell, P Beaudoin, N Heess, M Mozer, ...
arXiv preprint arXiv:2103.01937, 2021
86*2021
Systematic evaluation of causal discovery in visual model based reinforcement learning
NR Ke, A Didolkar, S Mittal, A Goyal, G Lajoie, S Bauer, D Rezende, ...
arXiv preprint arXiv:2107.00848, 2021
392021
ARHNet-Leveraging Community Interaction for Detection of Religious Hate Speech in Arabic
A Didolkar, AG Chowdhury, R Sawhney, R Shah
Proceedings of the 57th Conference of the Association for Computational …, 2019
35*2019
Augmenting NLP models using latent feature interpolations
A Jindal, AG Chowdhury, A Didolkar, D Jin, R Sawhney, R Shah
Proceedings of the 28th International Conference on Computational …, 2020
252020
Guaranteed discovery of controllable latent states with multi-step inverse models
A Lamb, R Islam, Y Efroni, A Didolkar, D Misra, D Foster, L Molu, R Chari, ...
arXiv preprint arXiv:2207.08229, 2022
232022
SpeechMix-Augmenting Deep Sound Recognition Using Hidden Space Interpolations.
A Jindal, NE Ranganatha, A Didolkar, AG Chowdhury, D Jin, R Sawhney, ...
INTERSPEECH, 861-865, 2020
192020
Agent-controller representations: Principled offline rl with rich exogenous information
R Islam, M Tomar, A Lamb, Y Efroni, H Zang, A Didolkar, D Misra, X Li, ...
arXiv preprint arXiv:2211.00164, 2022
122022
Guaranteed discovery of control-endogenous latent states with multi-step inverse models
A Lamb, R Islam, Y Efroni, A Didolkar, D Misra, D Foster, L Molu, R Chari, ...
arXiv preprint arXiv:2207.08229, 2022
102022
Temporal latent bottleneck: Synthesis of fast and slow processing mechanisms in sequence learning
A Didolkar, K Gupta, A Goyal, NB Gundavarapu, AM Lamb, NR Ke, ...
Advances in Neural Information Processing Systems 35, 10505-10520, 2022
92022
Beyond hostile linguistic cues: The gravity of online milieu for hate speech detection in arabic
A Didolkar, A Ghosh Chowdhury, R Sawhney, R Ratn Shah
Proceedings of the 30th ACM Conference on Hypertext and Social Media, 285-286, 2019
6*2019
Representation learning in deep rl via discrete information bottleneck
R Islam, H Zang, M Tomar, A Didolkar, MM Islam, SY Arnob, T Iqbal, X Li, ...
arXiv preprint arXiv:2212.13835, 2022
32022
Cycle consistency driven object discovery
A Didolkar, A Goyal, Y Bengio
arXiv preprint arXiv:2306.02204, 2023
22023
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
A Didolkar, A Goyal, NR Ke, S Guo, M Valko, T Lillicrap, D Rezende, ...
arXiv preprint arXiv:2405.12205, 2024
12024
Principled offline RL in the presence of rich exogenous information
R Islam, M Tomar, A Lamb, Y Efroni, H Zang, AR Didolkar, D Misra, X Li, ...
12023
Learning Beyond Pattern Matching? Assaying Mathematical Understanding in LLMs
S Guo, A Didolkar, NR Ke, A Goyal, F Huszár, B Schölkopf
arXiv preprint arXiv:2405.15485, 2024
2024
CNT (Conditioning on Noisy Targets): A new Algorithm for Leveraging Top-Down Feedback
A Jolicoeur-Martineau, A Lamb, V Verma, A Didolkar
arXiv preprint arXiv:2210.09505, 2022
2022
[Re] On Adverserial Mixup Resynthesis
NE Ranganatha, A Didolkar
2019
[Re] h-detach: Modifying the LSTM gradient towards better optimization.
A Didolkar
ReScience C 5 (2), 2019
2019
Active learning to discover pairwise genetic interactions via representation learning
M Jain, AK Denton, ST Whitfield, AR Didolkar, B Earnshaw, J Hartford
ICLR 2024 Workshop on Machine Learning for Genomics Explorations, 0
The system can't perform the operation now. Try again later.
Articles 1–20