Sotabase

Career

· Angel Investor, Aravind Srinivas (Current)2023–
· Cofounder, President, CEO, Perplexity2022–
· Research Scientist, OpenAI2021–2022
· Research Intern, Google2020–2021
· Research Intern, DeepMind2019–2019
· Research Intern, OpenAI2018–2018
· Doctor's degree in philosophy, University of California Berkeley2017–2021
· B.Tech and M.Tech, Indian Institute of Technology Madras

Publications (35)

Decision Transformer: Reinforcement Learning via Sequence Modeling
Neural Information Processing Systems · 2021
2,039
cited
Data-Efficient Image Recognition with Contrastive Predictive Coding
International Conference on Machine Learning · 2019
1,525
cited
CURL: Contrastive Unsupervised Representations for Reinforcement Learning
International Conference on Machine Learning · 2020
1,221
cited
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
Computer Vision and Pattern Recognition · 2020
1,175
cited
Bottleneck Transformers for Visual Recognition
Computer Vision and Pattern Recognition · 2021
1,131
cited
Reinforcement Learning with Augmented Data
Neural Information Processing Systems · 2020
742
cited
VideoGPT: Video Generation using VQ-VAE and Transformers
arXiv.org · 2021
654
cited
Deep Reinforcement Learning
International Conference on Computing Communication and Networking Technologies · 2023
529
cited
Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
International Conference on Machine Learning · 2019
487
cited
Scaling Local Self-Attention for Parameter Efficient Visual Backbones
Computer Vision and Pattern Recognition · 2021
461
cited
Revisiting ResNets: Improved Training and Scaling Strategies
Neural Information Processing Systems · 2021
346
cited
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning
International Conference on Machine Learning · 2020
230
cited
Universal Planning Networks
International Conference on Machine Learning · 2018
146
cited
Dynamic Action Repetition for Deep Reinforcement Learning
AAAI Conference on Artificial Intelligence · 2017
75
cited
D2RL: Deep Dense Architectures in Reinforcement Learning
arXiv.org · 2020
62
cited
Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain
International Conference on Learning Representations · 2015
54
cited
SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning
Computer Vision and Pattern Recognition · 2020
54
cited
Option Discovery in Hierarchical Reinforcement Learning using Spatio-Temporal Clustering
2016
44
cited
Reinforcement Learning with Latent Flow
Neural Information Processing Systems · 2021
27
cited
Dynamic Frame skip Deep Q Network
arXiv.org · 2016
24
cited
Sotabase
Aravind Srinivas | Researcher Profile | Sotabase | Sotabase