Alert button
Picture for Rahul Ramesh

Rahul Ramesh

Alert button

Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model

Feb 12, 2024
Mikail Khona, Maya Okawa, Jan Hula, Rahul Ramesh, Kento Nishi, Robert Dick, Ekdeep Singh Lubana, Hidenori Tanaka

Viaarxiv icon

How Capable Can a Transformer Become? A Study on Synthetic, Interpretable Tasks

Nov 21, 2023
Rahul Ramesh, Mikail Khona, Robert P. Dick, Hidenori Tanaka, Ekdeep Singh Lubana

Viaarxiv icon

The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold

May 02, 2023
Jialin Mao, Itay Griniasty, Han Kheng Teoh, Rahul Ramesh, Rubing Yang, Mark K. Transtrum, James P. Sethna, Pratik Chaudhari

Figure 1 for The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
Figure 2 for The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
Figure 3 for The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
Figure 4 for The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
Viaarxiv icon

A picture of the space of typical learnable tasks

Oct 31, 2022
Rahul Ramesh, Jialin Mao, Itay Griniasty, Rubing Yang, Han Kheng Teoh, Mark Transtrum, James P. Sethna, Pratik Chaudhari

Figure 1 for A picture of the space of typical learnable tasks
Figure 2 for A picture of the space of typical learnable tasks
Figure 3 for A picture of the space of typical learnable tasks
Figure 4 for A picture of the space of typical learnable tasks
Viaarxiv icon

The Value of Out-of-Distribution Data

Aug 23, 2022
Ashwin De Silva, Rahul Ramesh, Carey E. Priebe, Pratik Chaudhari, Joshua T. Vogelstein

Figure 1 for The Value of Out-of-Distribution Data
Figure 2 for The Value of Out-of-Distribution Data
Figure 3 for The Value of Out-of-Distribution Data
Figure 4 for The Value of Out-of-Distribution Data
Viaarxiv icon

Deep Reference Priors: What is the best way to pretrain a model?

Feb 01, 2022
Yansong Gao, Rahul Ramesh, Pratik Chaudhari

Figure 1 for Deep Reference Priors: What is the best way to pretrain a model?
Figure 2 for Deep Reference Priors: What is the best way to pretrain a model?
Figure 3 for Deep Reference Priors: What is the best way to pretrain a model?
Figure 4 for Deep Reference Priors: What is the best way to pretrain a model?
Viaarxiv icon

Boosting a Model Zoo for Multi-Task and Continual Learning

Jun 06, 2021
Rahul Ramesh, Pratik Chaudhari

Figure 1 for Boosting a Model Zoo for Multi-Task and Continual Learning
Figure 2 for Boosting a Model Zoo for Multi-Task and Continual Learning
Figure 3 for Boosting a Model Zoo for Multi-Task and Continual Learning
Figure 4 for Boosting a Model Zoo for Multi-Task and Continual Learning
Viaarxiv icon

Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning

Sep 09, 2019
Arjun Manoharan, Rahul Ramesh, Balaraman Ravindran

Figure 1 for Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning
Figure 2 for Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning
Figure 3 for Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning
Figure 4 for Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning
Viaarxiv icon

Successor Options: An Option Discovery Framework for Reinforcement Learning

May 14, 2019
Rahul Ramesh, Manan Tomar, Balaraman Ravindran

Figure 1 for Successor Options: An Option Discovery Framework for Reinforcement Learning
Figure 2 for Successor Options: An Option Discovery Framework for Reinforcement Learning
Figure 3 for Successor Options: An Option Discovery Framework for Reinforcement Learning
Figure 4 for Successor Options: An Option Discovery Framework for Reinforcement Learning
Viaarxiv icon

A Question-Answering framework for plots using Deep learning

Jun 12, 2018
Revanth Reddy, Rahul Ramesh, Ameet Deshpande, Mitesh M. Khapra

Figure 1 for A Question-Answering framework for plots using Deep learning
Figure 2 for A Question-Answering framework for plots using Deep learning
Figure 3 for A Question-Answering framework for plots using Deep learning
Figure 4 for A Question-Answering framework for plots using Deep learning
Viaarxiv icon