Picture for Dhanya Sridhar

Dhanya Sridhar

Sparsity regularization via tree-structured environments for disentangled representations

Add code
Jun 10, 2024
Viaarxiv icon

Leveraging Structure Between Environments: Phylogenetic Regularization Incentivizes Disentangled Representations

Add code
May 30, 2024
Viaarxiv icon

Does learning the right latent variables necessarily improve in-context learning?

Add code
May 29, 2024
Viaarxiv icon

Demystifying amortized causal discovery with transformers

May 27, 2024
Viaarxiv icon

Evaluating Interventional Reasoning Capabilities of Large Language Models

Add code
Apr 08, 2024
Viaarxiv icon

In-Context Learning Can Re-learn Forbidden Tasks

Add code
Feb 08, 2024
Viaarxiv icon

Estimating Social Influence from Observational Data

Add code
Mar 24, 2022
Figure 1 for Estimating Social Influence from Observational Data
Figure 2 for Estimating Social Influence from Observational Data
Figure 3 for Estimating Social Influence from Observational Data
Figure 4 for Estimating Social Influence from Observational Data
Viaarxiv icon

Identifiable Variational Autoencoders via Sparse Decoding

Oct 20, 2021
Figure 1 for Identifiable Variational Autoencoders via Sparse Decoding
Figure 2 for Identifiable Variational Autoencoders via Sparse Decoding
Figure 3 for Identifiable Variational Autoencoders via Sparse Decoding
Figure 4 for Identifiable Variational Autoencoders via Sparse Decoding
Viaarxiv icon

Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond

Add code
Sep 02, 2021
Figure 1 for Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
Viaarxiv icon

Causal Effects of Linguistic Properties

Add code
Oct 24, 2020
Figure 1 for Causal Effects of Linguistic Properties
Figure 2 for Causal Effects of Linguistic Properties
Figure 3 for Causal Effects of Linguistic Properties
Figure 4 for Causal Effects of Linguistic Properties
Viaarxiv icon