Search Results for author: Saachi Jain

Found 10 papers, 9 papers with code

Learning to Speak and Act in a Fantasy Text Adventure Game

1 code implementation IJCNLP 2019 Jack Urbanek, Angela Fan, Siddharth Karamcheti, Saachi Jain, Samuel Humeau, Emily Dinan, Tim Rocktäschel, Douwe Kiela, Arthur Szlam, Jason Weston

We analyze the ingredients necessary for successful grounding in this setting, and how each of these factors relate to agents that can talk and act successfully.

Retrieval

Dataset Interfaces: Diagnosing Model Failures Using Controllable Counterfactual Generation

1 code implementation15 Feb 2023 Joshua Vendrow, Saachi Jain, Logan Engstrom, Aleksander Madry

In this work, we introduce the notion of a dataset interface: a framework that, given an input dataset and a user-specified shift, returns instances from that input distribution that exhibit the desired shift.

counterfactual

Distilling Model Failures as Directions in Latent Space

1 code implementation29 Jun 2022 Saachi Jain, Hannah Lawrence, Ankur Moitra, Aleksander Madry

Moreover, by combining our framework with off-the-shelf diffusion models, we can generate images that are especially challenging for the analyzed model, and thus can be used to perform synthetic data augmentation that helps remedy the model's failure modes.

Data Augmentation

Certified Patch Robustness via Smoothed Vision Transformers

1 code implementation CVPR 2022 Hadi Salman, Saachi Jain, Eric Wong, Aleksander Mądry

Certified patch defenses can guarantee robustness of an image classifier to arbitrary changes within a bounded contiguous region.

A Data-Based Perspective on Transfer Learning

1 code implementation CVPR 2023 Saachi Jain, Hadi Salman, Alaa Khaddaj, Eric Wong, Sung Min Park, Aleksander Madry

It is commonly believed that in transfer learning including more pre-training data translates into better performance.

Transfer Learning

MASA: Motif-Aware State Assignment in Noisy Time Series Data

1 code implementation6 Sep 2018 Saachi Jain, David Hallac, Rok Sosic, Jure Leskovec

Such data can be interpreted as a sequence of states, where each state represents a prototype of system behavior.

Clustering Time Series +1

When does Bias Transfer in Transfer Learning?

1 code implementation6 Jul 2022 Hadi Salman, Saachi Jain, Andrew Ilyas, Logan Engstrom, Eric Wong, Aleksander Madry

Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside.

Transfer Learning

Combining Diverse Feature Priors

1 code implementation15 Oct 2021 Saachi Jain, Dimitris Tsipras, Aleksander Madry

To improve model generalization, model designers often restrict the features that their models use, either implicitly or explicitly.

Missingness Bias in Model Debugging

1 code implementation ICLR 2022 Saachi Jain, Hadi Salman, Eric Wong, Pengchuan Zhang, Vibhav Vineet, Sai Vemprala, Aleksander Madry

Missingness, or the absence of features from an input, is a concept fundamental to many model debugging tools.

A Mechanism for Producing Aligned Latent Spaces with Autoencoders

no code implementations29 Jun 2021 Saachi Jain, Adityanarayanan Radhakrishnan, Caroline Uhler

Aligned latent spaces, where meaningful semantic shifts in the input space correspond to a translation in the embedding space, play an important role in the success of downstream tasks such as unsupervised clustering and data imputation.

Clustering Imputation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.