Search Results for author: Varun Manjunatha

Found 23 papers, 10 papers with code

IGA: An Intent-Guided Authoring Assistant

no code implementations EMNLP 2021 Simeng Sun, Wenlong Zhao, Varun Manjunatha, Rajiv Jain, Vlad Morariu, Franck Dernoncourt, Balaji Vasan Srinivasan, Mohit Iyyer

While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored.

Language Modelling Sentence

Localizing and Editing Knowledge in Text-to-Image Generative Models

no code implementations20 Oct 2023 Samyadeep Basu, Nanxuan Zhao, Vlad Morariu, Soheil Feizi, Varun Manjunatha

We adapt Causal Mediation Analysis for text-to-image models and trace knowledge about distinct visual attributes to various (causal) components in the (i) UNet and (ii) text-encoder of the diffusion model.

Attribute Image Generation +1

KNN-LM Does Not Improve Open-ended Text Generation

no code implementations24 May 2023 Shufan Wang, Yixiao Song, Andrew Drozdov, Aparna Garimella, Varun Manjunatha, Mohit Iyyer

Digging deeper, we find that interpolating with a retrieval distribution actually increases perplexity compared to a baseline Transformer LM for the majority of tokens in the WikiText-103 test set, even though the overall perplexity is lower due to a smaller number of tokens for which perplexity dramatically decreases after interpolation.

Retrieval Text Generation

Influence Functions for Sequence Tagging Models

1 code implementation25 Oct 2022 Sarthak Jain, Varun Manjunatha, Byron C. Wallace, Ani Nenkova

We show the practical utility of segment influence by using the method to identify systematic annotation errors in two named entity recognition corpora.

named-entity-recognition Named Entity Recognition +3

Certified Neural Network Watermarks with Randomized Smoothing

1 code implementation16 Jul 2022 Arpit Bansal, Ping-Yeh Chiang, Michael Curry, Rajiv Jain, Curtis Wigington, Varun Manjunatha, John P Dickerson, Tom Goldstein

Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio.

Syntopical Graphs for Computational Argumentation Tasks

no code implementations ACL 2021 Joe Barrow, Rajiv Jain, Nedim Lipka, Franck Dernoncourt, Vlad Morariu, Varun Manjunatha, Douglas Oard, Philip Resnik, Henning Wachsmuth

Approaches to computational argumentation tasks such as stance detection and aspect detection have largely focused on the text of independent claims, losing out on potentially valuable context provided by the rest of the collection.

Stance Detection

SelfDoc: Self-Supervised Document Representation Learning

no code implementations CVPR 2021 Peizhao Li, Jiuxiang Gu, Jason Kuen, Vlad I. Morariu, Handong Zhao, Rajiv Jain, Varun Manjunatha, Hongfu Liu

For downstream usage, we propose a novel modality-adaptive attention mechanism for multimodal feature fusion by adaptively emphasizing language and vision signals.

Representation Learning

TABBIE: Pretrained Representations of Tabular Data

2 code implementations NAACL 2021 Hiroshi Iida, Dung Thai, Varun Manjunatha, Mohit Iyyer

Existing work on tabular representation learning jointly models tables and associated text using self-supervised objective functions derived from pretrained language models such as BERT.

 Ranked #1 on Column Type Annotation on VizNet-Sato-Full (Weighted-F1 metric)

Cell Detection Column Type Annotation +1

RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks

no code implementations18 Apr 2021 Kai Li, Curtis Wigington, Chris Tensmeyer, Vlad I. Morariu, Handong Zhao, Varun Manjunatha, Nikolaos Barmpalios, Yun Fu

Contrasted with prior work, this paper provides a complementary solution to align domains by learning the same auxiliary tasks in both domains simultaneously.

IGA : An Intent-Guided Authoring Assistant

1 code implementation14 Apr 2021 Simeng Sun, Wenlong Zhao, Varun Manjunatha, Rajiv Jain, Vlad Morariu, Franck Dernoncourt, Balaji Vasan Srinivasan, Mohit Iyyer

While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored.

Language Modelling Sentence

Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models

no code implementations NAACL 2021 Mengnan Du, Varun Manjunatha, Rajiv Jain, Ruchi Deshpande, Franck Dernoncourt, Jiuxiang Gu, Tong Sun, Xia Hu

These two observations are further employed to formulate a measurement which can quantify the shortcut degree of each training sample.

Cross-Domain Document Object Detection: Benchmark Suite and Method

1 code implementation CVPR 2020 Kai Li, Curtis Wigington, Chris Tensmeyer, Handong Zhao, Nikolaos Barmpalios, Vlad I. Morariu, Varun Manjunatha, Tong Sun, Yun Fu

We establish a benchmark suite consisting of different types of PDF document datasets that can be utilized for cross-domain DOD model training and evaluation.

object-detection Object Detection

Explicit Bias Discovery in Visual Question Answering Models

no code implementations CVPR 2019 Varun Manjunatha, Nirat Saini, Larry S. Davis

It is of interest to the community to explicitly discover such biases, both for understanding the behavior of such models, and towards debugging them.

Question Answering Visual Question Answering

Class Subset Selection for Transfer Learning using Submodularity

no code implementations30 Mar 2018 Varun Manjunatha, Srikumar Ramalingam, Tim K. Marks, Larry Davis

To accomplish this, we use a submodular set function to model the accuracy achievable on a new task when the features have been learned on a given subset of classes of the source dataset.

Image Classification Transfer Learning

The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives

2 code implementations CVPR 2017 Mohit Iyyer, Varun Manjunatha, Anupam Guha, Yogarshi Vyas, Jordan Boyd-Graber, Hal Daumé III, Larry Davis

While computers can now describe what is explicitly depicted in natural images, in this paper we examine whether they can understand the closure-driven narratives conveyed by stylized artwork and dialogue in comic book panels.

MetroViz: Visual Analysis of Public Transportation Data

1 code implementation18 Jul 2015 Fan Du, Joshua Brulé, Peter Enns, Varun Manjunatha, Yoav Segev

Understanding the quality and usage of public transportation resources is important for schedule optimization and resource allocation.

Human-Computer Interaction

SHOE: Supervised Hashing with Output Embeddings

no code implementations30 Jan 2015 Sravanthi Bondugula, Varun Manjunatha, Larry S. Davis, David Doermann

We present a supervised binary encoding scheme for image retrieval that learns projections by taking into account similarity between classes obtained from output embeddings.

Attribute Image Retrieval +2

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