Publications

In this work, we propose Drectional Grdient Projection (DiGraP), a novel layer-wise trainable method that incorporates directional information from gradients to improve OOD robustness.

In this work, we introduce a training-free framework to enhance the capability of Diffusion Models to generate visual text.

We present HyWay, short for “Hybrid Hallway”, to enable mingling and informal interactions among physical and virtual users, in casual spaces and settings, such as office water cooler areas, conference hallways, trade show floors, and more.

Using egocentric video and head motion data from 67 order picking tasks (244 picks;149 orders), we learn visual models of the 10 objects picked to fulfill the orders.

In this work, we introduce Learning to Discern (L2D), an offline imitation learning framework for learning from demonstrations with diverse quality and style.

Active Learning is a very common yet powerful framework for iteratively and adaptively sampling subsets of the unlabeled sets with a human in the loop with the goal of achieving labeling efficiency. Most real world datasets have imbalance either in classes and slices, and correspondingly, parts of the dataset are rare. As a result, there has been a lot of work in designing active learning approaches for mining these rare data instances. Most approaches assume access to a seed set of instances which contain these rare data instances. However, in the event of more extreme rareness, it is reasonable to assume that these rare data instances (either classes or slices) may not even be present in the seed labeled set, and a critical need for the active learning paradigm is to efficiently discover these rare data instances. In this work, we provide an active data discovery framework which can mine unknown data slices and classes efficiently using the submodular conditional gain and submodular conditional mutual information functions. We provide a general algorithmic framework which works in a number of scenarios including image classification and object detection and works with both rare classes and rare slices present in the unlabeled set. We show significant accuracy and labeling efficiency gains with our approach compared to existing state-of-the-art active learning approaches for actively discovering these rare classes and slices.

Code-switching in linguistically diverse, low resource languages is often semantically complex and lacks sophisticated methodologies that can be applied to real-world data for precisely detecting hate speech. In an attempt to bridge this gap, we introduce a three-tier pipeline that employs profanity modeling, deep graph embeddings, and author profiling to retrieve instances of hate speech in Hindi-English code-switched language (Hinglish) on social media platforms like Twitter. Through extensive comparison against several baselines on two real-world datasets, we demonstrate how targeted hate embeddings combined with social network-based features outperform state of the art, both quantitatively and qualitatively. Additionally, we present an expert-in-the-loop algorithm for bias elimination in the proposed model pipeline and study the prevalence and performance impact of the debiasing. Finally, we discuss the computational, practical, ethical, and reproducibility aspects of the deployment of our pipeline across the Web.

Temporal psycholinguistics can play a crucial role in studying expressions of suicidal intent on social media. Current methods are limited in their approach in leveraging contextual psychological cues from online user communities. This work embarks in a novel direction to explore historical activities of users and homophily networks formed between Twitter users for extracting suicidality trends. Empirical evidence proves the advantages of incorporating historical user profiling and temporal graph convolutional modeling for automated detection of suicidal connotations on Twitter.

In this work we propose a two-tier pipeline that leverages Discourse Marker based oversampling and fine-grained suggestion mining techniques to retrieve suggestions from online forums.