98 citations · 111 across the 13 of their papers we have counts for
13 papers
REALTALK: A 21-Day Real-World Dataset for Long-Term Conversation
Dong-Ho Lee, Adyasha Maharana, Jay Pujara +2
Long-term, open-domain dialogue capabilities are essential for chatbots aiming to recall past interactions and demonstrate emotional intelligence (EI). Yet, most existing research…
Adapt-: Scalable Continual Multimodal Instruction Tuning via Dynamic Data Selection
Adyasha Maharana, Jaehong Yoon, Tianlong Chen +1
Visual instruction datasets from various distributors are released at different times and often contain a significant number of semantically redundant text-image pairs, depending o…
Evaluating Very Long-Term Conversational Memory of LLM Agents
Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov +3
Existing works on long-term open-domain dialogues focus on evaluating model responses within contexts spanning no more than five chat sessions. Despite advancements in long-context…
Debiasing Multimodal Models via Causal Information Minimization
Vaidehi Patil, Adyasha Maharana, Mohit Bansal
Most existing debiasing methods for multimodal models, including causal intervention and inference methods, utilize approximate heuristics to represent the biases, such as shallow…
D2 Pruning: Message Passing for Balancing Diversity and Difficulty in Data Pruning
Adyasha Maharana, Prateek Yadav, Mohit Bansal
Analytical theories suggest that higher-quality data can lead to lower test errors in models trained on a fixed data budget. Moreover, a model can be trained on a lower compute bud…
Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models
Adyasha Maharana, Amita Kamath, Christopher Clark +2
As general purpose vision models get increasingly effective at a wide set of tasks, it is imperative that they be consistent across the tasks they support. Inconsistent AI models a…
StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation
Adyasha Maharana, Darryl Hannan, Mohit Bansal
Recent advances in text-to-image synthesis have led to large pretrained transformers with excellent capabilities to generate visualizations from a given text. However, these models…
Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization
Adyasha Maharana, Mohit Bansal
While much research has been done in text-to-image synthesis, little work has been done to explore the usage of linguistic structure of the input text. Such information is even mor…
Improving Generation and Evaluation of Visual Stories via Semantic Consistency
Adyasha Maharana, Darryl Hannan, Mohit Bansal
Story visualization is an under-explored task that falls at the intersection of many important research directions in both computer vision and natural language processing. In this…
Use of Technology and Innovations in the COVID-19 Pandemic Response in Africa
Adyasha Maharana, Morine Amutorine, Moinina David Sengeh +1
The use of technology has been ubiquitous in efforts to combat the ongoing public health crisis due to emergence and spread of the SARS-CoV-2 virus. African countries have made tre…
Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension
Adyasha Maharana, Mohit Bansal
Reading comprehension models often overfit to nuances of training datasets and fail at adversarial evaluation. Training with adversarially augmented dataset improves robustness aga…
Using Deep Learning to Examine the Association between the Built Environment and Neighborhood Adult Obesity Prevalence
Adyasha Maharana, Elaine O. Nsoesie
More than one-third of the adult population in the United States is obese. Obesity has been linked to factors such as, genetics, diet, physical activity and the environment. Howeve…
Using Deep Learning and Satellite Imagery to Quantify the Impact of the Built Environment on Neighborhood Crime Rates
Adyasha Maharana, Quynh C. Nguyen, Elaine O. Nsoesie
The built environment has been postulated to have an impact on neighborhood crime rates, however, measures of the built environment can be subjective and differ across studies lead…