22 citations · 42 across the 14 of their papers we have counts for
16 papers
MINDS: A Cross-cultural Dialogue Corpus for Social Norm Classification and Adherence Detection
Pritish Sahu, Anirudh Som, Dimitra Vergyri +1
Social norms are implicit, culturally grounded expectations that guide interpersonal communication. Unlike factual commonsense, norm reasoning is subjective, context-dependent, and…
SayCoNav: Utilizing Large Language Models for Adaptive Collaboration in Decentralized Multi-Robot Navigation
Abhinav Rajvanshi, Pritish Sahu, Tixiao Shan +2
Adaptive collaboration is critical to a team of autonomous robots to perform complicated navigation tasks in large-scale unknown environments. An effective collaboration strategy s…
GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEs
Kalliopi Basioti, Pritish Sahu, Qingze Tony Liu +3
Raven's Progressive Matrices (RPMs) is an established benchmark to examine the ability to perform high-level abstract visual reasoning (AVR). Despite the current success of algorit…
Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verification
Pritish Sahu, Karan Sikka, Ajay Divakaran
Large Visual Language Models (LVLMs) struggle with hallucinations in visual instruction following task(s), limiting their trustworthiness and real-world applicability. We propose P…
Unpacking Large Language Models with Conceptual Consistency
Pritish Sahu, Michael Cogswell, Yunye Gong +1
If a Large Language Model (LLM) answers "yes" to the question "Are mountains tall?" then does it know what a mountain is? Can you rely on it responding correctly or incorrectly to…
SAViR-T: Spatially Attentive Visual Reasoning with Transformers
Pritish Sahu, Kalliopi Basioti, Vladimir Pavlovic
We present a novel computational model, "SAViR-T", for the family of visual reasoning problems embodied in the Raven's Progressive Matrices (RPM). Our model considers explicit spat…
Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmark
Pritish Sahu, Karan Sikka, Ajay Divakaran
We focus on Multimodal Machine Reading Comprehension (M3C) where a model is expected to answer questions based on given passage (or context), and the context and the questions can…
DAReN: A Collaborative Approach Towards Reasoning And Disentangling
Pritish Sahu, Kalliopi Basioti, Vladimir Pavlovic
Computational learning approaches to solving visual reasoning tests, such as Raven's Progressive Matrices (RPM), critically depend on the ability to identify the visual concepts us…
Comprehension Based Question Answering using Bloom's Taxonomy
Pritish Sahu, Michael Cogswell, Sara Rutherford-Quach +1
Current pre-trained language models have lots of knowledge, but a more limited ability to use that knowledge. Bloom's Taxonomy helps educators teach children how to use knowledge b…
Towards Solving Multimodal Comprehension
Pritish Sahu, Karan Sikka, Ajay Divakaran
This paper targets the problem of procedural multimodal machine comprehension (M3C). This task requires an AI to comprehend given steps of multimodal instructions and then answer q…
Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings
Karan Sikka, Jihua Huang, Andrew Silberfarb +6
We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs. We propose Common-Sense based Neuro-Symbolic Loss (CSNL) that formulates prior knowledge as nov…
Task-Discriminative Domain Alignment for Unsupervised Domain Adaptation
Behnam Gholami, Pritish Sahu, Minyoung Kim +1
Domain Adaptation (DA), the process of effectively adapting task models learned on one domain, the source, to other related but distinct domains, the targets, with no or minimal re…
Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement
Minyoung Kim, Yuting Wang, Pritish Sahu +1
We propose a family of novel hierarchical Bayesian deep auto-encoder models capable of identifying disentangled factors of variability in data. While many recent attempts at factor…
Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approach
Minyoung Kim, Pritish Sahu, Behnam Gholami +1
In unsupervised domain adaptation, it is widely known that the target domain error can be provably reduced by having a shared input representation that makes the source and target…
Relevance Factor VAE: Learning and Identifying Disentangled Factors
Minyoung Kim, Yuting Wang, Pritish Sahu +1
We propose a novel VAE-based deep auto-encoder model that can learn disentangled latent representations in a fully unsupervised manner, endowed with the ability to identify all mea…
Unsupervised Multi-Target Domain Adaptation: An Information Theoretic Approach
Behnam Gholami, Pritish Sahu, Ognjen Rudovic +2
Unsupervised domain adaptation (uDA) models focus on pairwise adaptation settings where there is a single, labeled, source and a single target domain. However, in many real-world s…