no code implementations • 21 Apr 2024 • Charith Chandra Sai Balne, Sreyoshi Bhaduri, Tamoghna Roy, Vinija Jain, Aman Chadha
The rise of deep learning has marked significant progress in fields such as computer vision, natural language processing, and medical imaging, primarily through the adaptation of pre-trained models for specific tasks.
no code implementations • 17 Apr 2024 • Paras Sheth, Tharindu Kumarage, Raha Moraffah, Aman Chadha, Huan Liu
Content moderation faces a challenging task as social media's ability to spread hate speech contrasts with its role in promoting global connectivity.
no code implementations • 28 Mar 2024 • Vipula Rawte, S. M Towhidul Islam Tonmoy, Krishnav Rajbangshi, Shravani Nag, Aman Chadha, Amit P. Sheth, Amitava Das
We present FACTOID (FACTual enTAILment for hallucInation Detection), a benchmark dataset for FE.
no code implementations • 27 Mar 2024 • Vipula Rawte, S. M Towhidul Islam Tonmoy, S M Mehedi Zaman, Prachi Priya, Aman Chadha, Amit P. Sheth, Amitava Das
We have fine-tuned an LLM with injected [PAUSE] tokens, allowing the LLM to pause while reading lengthier prompts.
no code implementations • 25 Mar 2024 • Sanyam Lakhanpal, Shivang Chopra, Vinija Jain, Aman Chadha, Man Luo
We introduce a benchmark, LenCom-Eval, specifically designed for testing models' capability in generating images with Lengthy and Complex visual text.
Optical Character Recognition (OCR) Text-to-Image Generation
no code implementations • 12 Mar 2024 • Preetam Prabhu Srikar Dammu, Himanshu Naidu, Mouly Dewan, Youngmin Kim, Tanya Roosta, Aman Chadha, Chirag Shah
In the midst of widespread misinformation and disinformation through social media and the proliferation of AI-generated texts, it has become increasingly difficult for people to validate and trust information they encounter.
no code implementations • 4 Mar 2024 • Fiona Anting Tan, Gerard Christopher Yeo, Fanyou Wu, Weijie Xu, Vinija Jain, Aman Chadha, Kokil Jaidka, Yang Liu, See-Kiong Ng
Drawing inspiration from psychological research on the links between certain personality traits and Theory-of-Mind (ToM) reasoning, and from prompt engineering research on the hyper-sensitivity of prompts in affecting LLMs capabilities, this study investigates how inducing personalities in LLMs using prompts affects their ToM reasoning capabilities.
no code implementations • 3 Mar 2024 • Arijit Ghosh Chowdhury, Md Mofijul Islam, Faysal Hossain Shezan, Vaibhav Kumar, Vinija Jain, Aman Chadha
Large Language Models (LLMs) have become a cornerstone in the field of Natural Language Processing (NLP), offering transformative capabilities in understanding and generating human-like text.
no code implementations • 2 Mar 2024 • Tharindu Kumarage, Garima Agrawal, Paras Sheth, Raha Moraffah, Aman Chadha, Joshua Garland, Huan Liu
We have witnessed lately a rapid proliferation of advanced Large Language Models (LLMs) capable of generating high-quality text.
no code implementations • 28 Feb 2024 • Swagata Ashwani, Kshiteesh Hegde, Nishith Reddy Mannuru, Mayank Jindal, Dushyant Singh Sengar, Krishna Chaitanya Rao Kathala, Dishant Banga, Vinija Jain, Aman Chadha
The knowledge from ConceptNet enhances the performance of multiple causal reasoning tasks such as causal discovery, causal identification and counterfactual reasoning.
no code implementations • 20 Feb 2024 • Akash Ghosh, Arkadeep Acharya, Sriparna Saha, Vinija Jain, Aman Chadha
The advent of Large Language Models (LLMs) has significantly reshaped the trajectory of the AI revolution.
no code implementations • 18 Feb 2024 • Aishik Rakshit, Smriti Singh, Shuvam Keshari, Arijit Ghosh Chowdhury, Vinija Jain, Aman Chadha
Embeddings play a pivotal role in the efficacy of Large Language Models.
no code implementations • 16 Feb 2024 • Smriti Singh, Shuvam Keshari, Vinija Jain, Aman Chadha
Socioeconomic bias in society exacerbates disparities, influencing access to opportunities and resources based on individuals' economic and social backgrounds.
no code implementations • 14 Feb 2024 • Maryam Amirizaniani, Jihan Yao, Adrian Lavergne, Elizabeth Snell Okada, Aman Chadha, Tanya Roosta, Chirag Shah
An effective method is to probe the LLM using different versions of the same question.
no code implementations • 14 Feb 2024 • Maryam Amirizaniani, Tanya Roosta, Aman Chadha, Chirag Shah
Probing LLMs with varied iterations of a single question could reveal potential inconsistencies in their knowledge or functionality.
no code implementations • 11 Feb 2024 • Arpita Vats, Vinija Jain, Rahul Raja, Aman Chadha
The paper underscores the significance of Large Language Models (LLMs) in reshaping recommender systems, attributing their value to unique reasoning abilities absent in traditional recommenders.
no code implementations • 7 Feb 2024 • Shivang Chopra, Suraj Kothawade, Houda Aynaou, Aman Chadha
Our proposed DM-SFDA method involves fine-tuning a pre-trained text-to-image diffusion model to generate source domain images using features from the target images to guide the diffusion process.
Source-Free Domain Adaptation Unsupervised Domain Adaptation
no code implementations • 5 Feb 2024 • Pranab Sahoo, Ayush Kumar Singh, Sriparna Saha, Vinija Jain, Samrat Mondal, Aman Chadha
This approach leverages task-specific instructions, known as prompts, to enhance model efficacy without modifying the core model parameters.
no code implementations • 23 Jan 2024 • Chenyang Gao, Brecht Desplanques, Chelsea J. -T. Ju, Aman Chadha, Andreas Stolcke
Automated speaker identification (SID) is a crucial step for the personalization of a wide range of speech-enabled services.
1 code implementation • 20 Jan 2024 • Georgios Ioannides, Aman Chadha, Aaron Elkins
We propose the Multi-Head Gaussian Adaptive Attention Mechanism (GAAM), a novel probabilistic attention framework, and the Gaussian Adaptive Transformer (GAT), designed to enhance information aggregation across multiple modalities, including Speech, Text and Vision.
no code implementations • 15 Jan 2024 • Saurav Pawar, S. M Towhidul Islam Tonmoy, S M Mehedi Zaman, Vinija Jain, Aman Chadha, Amitava Das
The advent of Large Language Models (LLMs) represents a notable breakthrough in Natural Language Processing (NLP), contributing to substantial progress in both text comprehension and generation.
1 code implementation • 3 Jan 2024 • Akash Ghosh, Arkadeep Acharya, Prince Jha, Aniket Gaudgaul, Rajdeep Majumdar, Sriparna Saha, Aman Chadha, Raghav Jain, Setu Sinha, Shivani Agarwal
This work introduces the task of multimodal medical question summarization for codemixed input in a low-resource setting.
1 code implementation • 2 Jan 2024 • S. M Towhidul Islam Tonmoy, S M Mehedi Zaman, Vinija Jain, Anku Rani, Vipula Rawte, Aman Chadha, Amitava Das
As Large Language Models (LLMs) continue to advance in their ability to write human-like text, a key challenge remains around their tendency to hallucinate generating content that appears factual but is ungrounded.
no code implementations • 16 Dec 2023 • Akash Ghosh, Arkadeep Acharya, Raghav Jain, Sriparna Saha, Aman Chadha, Setu Sinha
This multimodal approach not only enhances the decision-making process in healthcare but also fosters a more nuanced understanding of patient queries, laying the groundwork for future research in personalized and responsive medical care
no code implementations • 12 Dec 2023 • Ibtihel Amara, Vinija Jain, Aman Chadha
We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data.
no code implementations • 1 Dec 2023 • Anku Rani, Dwip Dalal, Shreya Gautam, Pankaj Gupta, Vinija Jain, Aman Chadha, Amit Sheth, Amitava Das
This research explores the problem of deception through the lens of psychology, employing a framework that categorizes deception into three forms: lies of omission, lies of commission, and lies of influence.
no code implementations • 14 Oct 2023 • Ankitha Sudarshan, Vinay Samuel, Parth Patwa, Ibtihel Amara, Aman Chadha
Automatic Speech Recognition (ASR) has witnessed a profound research interest.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 11 Oct 2023 • Thilini Wijesiriwardene, Ruwan Wickramarachchi, Aishwarya Naresh Reganti, Vinija Jain, Aman Chadha, Amit Sheth, Amitava Das
Through our analysis, we find that LLMs' ability to identify sentence analogies is positively correlated with their ability to encode syntactic and semantic structures of sentences.
no code implementations • 8 Oct 2023 • Megha Chakraborty, S. M Towhidul Islam Tonmoy, S M Mehedi Zaman, Krish Sharma, Niyar R Barman, Chandan Gupta, Shreya Gautam, Tanay Kumar, Vinija Jain, Aman Chadha, Amit P. Sheth, Amitava Das
Given this cynosural spotlight on generative AI, AI-generated text detection (AGTD) has emerged as a topic that has already received immediate attention in research, with some initial methods having been proposed, soon followed by emergence of techniques to bypass detection.
1 code implementation • 8 Oct 2023 • Yixin Wan, Jieyu Zhao, Aman Chadha, Nanyun Peng, Kai-Wei Chang
Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations.
no code implementations • 8 Oct 2023 • Vipula Rawte, Swagata Chakraborty, Agnibh Pathak, Anubhav Sarkar, S. M Towhidul Islam Tonmoy, Aman Chadha, Amit P. Sheth, Amitava Das
Finally, to establish a method for quantifying and to offer a comparative spectrum that allows us to evaluate and rank LLMs based on their vulnerability to producing hallucinations, we propose Hallucination Vulnerability Index (HVI).
no code implementations • 2 Oct 2023 • Shivang Chopra, Suraj Kothawade, Houda Aynaou, Aman Chadha
Domain Adaptation (DA) is a method for enhancing a model's performance on a target domain with inadequate annotated data by applying the information the model has acquired from a related source domain with sufficient labeled data.
no code implementations • 21 Sep 2023 • Vinay Samuel, Houda Aynaou, Arijit Ghosh Chowdhury, Karthik Venkat Ramanan, Aman Chadha
Large Language Models (LLMs) have demonstrated impressive zero shot performance on a wide range of NLP tasks, demonstrating the ability to reason and apply commonsense.
no code implementations • 12 Sep 2023 • Shreyash Mishra, S Suryavardan, Megha Chakraborty, Parth Patwa, Anku Rani, Aman Chadha, Aishwarya Reganti, Amitava Das, Amit Sheth, Manoj Chinnakotla, Asif Ekbal, Srijan Kumar
In this paper, we present the overview of the Memotion 3 shared task, as part of the DeFactify 2 workshop at AAAI-23.
no code implementations • 11 Sep 2023 • Mohsin Ali, Kandukuri Sai Teja, Neeharika Gupta, Parth Patwa, Anubhab Chatterjee, Vinija Jain, Aman Chadha, Amitava Das
Therefore, to enrich word information and incorporate positional information, positional encoding is defined.
1 code implementation • 3 Sep 2023 • Arijit Ghosh Chowdhury, Aman Chadha
Robustness in Natural Language Processing continues to be a pertinent issue, where state of the art models under-perform under naturally shifted distributions.
no code implementations • 28 Aug 2023 • Hong Yung Yip, Chidaksh Ravuru, Neelabha Banerjee, Shashwat Jha, Amit Sheth, Aman Chadha, Amitava Das
We analyze their effectiveness in preserving the (a) topological structure of node-level graph reconstruction with an increasing number of hops and (b) semantic information on various word semantic and analogy tests.
no code implementations • 28 Aug 2023 • Muhammad Rahman, Sachi Figliolini, Joyce Kim, Eivy Cedeno, Charles Kleier, Chirag Shah, Aman Chadha
It is difficult to find good resources or schedule an appointment with a career counselor to help with editing a resume for a specific role.
no code implementations • 19 Aug 2023 • Maithili Sabane, Onkar Litake, Aman Chadha
The recent advances in deep-learning have led to the development of highly sophisticated systems with an unquenchable appetite for data.
1 code implementation • 3 Aug 2023 • Paras Sheth, Tharindu Kumarage, Raha Moraffah, Aman Chadha, Huan Liu
By disentangling input into platform-dependent features (useful for predicting hate targets) and platform-independent features (used to predict the presence of hate), we learn invariant representations resistant to distribution shifts.
no code implementations • 19 Jul 2023 • S Suryavardan, Shreyash Mishra, Megha Chakraborty, Parth Patwa, Anku Rani, Aman Chadha, Aishwarya Reganti, Amitava Das, Amit Sheth, Manoj Chinnakotla, Asif Ekbal, Srijan Kumar
With social media usage growing exponentially in the past few years, fake news has also become extremely prevalent.
1 code implementation • 15 Jun 2023 • Dominick Reilly, Aman Chadha, Srijan Das
Both PAAT and PAAB surpass their respective backbone Transformers by up to 9. 8% in real-world action recognition and 21. 8% in multi-view robotic video alignment.
1 code implementation • 15 Jun 2023 • Paras Sheth, Tharindu Kumarage, Raha Moraffah, Aman Chadha, Huan Liu
Hate speech detection refers to the task of detecting hateful content that aims at denigrating an individual or a group based on their religion, gender, sexual orientation, or other characteristics.
no code implementations • 22 May 2023 • Megha Chakraborty, Khushbu Pahwa, Anku Rani, Shreyas Chatterjee, Dwip Dalal, Harshit Dave, Ritvik G, Preethi Gurumurthy, Adarsh Mahor, Samahriti Mukherjee, Aditya Pakala, Ishan Paul, Janvita Reddy, Arghya Sarkar, Kinjal Sensharma, Aman Chadha, Amit P. Sheth, Amitava Das
To address this gap, we introduce FACTIFY 3M, a dataset of 3 million samples that pushes the boundaries of the domain of fact verification via a multimodal fake news dataset, in addition to offering explainability through the concept of 5W question-answering.
no code implementations • 12 May 2023 • Varuna Krishna, S Suryavardan, Shreyash Mishra, Sathyanarayanan Ramamoorthy, Parth Patwa, Megha Chakraborty, Aman Chadha, Amitava Das, Amit Sheth
We also evaluate pre-trained IMAGINATOR JEs on three downstream tasks: (i) image captioning, (ii) Image2Tweet, and (iii) text-based image retrieval.
no code implementations • 8 May 2023 • Thilini Wijesiriwardene, Ruwan Wickramarachchi, Bimal G. Gajera, Shreeyash Mukul Gowaikar, Chandan Gupta, Aman Chadha, Aishwarya Naresh Reganti, Amit Sheth, Amitava Das
Over the past decade, analogies, in the form of word-level analogies, have played a significant role as an intrinsic measure of evaluating the quality of word embedding methods such as word2vec.
no code implementations • 7 May 2023 • Anku Rani, S. M Towhidul Islam Tonmoy, Dwip Dalal, Shreya Gautam, Megha Chakraborty, Aman Chadha, Amit Sheth, Amitava Das
Finally, we report a baseline QA system to automatically locate those answers from evidence documents, which can serve as a baseline for future research in the field.
1 code implementation • 8 Apr 2023 • S Suryavardan, Shreyash Mishra, Parth Patwa, Megha Chakraborty, Anku Rani, Aishwarya Reganti, Aman Chadha, Amitava Das, Amit Sheth, Manoj Chinnakotla, Asif Ekbal, Srijan Kumar
In this paper, we provide a multi-modal fact-checking dataset called FACTIFY 2, improving Factify 1 by using new data sources and adding satire articles.
1 code implementation • 17 Mar 2023 • Shreyash Mishra, S Suryavardan, Parth Patwa, Megha Chakraborty, Anku Rani, Aishwarya Reganti, Aman Chadha, Amitava Das, Amit Sheth, Manoj Chinnakotla, Asif Ekbal, Srijan Kumar
Memes are the new-age conveyance mechanism for humor on social media sites.
no code implementations • 19 Feb 2023 • Aman Chadha, Vinija Jain
While few-shot learning as a transfer learning paradigm has gained significant traction for scenarios with limited data, it has primarily been explored in the context of building unimodal and unilingual models.
no code implementations • 26 Jan 2023 • Arpita Vats, Aman Chadha
The ability to recognize and interpret facial emotions is a critical component of human communication, as it allows individuals to understand and respond to emotions conveyed through facial expressions and vocal tones.
no code implementations • 24 Oct 2022 • Mohammad Samragh, Arnav Kundu, Ting-yao Hu, Minsik Cho, Aman Chadha, Ashish Shrivastava, Oncel Tuzel, Devang Naik
This paper explores the possibility of using visual object detection techniques for word localization in speech data.
no code implementations • 25 Jun 2021 • Aman Chadha, Vinija Jain
We demonstrate the effectiveness of iReason using a two-pronged comparative analysis with language representation learning models (BERT, GPT-2) as well as current state-of-the-art multimodal causality models.
no code implementations • 16 Nov 2020 • Aman Chadha, Gurneet Arora, Navpreet Kaloty
Most prior art in visual understanding relies solely on analyzing the "what" (e. g., event recognition) and "where" (e. g., event localization), which in some cases, fails to describe correct contextual relationships between events or leads to incorrect underlying visual attention.
Ranked #4 on Video Question Answering on TVQA
1 code implementation • Springer Journal of Computational Visual Media (CVM), Tsinghua University Press 2020 • Aman Chadha, John Britto, M. Mani Roja
However, generative adversarial networks (GANs) offer a competitive advantage by being able to mitigate the issue of a lack of finer texture details, usually seen with CNNs when super-resolving at large upscaling factors.
Ranked #1 on Video Super-Resolution on Vimeo90K
1 code implementation • 13 Jun 2020 • Aman Chadha, John Britto, M. Mani Roja
However, generative adversarial networks (GANs) offer a competitive advantage by being able to mitigate the issue of a lack of finer texture details, usually seen with CNNs when super-resolving at large upscaling factors.
no code implementations • 30 Aug 2012 • Aman Chadha, Sushmit Mallik, Ravdeep Johar
The aim of a Content-Based Image Retrieval (CBIR) system, also known as Query by Image Content (QBIC), is to help users to retrieve relevant images based on their contents.
no code implementations • 4 Nov 2011 • Divya Jyoti, Aman Chadha, Pallavi Vaidya, M. Mani Roja
The proposed Face Detection and Recognition system using Discrete Wavelet Transform (DWT) accepts face frames as input from a database containing images from low cost devices such as VGA cameras, webcams or even CCTV's, where image quality is inferior.