no code implementations • 20 Nov 2024 • Gaurav Verma, Rachneet Kaur, Nishan Srishankar, Zhen Zeng, Tucker Balch, Manuela Veloso
Our experiments on two popular benchmarks -- Mind2Web & VisualWebArena -- show that using in-context demonstrations (for proprietary models) or meta-adaptation demonstrations (for meta-learned open-weights models) boosts task success rate by 3. 36% to 7. 21% over non-adapted state-of-the-art models, corresponding to a relative increase of 21. 03% to 65. 75%.
no code implementations • 3 Nov 2024 • Sejoon Oh, Yiqiao Jin, Megha Sharma, Donghyun Kim, Eric Ma, Gaurav Verma, Srijan Kumar
Multimodal large language models (MLLMs) have revolutionized vision-language understanding but remain vulnerable to multimodal jailbreak attacks, where adversarial inputs are meticulously crafted to elicit harmful or inappropriate responses.
1 code implementation • 24 Oct 2024 • Mohit Chandra, Siddharth Sriraman, Gaurav Verma, Harneet Singh Khanuja, Jose Suarez Campayo, Zihang Li, Michael L. Birnbaum, Munmun De Choudhury
Adverse Drug Reactions (ADRs) from psychiatric medications are the leading cause of hospitalizations among mental health patients.
1 code implementation • 1 Aug 2024 • Sejoon Oh, Gaurav Verma, Srijan Kumar
Text-aware recommender systems incorporate rich textual features, such as titles and descriptions, to generate item recommendations for users.
no code implementations • 21 Jul 2024 • Gaurav Verma, Rynaa Grover, Jiawei Zhou, Binny Mathew, Jordan Kraemer, Munmun De Choudhury, Srijan Kumar
In contrast to prior work that has demonstrated the effectiveness of such classifiers in detecting hateful speech ($F_1 = 0. 89$), our work shows that accurate and reliable detection of violence-provoking speech is a challenging task ($F_1 = 0. 69$).
1 code implementation • 28 Jun 2024 • Michael Canesche, Gaurav Verma, Fernando Magno Quintao Pereira
By applying this approach to the first 300 kernels that Ansor generates, we usually obtain better kernels in less time than if we let Ansor analyze 10, 000 kernels.
1 code implementation • 26 Feb 2024 • Gaurav Verma, MinJe Choi, Kartik Sharma, Jamelle Watson-Daniels, Sejoon Oh, Srijan Kumar
It is desirable to understand the roles of these two modules in modeling domain-specific visual attributes to inform the design of future models and streamline the interpretability efforts on the current models.
1 code implementation • 21 Feb 2024 • Yiqiao Jin, MinJe Choi, Gaurav Verma, Jindong Wang, Srijan Kumar
Social media platforms are hubs for multimodal information exchange, encompassing text, images, and videos, making it challenging for machines to comprehend the information or emotions associated with interactions in online spaces.
1 code implementation • 19 Oct 2023 • Yiqiao Jin, Mohit Chandra, Gaurav Verma, Yibo Hu, Munmun De Choudhury, Srijan Kumar
Our findings underscore the pressing need to bolster the cross-lingual capacities of these models, and to provide an equitable information ecosystem accessible to all.
1 code implementation • 19 Jun 2023 • Shivaen Ramshetty, Gaurav Verma, Srijan Kumar
The robustness of multimodal deep learning models to realistic changes in the input text is critical for their applicability to important tasks such as text-to-image retrieval and cross-modal entailment.
1 code implementation • 19 Jun 2023 • Venkata Prabhakara Sarath Nookala, Gaurav Verma, Subhabrata Mukherjee, Srijan Kumar
Our results on six GLUE tasks indicate that compared to fully fine-tuned models, vanilla FSL methods lead to a notable relative drop in task performance (i. e., are less robust) in the face of adversarial perturbations.
no code implementations • 17 May 2023 • Sergio Pelaez, Gaurav Verma, Barbara Ribeiro, Philip Shapira
We discuss the implications of our approach for conducting large-scale text analyses with complex and abstract concepts and suggest that, with careful framework design and interactive human oversight, generative language models can offer significant advantages in quality and in reduced time and costs for producing labels and rationales.
no code implementations • 11 May 2023 • Gaurav Verma, Ryan A. Rossi, Christopher Tensmeyer, Jiuxiang Gu, Ani Nenkova
Visual text evokes an image in a person's mind, while non-visual text fails to do so.
1 code implementation • 11 Apr 2023 • Gaurav Verma, Siddhisanket Raskar, Zhen Xie, Abid M Malik, Murali Emani, Barbara Chapman
Tuning tensor program generation involves searching for various possible program transformation combinations for a given program on target hardware to optimize the tensor program execution.
no code implementations • 4 Nov 2022 • Gaurav Verma, Vishwa Vinay, Ryan A. Rossi, Srijan Kumar
Our work aims to highlight and encourage further research on the robustness of deep multimodal models to realistic variations, especially in human-facing societal applications.
1 code implementation • 19 May 2022 • Gaurav Verma, Rohit Mujumdar, Zijie J. Wang, Munmun De Choudhury, Srijan Kumar
Advances in Natural Language Processing (NLP) have revolutionized the way researchers and practitioners address crucial societal problems.
no code implementations • 19 May 2022 • Yunhao Yuan, Gaurav Verma, Barbara Keller, Talayeh Aledavood
We find that anger words are strongly associated with minority stress during the COVID-19 pandemic.
1 code implementation • 10 Feb 2022 • Manoj Niverthi, Gaurav Verma, Srijan Kumar
We find that evasion child accounts demonstrate similarities with respect to their banned parent accounts on several behavioral axes - from similarity in usernames and edited pages to similarity in content added to the platform and its psycholinguistic attributes.
no code implementations • 13 Sep 2021 • Kshitij Gulati, Gaurav Verma, Mukesh Mohania, Ashish Kundu
The proposed work's novel contributions, including the incorporation of occasion context, region-wise makeup recommendation, real-time makeup previews and continuous makeup feedback, set our system apart from the current work in makeup recommendation.
no code implementations • EACL 2021 • Hrituraj Singh, Gaurav Verma, Aparna Garimella, Balaji Vasan Srinivasan
In this paper, we propose a Director-Generator framework to rewrite content in the target author's style, specifically focusing on certain target attributes.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Hrituraj Singh, Gaurav Verma, Balaji Vasan Srinivasan
While recent advances in language modeling have resulted in powerful generation models, their generation style remains implicitly dependent on the training data and can not emulate a specific target style.
no code implementations • EMNLP (WNUT) 2020 • Abhilasha Sancheti, Kushal Chawla, Gaurav Verma
We describe our system for WNUT-2020 shared task on the identification of informative COVID-19 English tweets.
no code implementations • 5 Jun 2020 • Gaurav Verma, Niyati Chhaya, Vishwa Vinay
With rising concern around abusive and hateful behavior on social media platforms, we present an ensemble learning method to identify and analyze the linguistic properties of such content.
no code implementations • 2 Mar 2020 • Gaurav Verma, Vishwa Vinay, Sahil Bansal, Shashank Oberoi, Makkunda Sharma, Prakhar Gupta
Interactive search sessions often contain multiple queries, where the user submits a reformulated version of the previous query in response to the original results.
no code implementations • 22 Sep 2019 • Bakhtiyar Syed, Gaurav Verma, Balaji Vasan Srinivasan, Anandhavelu Natarajan, Vasudeva Varma
Given the recent progress in language modeling using Transformer-based neural models and an active interest in generating stylized text, we present an approach to leverage the generalization capabilities of a language model to rewrite an input text in a target author's style.
no code implementations • 18 Sep 2019 • Gaurav Verma, Balaji Vasan Srinivasan
With a growing interest in modeling inherent subjectivity in natural language, we present a linguistically-motivated process to understand and analyze the writing style of individuals from three perspectives: lexical, syntactic, and semantic.
no code implementations • 21 Jun 2019 • Aadhavan M. Nambhi, Bhanu Prakash Reddy, Aarsh Prakash Agarwal, Gaurav Verma, Harvineet Singh, Iftikhar Ahamath Burhanuddin
Data analytics software applications have become an integral part of the decision-making process of analysts.
no code implementations • 30 Mar 2019 • Gaurav Verma, Eeshan Gunesh Dhekane, Tanaya Guha
We introduce the problem of learning affective correspondence between audio (music) and visual data (images).