no code implementations • 2 May 2024 • Somesh Singh, Harini S I, Yaman K Singla, Veeky Baths, Rajiv Ratn Shah, Changyou Chen, Balaji Krishnamurthy
Specifically, we show that training LLMs to predict the receiver behavior of likes and comments improves the LLM's performance on a wide variety of downstream content understanding tasks.
1 code implementation • 2 Feb 2024 • Sohan Patnaik, Heril Changwal, Milan Aggarwal, Sumit Bhatia, Yaman Kumar, Balaji Krishnamurthy
Typically, only a small part of the whole table is relevant to derive the answer for a given question.
Ranked #1 on Semantic Parsing on WikiSQL (Denotation accuracy (test) metric)
no code implementations • 18 Nov 2023 • Varun Khurana, Yaman K Singla, Jayakumar Subramanian, Rajiv Ratn Shah, Changyou Chen, Zhiqiang Xu, Balaji Krishnamurthy
We show that BoigLLM outperforms 13x larger models such as GPT-3. 5 and GPT-4 in this task, demonstrating that while these state-of-the-art models can understand images, they lack information on how these images perform in the real world.
no code implementations • 9 Nov 2023 • Pragyan Banerjee, Abhinav Java, Surgan Jandial, Simra Shahid, Shaz Furniturewala, Balaji Krishnamurthy, Sumit Bhatia
Fairness in Language Models (LMs) remains a longstanding challenge, given the inherent biases in training data that can be perpetuated by models and affect the downstream tasks.
no code implementations • 1 Sep 2023 • Ashmit Khandelwal, Aditya Agrawal, Aanisha Bhattacharyya, Yaman K Singla, Somesh Singh, Uttaran Bhattacharya, Ishita Dasgupta, Stefano Petrangeli, Rajiv Ratn Shah, Changyou Chen, Balaji Krishnamurthy
We call these models Large Content and Behavior Models (LCBMs).
no code implementations • 1 Sep 2023 • Harini S I, Somesh Singh, Yaman K Singla, Aanisha Bhattacharyya, Veeky Baths, Changyou Chen, Rajiv Ratn Shah, Balaji Krishnamurthy
Finally, with the intent of memorable ad generation, we present a scalable method to build a high-quality memorable ad generation model by leveraging automatically annotated data.
1 code implementation • 22 Aug 2023 • Silky Singh, Shripad Deshmukh, Mausoom Sarkar, Balaji Krishnamurthy
We demonstrate the effectiveness of our approach, named LOCATE, on multiple standard video object segmentation, image saliency detection, and object segmentation benchmarks, achieving results on par with and, in many cases surpassing state-of-the-art methods.
no code implementations • 10 Jul 2023 • Silky Singh, Shripad Deshmukh, Mausoom Sarkar, Rishabh Jain, Mayur Hemani, Balaji Krishnamurthy
Segmentation of objects in a video is challenging due to the nuances such as motion blurring, parallax, occlusions, changes in illumination, etc.
1 code implementation • 28 Jun 2023 • Sukriti Verma, Ayush Chopra, Jayakumar Subramanian, Mausoom Sarkar, Nikaash Puri, Piyush Gupta, Balaji Krishnamurthy
The two-time scale nature of SAC, which is an actor-critic algorithm, is characterised by the fact that the critic estimate has not converged for the actor at any given time, but since the critic learns faster than the actor, it ensures eventual consistency between the two.
1 code implementation • 16 May 2023 • Aanisha Bhattacharya, Yaman K Singla, Balaji Krishnamurthy, Rajiv Ratn Shah, Changyou Chen
Multimedia content, such as advertisements and story videos, exhibit a rich blend of creativity and multiple modalities.
1 code implementation • 16 May 2023 • Simra Shahid, Tanay Anand, Nikitha Srikanth, Sumit Bhatia, Balaji Krishnamurthy, Nikaash Puri
We present HyHTM - a Hyperbolic geometry based Hierarchical Topic Models - that addresses these limitations by incorporating hierarchical information from hyperbolic geometry to explicitly model hierarchies in topic models.
no code implementations • 11 May 2023 • H S V N S Kowndinya Renduchintala, KrishnaTeja Killamsetty, Sumit Bhatia, Milan Aggarwal, Ganesh Ramakrishnan, Rishabh Iyer, Balaji Krishnamurthy
A salient characteristic of pre-trained language models (PTLMs) is a remarkable improvement in their generalization capability and emergence of new capabilities with increasing model capacity and pre-training dataset size.
1 code implementation • 6 May 2023 • Shripad Vilasrao Deshmukh, Arpan Dasgupta, Balaji Krishnamurthy, Nan Jiang, Chirag Agarwal, Georgios Theocharous, Jayakumar Subramanian
To do so, we encode trajectories in offline training data individually as well as collectively (encoding a set of trajectories).
no code implementations • CVPR 2023 • Mausoom Sarkar, Nikitha SR, Mayur Hemani, Rishabh Jain, Balaji Krishnamurthy
Face parsing is defined as the per-pixel labeling of images containing human faces.
no code implementations • 11 Feb 2023 • Varun Khurana, Yaman Kumar Singla, Nora Hollenstein, Rajesh Kumar, Balaji Krishnamurthy
Feedback can be either explicit (e. g. ranking used in training language models) or implicit (e. g. using human cognitive signals in the form of eyetracking).
no code implementations • 17 Jan 2023 • Tarun Ram Menta, Surgan Jandial, Akash Patil, Vimal KB, Saketh Bachu, Balaji Krishnamurthy, Vineeth N. Balasubramanian, Chirag Agarwal, Mausoom Sarkar
As transfer learning techniques are increasingly used to transfer knowledge from the source model to the target task, it becomes important to quantify which source models are suitable for a given target task without performing computationally expensive fine tuning.
no code implementations • ICCV 2023 • Rishabh Jain, Mayur Hemani, Duygu Ceylan, Krishna Kumar Singh, Jingwan Lu, Mausoom Sarkar, Balaji Krishnamurthy
Numerous pose-guided human editing methods have been explored by the vision community due to their extensive practical applications.
no code implementations • CVPR 2023 • Rishabh Jain, Krishna Kumar Singh, Mayur Hemani, Jingwan Lu, Mausoom Sarkar, Duygu Ceylan, Balaji Krishnamurthy
The task of human reposing involves generating a realistic image of a person standing in an arbitrary conceivable pose.
1 code implementation • 21 Oct 2022 • Surgan Jandial, Yash Khasbage, Arghya Pal, Vineeth N Balasubramanian, Balaji Krishnamurthy
The inadvertent stealing of private/sensitive information using Knowledge Distillation (KD) has been getting significant attention recently and has guided subsequent defense efforts considering its critical nature.
no code implementations • 12 Sep 2022 • Abhinav Java, Shripad Deshmukh, Milan Aggarwal, Surgan Jandial, Mausoom Sarkar, Balaji Krishnamurthy
MONOMER fuses context from visual, textual, and spatial modalities of snippets and documents to find query snippet in target documents.
1 code implementation • 20 Aug 2022 • Yaman Kumar Singla, Rajat Jha, Arunim Gupta, Milan Aggarwal, Aditya Garg, Tushar Malyan, Ayush Bhardwaj, Rajiv Ratn Shah, Balaji Krishnamurthy, Changyou Chen
Motivated by persuasion literature in social psychology and marketing, we introduce an extensive vocabulary of persuasion strategies and build the first ad image corpus annotated with persuasion strategies.
1 code implementation • Findings (NAACL) 2022 • Jivat Neet Kaur, Sumit Bhatia, Milan Aggarwal, Rachit Bansal, Balaji Krishnamurthy
Large transformer-based pre-trained language models have achieved impressive performance on a variety of knowledge-intensive tasks and can capture factual knowledge in their parameters.
1 code implementation • 20 Jul 2022 • Ayush Chopra, Alexander Rodríguez, Jayakumar Subramanian, Arnau Quera-Bofarull, Balaji Krishnamurthy, B. Aditya Prakash, Ramesh Raskar
Mechanistic simulators are an indispensable tool for epidemiology to explore the behavior of complex, dynamic infections under varying conditions and navigate uncertain environments.
no code implementations • 13 Jun 2022 • Puneet Mangla, Shivam Chandhok, Milan Aggarwal, Vineeth N Balasubramanian, Balaji Krishnamurthy
To this end, we propose IntriNsic multimodality for DomaIn GeneralizatiOn (INDIGO), a simple and elegant way of leveraging the intrinsic modality present in these pre-trained multimodal networks along with the visual modality to enhance generalization to unseen domains at test-time.
no code implementations • NAACL 2022 • Rachit Bansal, Milan Aggarwal, Sumit Bhatia, Jivat Neet Kaur, Balaji Krishnamurthy
To train CoSe-Co, we propose a novel dataset comprising of sentence and commonsense knowledge pairs.
no code implementations • 8 May 2022 • Vedant Singh, Surgan Jandial, Ayush Chopra, Siddharth Ramesh, Balaji Krishnamurthy, Vineeth N. Balasubramanian
Conditional image generation has paved the way for several breakthroughs in image editing, generating stock photos and 3-D object generation.
no code implementations • 9 Oct 2021 • Ayush Chopra, Esma Gel, Jayakumar Subramanian, Balaji Krishnamurthy, Santiago Romero-Brufau, Kalyan S. Pasupathy, Thomas C. Kingsley, Ramesh Raskar
We introduce DeepABM, a framework for agent-based modeling that leverages geometric message passing of graph neural networks for simulating action and interactions over large agent populations.
1 code implementation • 25 Sep 2021 • Swapnil Parekh, Yaman Singla Kumar, Somesh Singh, Changyou Chen, Balaji Krishnamurthy, Rajiv Ratn Shah
It is well known that natural language models are vulnerable to adversarial attacks, which are mostly input-specific in nature.
no code implementations • ICCV 2021 • Ayush Chopra, Rishabh Jain, Mayur Hemani, Balaji Krishnamurthy
Image-based virtual try-on involves synthesizing perceptually convincing images of a model wearing a particular garment and has garnered significant research interest due to its immense practical applicability.
no code implementations • 8 Sep 2021 • Sumedh A Sontakke, Sumegh Roychowdhury, Mausoom Sarkar, Nikaash Puri, Balaji Krishnamurthy, Laurent Itti
Humans excel at learning long-horizon tasks from demonstrations augmented with textual commentary, as evidenced by the burgeoning popularity of tutorial videos online.
no code implementations • AKBC Workshop CSKB 2021 • Jivat Neet Kaur, Sumit Bhatia, Milan Aggarwal, Rachit Bansal, Balaji Krishnamurthy
This allows the training of the language model to be de-coupled from the external knowledge source and the latter can be updated without affecting the parameters of the language model.
no code implementations • AKBC Workshop CSKB 2021 • Rachit Bansal, Milan Aggarwal, Sumit Bhatia, Jivat Neet Kaur, Balaji Krishnamurthy
Pre-trained Language Models (PTLMs) have been shown to perform well on natural language reasoning tasks requiring commonsense.
no code implementations • 30 Aug 2021 • Yaman Kumar Singla, Avykat Gupta, Shaurya Bagga, Changyou Chen, Balaji Krishnamurthy, Rajiv Ratn Shah
In our technique, we take advantage of the fact that oral proficiency tests rate multiple responses for a candidate.
1 code implementation • EMNLP 2020 • Milan Aggarwal, Hiresh Gupta, Mausoom Sarkar, Balaji Krishnamurthy
To mitigate this, we propose Form2Seq, a novel sequence-to-sequence (Seq2Seq) inspired framework for structure extraction using text, with a specific focus on forms, which leverages relative spatial arrangement of structures.
1 code implementation • 9 Jul 2021 • Milan Aggarwal, Mausoom Sarkar, Hiresh Gupta, Balaji Krishnamurthy
Experimental results show the effectiveness of our approach achieving a recall of 90. 29%, 73. 80%, 83. 12%, and 52. 72% for the above structures, respectively, outperforming semantic segmentation baselines significantly.
no code implementations • 14 May 2021 • Sukriti Verma, Nikaash Puri, Piyush Gupta, Balaji Krishnamurthy
Our approach builds on top of existing local model explanation methods to extract conditions important for explaining model behavior for specific instances followed by an evolutionary algorithm that optimizes an information theory based fitness function to construct rules that explain global model behavior.
no code implementations • 8 Dec 2020 • Puneet Mangla, Nupur Kumari, Mayank Singh, Balaji Krishnamurthy, Vineeth N Balasubramanian
Previous works have addressed training in low data setting by leveraging transfer learning and data augmentation techniques.
no code implementations • ACL 2021 • Madhur Panwar, Shashank Shailabh, Milan Aggarwal, Balaji Krishnamurthy
Topic models have been widely used to learn text representations and gain insight into document corpora.
no code implementations • 19 Oct 2020 • Parth Patel, Nupur Kumari, Mayank Singh, Balaji Krishnamurthy
We propose a self-supervised approach (LT-GAN) to improve the generation quality and diversity of images by estimating the GAN-induced transformation (i. e. transformation induced in the generated images by perturbing the latent space of generator).
Ranked #4 on Image Generation on CelebA-HQ 128x128
1 code implementation • 6 Oct 2020 • Sumegh Roychowdhury, Sumedh A. Sontakke, Nikaash Puri, Mausoom Sarkar, Milan Aggarwal, Pinkesh Badjatiya, Balaji Krishnamurthy, Laurent Itti
Also, they are believed to be arranged hierarchically, allowing for an efficient representation of complex long-horizon experiences.
no code implementations • 28 Sep 2020 • Puneet Mangla, Nupur Kumari, Mayank Singh, Vineeth N. Balasubramanian, Balaji Krishnamurthy
Recent advances in generative adversarial networks (GANs) have shown remarkable progress in generating high-quality images.
no code implementations • 3 Sep 2020 • Surgan Jandial, Pinkesh Badjatiya, Pranit Chawla, Ayush Chopra, Mausoom Sarkar, Balaji Krishnamurthy
The ability to efficiently search for images is essential for improving the user experiences across various products.
no code implementations • 24 Jun 2020 • Surgan Jandial, Ayush Chopra, Mausoom Sarkar, Piyush Gupta, Balaji Krishnamurthy, Vineeth Balasubramanian
Deep neural networks (DNNs) are powerful learning machines that have enabled breakthroughs in several domains.
1 code implementation • ICLR 2020 • Piyush Gupta, Nikaash Puri, Sukriti Verma, Dhruv Kayastha, Shripad Deshmukh, Balaji Krishnamurthy, Sameer Singh
We show through illustrative examples (Chess, Atari, Go), human studies (Chess), and automated evaluation methods (Chess) that our approach generates saliency maps that are more interpretable for humans than existing approaches.
no code implementations • 30 Apr 2020 • Siddhartha Gairola, Mayur Hemani, Ayush Chopra, Balaji Krishnamurthy
Few-shot segmentation (FSS) methods perform image segmentation for a particular object class in a target (query) image, using a small set of (support) image-mask pairs.
no code implementations • 16 Feb 2020 • Hrituraj Singh, Milan Aggrawal, Balaji Krishnamurthy
We model FOL parsing as a sequence to sequence mapping task where given a natural language sentence, it is encoded into an intermediate representation using an LSTM followed by a decoder which sequentially generates the predicates in the corresponding FOL formula.
1 code implementation • 17 Jan 2020 • Surgan Jandial, Ayush Chopra, Kumar Ayush, Mayur Hemani, Abhijeet Kumar, Balaji Krishnamurthy
An efficient framework for this is composed of two stages: (1) warping (transforming) the try-on cloth to align with the pose and shape of the target model, and (2) a texture transfer module to seamlessly integrate the warped try-on cloth onto the target model image.
no code implementations • 15 Jan 2020 • Nupur Kumari, Siddarth R., Akash Rupela, Piyush Gupta, Balaji Krishnamurthy
This graph captures the structural characteristics of the point cloud, and its weights are determined using a Finite Markov Chain.
no code implementations • 15 Jan 2020 • Pinkesh Badjatiya, Mausoom Sarkar, Abhishek Sinha, Siddharth Singh, Nikaash Puri, Jayakumar Subramanian, Balaji Krishnamurthy
We show how agents trained with SQLoss evolve cooperative behavior in several social dilemma matrix games.
2 code implementations • 23 Dec 2019 • Nikaash Puri, Sukriti Verma, Piyush Gupta, Dhruv Kayastha, Shripad Deshmukh, Balaji Krishnamurthy, Sameer Singh
We show through illustrative examples (Chess, Atari, Go), human studies (Chess), and automated evaluation methods (Chess) that SARFA generates saliency maps that are more interpretable for humans than existing approaches.
no code implementations • 1 Dec 2019 • Tejus Gupta, Abhishek Sinha, Nupur Kumari, Mayank Singh, Balaji Krishnamurthy
We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks.
1 code implementation • ECCV 2020 • Mayank Singh, Nupur Kumari, Puneet Mangla, Abhishek Sinha, Vineeth N. Balasubramanian, Balaji Krishnamurthy
Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust.
Ranked #1 on Weakly-Supervised Object Localization on CUB-200-2011 (Top-1 Error Rate metric)
BIG-bench Machine Learning Weakly-Supervised Object Localization
no code implementations • ECCV 2020 • Mausoom Sarkar, Milan Aggarwal, Arneh Jain, Hiresh Gupta, Balaji Krishnamurthy
We introduce our new human-annotated forms dataset and show that our method significantly outperforms different segmentation baselines on this dataset in extracting hierarchical structures.
no code implementations • 25 Sep 2019 • Ayush Chopra, Surgan Jandial, Mausoom Sarkar, Balaji Krishnamurthy, Vineeth Balasubramanian
Deep neural networks are powerful learning machines that have enabled breakthroughs in several domains.
7 code implementations • 28 Jul 2019 • Puneet Mangla, Mayank Singh, Abhishek Sinha, Nupur Kumari, Vineeth N. Balasubramanian, Balaji Krishnamurthy
A recent regularization technique - Manifold Mixup focuses on learning a general-purpose representation, robust to small changes in the data distribution.
1 code implementation • 13 May 2019 • Mayank Singh, Abhishek Sinha, Nupur Kumari, Harshitha Machiraju, Balaji Krishnamurthy, Vineeth N. Balasubramanian
We analyze the adversarially trained robust models to study their vulnerability against adversarial attacks at the level of the latent layers.
no code implementations • 11 Nov 2018 • Milan Aggarwal, Nupur Kumari, Ayush Bansal, Balaji Krishnamurthy
Generating paraphrases, that is, different variations of a sentence conveying the same meaning, is an important yet challenging task in NLP.
1 code implementation • 23 Apr 2018 • Akilesh B, Abhishek Sinha, Mausoom Sarkar, Balaji Krishnamurthy
We develop an attention mechanism for multi-modal fusion of visual and textual modalities that allows the agent to learn to complete the task and achieve language grounding.
no code implementations • 3 Jan 2018 • Mayank Singh, Abhishek Sinha, Balaji Krishnamurthy
Recently, Neural networks have seen a huge surge in its adoption due to their ability to provide high accuracy on various tasks.
no code implementations • ICLR 2018 • Abhishek Sinha, Akilesh B, Mausoom Sarkar, Balaji Krishnamurthy
In this work, we focus on the problem of grounding language by training an agent to follow a set of natural language instructions and navigate to a target object in a 2D grid environment.
no code implementations • ICLR 2018 • Milan Aggarwal, Aarushi Arora, Shagun Sodhani, Balaji Krishnamurthy
We develop a reinforcement learning based search assistant which can assist users through a set of actions and sequence of interactions to enable them realize their intent.
no code implementations • 22 Jun 2017 • Nikaash Puri, Piyush Gupta, Pratiksha Agarwal, Sukriti Verma, Balaji Krishnamurthy
Explaining the behavior of a black box machine learning model at the instance level is useful for building trust.
no code implementations • 17 Apr 2017 • Abhishek Sinha, Mausoom Sarkar, Aahitagni Mukherjee, Balaji Krishnamurthy
In this paper, we explore the idea of learning weight evolution pattern from a simple network for accelerating training of novel neural networks.