347 citations · 795 across the 48 of their papers we have counts for
52 papers
ResearchCodeAgent: An LLM Multi-Agent System for Automated Codification of Research Methodologies
Shubham Gandhi, Dhruv Shah, Manasi Patwardhan +2
In this paper we introduce ResearchCodeAgent, a novel multi-agent system leveraging large language models (LLMs) agents to automate the codification of research methodologies descr…
BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks
Shubham Gandhi, Manasi Patwardhan, Lovekesh Vig +1
Large Language Models (LLMs) excel in diverse applications including generation of code snippets, but often struggle with generating code for complex Machine Learning (ML) tasks. A…
SmartFlow: Robotic Process Automation using LLMs
Arushi Jain, Shubham Paliwal, Monika Sharma +2
Robotic Process Automation (RPA) systems face challenges in handling complex processes and diverse screen layouts that require advanced human-like decision-making capabilities. The…
Acceleron: A Tool to Accelerate Research Ideation
Harshit Nigam, Manasi Patwardhan, Lovekesh Vig +1
Several tools have recently been proposed for assisting researchers during various stages of the research life-cycle. However, these primarily concentrate on tasks such as retrievi…
Adapt and Decompose: Efficient Generalization of Text-to-SQL via Domain Adapted Least-To-Most Prompting
Aseem Arora, Shabbirhussain Bhaisaheb, Harshit Nigam +3
Cross-domain and cross-compositional generalization of Text-to-SQL semantic parsing is a challenging task. Existing Large Language Model (LLM) based solutions rely on inference-tim…
Neuro-symbolic Meta Reinforcement Learning for Trading
S I Harini, Gautam Shroff, Ashwin Srinivasan +2
We model short-duration (e.g. day) trading in financial markets as a sequential decision-making problem under uncertainty, with the added complication of continual concept-drift. W…
Calibrating Deep Neural Networks using Explicit Regularisation and Dynamic Data Pruning
Ramya Hebbalaguppe, Rishabh Patra, Tirtharaj Dash +2
Deep neural networks (DNN) are prone to miscalibrated predictions, often exhibiting a mismatch between the predicted output and the associated confidence scores. Contemporary model…
Neural Feature-Adaptation for Symbolic Predictions Using Pre-Training and Semantic Loss
Vedant Shah, Aditya Agrawal, Lovekesh Vig +3
We are interested in neurosymbolic systems consisting of a high-level symbolic layer for explainable prediction in terms of human-intelligible concepts; and a low-level neural laye…
Knowledge-based Analogical Reasoning in Neuro-symbolic Latent Spaces
Vishwa Shah, Aditya Sharma, Gautam Shroff +3
Analogical Reasoning problems challenge both connectionist and symbolic AI systems as these entail a combination of background knowledge, reasoning and pattern recognition. While s…
Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions
Vibhor Gupta, Jyoti Narwariya, Pankaj Malhotra +2
We consider a sequence of related multivariate time series learning tasks, such as predicting failures for different instances of a machine from time series of multi-sensor data, o…
Learning to Liquidate Forex: Optimal Stopping via Adaptive Top-K Regression
Diksha Garg, Pankaj Malhotra, Anil Bhatia +3
We consider learning a trading agent acting on behalf of the treasury of a firm earning revenue in a foreign currency (FC) and incurring expenses in the home currency (HC). The goa…
DRTCI: Learning Disentangled Representations for Temporal Causal Inference
Garima Gupta, Lovekesh Vig, Gautam Shroff
Medical professionals evaluating alternative treatment plans for a patient often encounter time varying confounders, or covariates that affect both the future treatment assignment…
Solving Visual Analogies Using Neural Algorithmic Reasoning
Atharv Sonwane, Gautam Shroff, Lovekesh Vig +2
We consider a class of visual analogical reasoning problems that involve discovering the sequence of transformations by which pairs of input/output images are related, so as to ana…
Using Program Synthesis and Inductive Logic Programming to solve Bongard Problems
Atharv Sonwane, Sharad Chitlangia, Tirtharaj Dash +3
The ability to recognise and make analogies is often used as a measure or test of human intelligence. The ability to solve Bongard problems is an example of such a test. It has als…
Forecasting Market Prices using DL with Data Augmentation and Meta-learning: ARIMA still wins!
Vedant Shah, Gautam Shroff
Deep-learning techniques have been successfully used for time-series forecasting and have often shown superior performance on many standard benchmark datasets as compared to tradit…
Batch-Constrained Distributional Reinforcement Learning for Session-based Recommendation
Diksha Garg, Priyanka Gupta, Pankaj Malhotra +2
Most of the existing deep reinforcement learning (RL) approaches for session-based recommendations either rely on costly online interactions with real users, or rely on potentially…
CAMTA: Causal Attention Model for Multi-touch Attribution
Sachin Kumar, Garima Gupta, Ranjitha Prasad +3
Advertising channels have evolved from conventional print media, billboards and radio advertising to online digital advertising (ad), where the users are exposed to a sequence of a…
Hi-CI: Deep Causal Inference in High Dimensions
Ankit Sharma, Garima Gupta, Ranjitha Prasad +3
We address the problem of counterfactual regression using causal inference (CI) in observational studies consisting of high dimensional covariates and high cardinality treatments.…
Handling Variable-Dimensional Time Series with Graph Neural Networks
Vibhor Gupta, Jyoti Narwariya, Pankaj Malhotra +2
Several applications of Internet of Things (IoT) technology involve capturing data from multiple sensors resulting in multi-sensor time series. Existing neural networks based appro…
Graph Neural Networks for Leveraging Industrial Equipment Structure: An application to Remaining Useful Life Estimation
Jyoti Narwariya, Pankaj Malhotra, Vishnu TV +2
Automated equipment health monitoring from streaming multisensor time-series data can be used to enable condition-based maintenance, avoid sudden catastrophic failures, and ensure…
MultiMBNN: Matched and Balanced Causal Inference with Neural Networks
Ankit Sharma, Garima Gupta, Ranjitha Prasad +3
Causal inference (CI) in observational studies has received a lot of attention in healthcare, education, ad attribution, policy evaluation, etc. Confounding is a typical hazard, wh…
MetaCI: Meta-Learning for Causal Inference in a Heterogeneous Population
Ankit Sharma, Garima Gupta, Ranjitha Prasad +3
Performing inference on data obtained through observational studies is becoming extremely relevant due to the widespread availability of data in fields such as healthcare, educatio…
Meta-Learning for Few-Shot Time Series Classification
Jyoti Narwariya, Pankaj Malhotra, Lovekesh Vig +2
Deep neural networks (DNNs) have achieved state-of-the-art results on time series classification (TSC) tasks. In this work, we focus on leveraging DNNs in the often-encountered pra…
NISER: Normalized Item and Session Representations to Handle Popularity Bias
Priyanka Gupta, Diksha Garg, Pankaj Malhotra +2
The goal of session-based recommendation (SR) models is to utilize the information from past actions (e.g. item/product clicks) in a session to recommend items that a user is likel…