Zobrazeno 1 - 10
of 81
pro vyhledávání: '"BHATTACHARYA, SOURANGSHU"'
Autor:
Purohit, Kiran, V, Venktesh, Devalla, Raghuram, Yerragorla, Krishna Mohan, Bhattacharya, Sourangshu, Anand, Avishek
Answering reasoning-based complex questions over text and hybrid sources, including tables, is a challenging task. Recent advances in large language models (LLMs) have enabled in-context learning (ICL), allowing LLMs to acquire proficiency in a speci
Externí odkaz:
http://arxiv.org/abs/2411.03877
Deep convolutional neural networks (CNNs) have achieved impressive performance in many computer vision tasks. However, their large model sizes require heavy computational resources, making pruning redundant filters from existing pre-trained CNNs an e
Externí odkaz:
http://arxiv.org/abs/2409.03777
Autor:
Das, Soumi, Nag, Shubhadip, Sharma, Shreyyash, Bhattacharya, Suparna, Bhattacharya, Sourangshu
Trustworthy AI is crucial to the widespread adoption of AI in high-stakes applications with fairness, robustness, and accuracy being some of the key trustworthiness metrics. In this work, we propose a controllable framework for data-centric trustwort
Externí odkaz:
http://arxiv.org/abs/2403.05174
Answering complex questions is a challenging task that requires question decomposition and multistep reasoning for arriving at the solution. While existing supervised and unsupervised approaches are specialized to a certain task and involve training,
Externí odkaz:
http://arxiv.org/abs/2310.18371
Federated Learning systems are increasingly subjected to a multitude of model poisoning attacks from clients. Among these, edge-case attacks that target a small fraction of the input space are nearly impossible to detect using existing defenses, lead
Externí odkaz:
http://arxiv.org/abs/2305.02022
Team competition in multi-agent Markov games is an increasingly important setting for multi-agent reinforcement learning, due to its general applicability in modeling many real-life situations. Multi-agent actor-critic methods are the most suitable c
Externí odkaz:
http://arxiv.org/abs/2301.05873
A large fraction of data generated via human activities such as online purchases, health records, spatial mobility etc. can be represented as a sequence of events over a continuous-time. Learning deep learning models over these continuous-time event
Externí odkaz:
http://arxiv.org/abs/2206.12414
Autor:
Sinha, Suvadip, Gupta, Om, Singh, Vishal, Lekshmi, B., Nandy, Dibyendu, Mitra, Dhrubaditya, Chatterjee, Saikat, Bhattacharya, Sourangshu, Chatterjee, Saptarshi, Srivastava, Nandita, Brandenburg, Axel, Pal, Sanchita
Publikováno v:
Astrophys. J. 935, 45 (2022)
Solar flares create adverse space weather impacting space and Earth-based technologies. However, the difficulty of forecasting flares, and by extension severe space weather, is accentuated by the lack of any unique flare trigger or a single physical
Externí odkaz:
http://arxiv.org/abs/2204.05910
Data valuation and subset selection have emerged as valuable tools for application-specific selection of important training data. However, the efficiency-accuracy tradeoffs of state-of-the-art methods hinder their widespread application to many AI wo
Externí odkaz:
http://arxiv.org/abs/2203.06814
This paper investigates the dynamics of competition among organizations with unequal expertise. Multi-agent reinforcement learning has been used to simulate and understand the impact of various incentive schemes designed to offset such inequality. We
Externí odkaz:
http://arxiv.org/abs/2201.01450