Zobrazeno 1 - 10
of 46 455
pro vyhledávání: '"Ashwin BY"'
Visual navigation takes inspiration from humans, who navigate in previously unseen environments using vision without detailed environment maps. Inspired by this, we introduce a novel no-RL, no-graph, no-odometry approach to visual navigation using fe
Externí odkaz:
http://arxiv.org/abs/2411.09893
Current metadata creation for web archives is time consuming and costly due to reliance on human effort. This paper explores the use of gpt-4o for metadata generation within the Web Archive Singapore, focusing on scalability, efficiency, and cost eff
Externí odkaz:
http://arxiv.org/abs/2411.05409
Autor:
Jain, Sparsh, Sankar, Ashwin, Choudhary, Devilal, Suman, Dhairya, Narasimhan, Nikhil, Khan, Mohammed Safi Ur Rahman, Kunchukuttan, Anoop, Khapra, Mitesh M, Dabre, Raj
Automatic Speech Translation (AST) datasets for Indian languages remain critically scarce, with public resources covering fewer than 10 of the 22 official languages. This scarcity has resulted in AST systems for Indian languages lagging far behind th
Externí odkaz:
http://arxiv.org/abs/2411.04699
GraphVL: Graph-Enhanced Semantic Modeling via Vision-Language Models for Generalized Class Discovery
Autor:
Solanki, Bhupendra, Nair, Ashwin, Singha, Mainak, Mukhopadhyay, Souradeep, Jha, Ankit, Banerjee, Biplab
Generalized Category Discovery (GCD) aims to cluster unlabeled images into known and novel categories using labeled images from known classes. To address the challenge of transferring features from known to unknown classes while mitigating model bias
Externí odkaz:
http://arxiv.org/abs/2411.02074
Autor:
Alsubeihi, Mohammed, Jessop, Arthur, Moseley, Ben, Fonte, Cláudio P., Rajagopalan, Ashwin Kumar
Population balance equation (PBE) models have potential to automate many engineering processes with far-reaching implications. In the pharmaceutical sector, crystallization model-based design can contribute to shortening excessive drug development ti
Externí odkaz:
http://arxiv.org/abs/2411.00742
Autor:
Balasubramanian, Ashwin, Zou, Vito, Narayana, Hitesh, You, Christina, Luceri, Luca, Ferrara, Emilio
In this paper, we introduce the first release of a large-scale dataset capturing discourse on $\mathbb{X}$ (a.k.a., Twitter) related to the upcoming 2024 U.S. Presidential Election. Our dataset comprises 22 million publicly available posts on X.com,
Externí odkaz:
http://arxiv.org/abs/2411.00376
Autor:
De Silva, Ashwin, Ramesh, Rahul, Yang, Rubing, Yu, Siyu, Vogelstein, Joshua T, Chaudhari, Pratik
In real-world applications, the distribution of the data, and our goals, evolve over time. The prevailing theoretical framework for studying machine learning, namely probably approximately correct (PAC) learning, largely ignores time. As a consequenc
Externí odkaz:
http://arxiv.org/abs/2411.00109
Publikováno v:
NeurIPS 2024 Workshop on Open-World Agents
Recent advancements in Large Language Model (LLM)-based frameworks have extended their capabilities to complex real-world applications, such as interactive web navigation. These systems, driven by user commands, navigate web browsers to complete task
Externí odkaz:
http://arxiv.org/abs/2410.23555
Enhancing and preserving the readability of document images, particularly historical ones, is crucial for effective document image analysis. Numerous models have been proposed for this task, including convolutional-based, transformer-based, and hybri
Externí odkaz:
http://arxiv.org/abs/2410.22811
Our interest is in constructing interactive systems involving a human-expert interacting with a machine learning engine on data analysis tasks. This is of relevance when addressing complex problems arising in areas of science, the environment, medici
Externí odkaz:
http://arxiv.org/abs/2410.20600