no code implementations • 7 Feb 2024 • Dipankar Sarkar
Information retrieval is a rapidly evolving field of information retrieval, which is characterized by a continuous refinement of techniques and technologies, from basic hyperlink-based navigation to sophisticated algorithm-driven search engines.
no code implementations • 31 Dec 2023 • Dipankar Sarkar
The paper delineates the scholarly discourse and developments that have informed the creation of Viz, focusing primarily on the advancements in LLM models, copyright issues in AI training (NYT case, 2023), and the evolution of model fine-tuning techniques, particularly low-rank adapters and quantized low-rank adapters, to create a sustainable and economically compliant framework for LLM utilization.
no code implementations • 16 Jun 2021 • Dipankar Sarkar, Mukur Gupta
Recent works have focused on using complex reinforcement learning techniques to find the optimal data ordering strategy to maximize learning for a given network.
no code implementations • 19 Feb 2021 • Neeraj Kumar, Srishti Goel, Ankur Narang, Brejesh lall, Mujtaba Hasan, Pranshu Agarwal, Dipankar Sarkar
We propose a novel method OneShotAu2AV to generate an animated video of arbitrary length using an audio clip and a single unseen image of a person as an input.
no code implementations • 14 Nov 2020 • Dipankar Sarkar, Sumit Rai, Ankur Narang
Federated learning has allowed the training of statistical models over remote devices without the transfer of raw client data.
no code implementations • 12 Nov 2020 • Dipankar Sarkar, Ankur Narang, Sumit Rai
The Federated Learning setting has a central server coordinating the training of a model on a network of devices.