Zobrazeno 1 - 10
of 28 658
pro vyhledávání: '"P Sengupta"'
Autor:
Mukherjee, Subhojyoti, Lalitha, Anusha, Sengupta, Sailik, Deshmukh, Aniket, Kveton, Branislav
Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs) is a challenging problem as human preferences are complex, multifaceted, and often conflicting. Recent works on MOAHF considered a-priori multi-objective optimizati
Externí odkaz:
http://arxiv.org/abs/2412.05469
People who are blind perceive the world differently than those who are sighted, which can result in distinct motion characteristics. For instance, when crossing at an intersection, blind individuals may have different patterns of movement, such as ve
Externí odkaz:
http://arxiv.org/abs/2412.05277
We study the dynamics of entanglement asymmetry in periodically driven quantum systems. Using a periodically driven XY chain as a model for a driven integrable quantum system, we provide semi-analytic results for the behavior of the dynamics of the e
Externí odkaz:
http://arxiv.org/abs/2412.03654
We introduce a novel continual learning problem: how to sequentially update the weights of a personalized 2D and 3D generative face model as new batches of photos in different appearances, styles, poses, and lighting are captured regularly. We observ
Externí odkaz:
http://arxiv.org/abs/2412.02627
Despite the success of the O-RAN Alliance in developing a set of interoperable interfaces, development of unique Radio Access Network (RAN) deployments remains challenging. This is especially true for military communications, where deployments are hi
Externí odkaz:
http://arxiv.org/abs/2412.00983
Autor:
Sengupta, Saptarshi, Curtis, Kristal, Mallipeddi, Akshay, Mathur, Abhinav, Ross, Joseph, Gou, Liang
Extending the capabilities of Large Language Models (LLMs) with functions or tools for environment interaction has led to the emergence of the agent paradigm. In industry, training an LLM is not always feasible because of the scarcity of domain data,
Externí odkaz:
http://arxiv.org/abs/2412.04494
Autor:
Joshi, Ratnesh Kumar, Priya, Priyanshu, Desai, Vishesh, Dudhate, Saurav, Senapati, Siddhant, Ekbal, Asif, Ramnani, Roshni, Maitra, Anutosh, Sengupta, Shubhashis
Given the advancements in conversational artificial intelligence, the evaluation and assessment of Large Language Models (LLMs) play a crucial role in ensuring optimal performance across various conversational tasks. In this paper, we present a compr
Externí odkaz:
http://arxiv.org/abs/2411.17204
Image-based relighting of indoor rooms creates an immersive virtual understanding of the space, which is useful for interior design, virtual staging, and real estate. Relighting indoor rooms from a single image is especially challenging due to comple
Externí odkaz:
http://arxiv.org/abs/2411.17696
A scheme for generating weakly lower semi-continuous action functionals corresponding to the Euler-Lagrange equations of Chern-Simons theory is described. Coercivity is deduced for such a functional in appropriate function spaces to prove the existen
Externí odkaz:
http://arxiv.org/abs/2411.17635
Facial aging is a complex process, highly dependent on multiple factors like gender, ethnicity, lifestyle, etc., making it extremely challenging to learn a global aging prior to predict aging for any individual accurately. Existing techniques often p
Externí odkaz:
http://arxiv.org/abs/2411.14521