Zobrazeno 1 - 10
of 9 036
pro vyhledávání: '"Tuli A."'
Autor:
Lin, Chi-Heng, Gao, Shangqian, Smith, James Seale, Patel, Abhishek, Tuli, Shikhar, Shen, Yilin, Jin, Hongxia, Hsu, Yen-Chang
Large Language Models (LLMs) have reshaped the landscape of artificial intelligence by demonstrating exceptional performance across various tasks. However, substantial computational requirements make their deployment challenging on devices with limit
Externí odkaz:
http://arxiv.org/abs/2408.09632
Autor:
Dorna, Vineeth, Subhalingam, D., Kolluru, Keshav, Tuli, Shreshth, Singh, Mrityunjay, Singal, Saurabh, Krishnan, N. M. Anoop, Ranu, Sayan
3D generative models have shown significant promise in structure-based drug design (SBDD), particularly in discovering ligands tailored to specific target binding sites. Existing algorithms often focus primarily on ligand-target binding, characterize
Externí odkaz:
http://arxiv.org/abs/2406.01650
Autor:
Kalithasan, Namasivayam, Tuli, Arnav, Bindal, Vishal, Singh, Himanshu Gaurav, Singla, Parag, Paul, Rohan
Automatically detecting and recovering from failures is an important but challenging problem for autonomous robots. Most of the recent work on learning to plan from demonstrations lacks the ability to detect and recover from errors in the absence of
Externí odkaz:
http://arxiv.org/abs/2405.18948
Traditional language models operate autoregressively, i.e., they predict one token at a time. Rapid explosion in model sizes has resulted in high inference times. In this work, we propose DynaMo, a suite of multi-token prediction language models that
Externí odkaz:
http://arxiv.org/abs/2405.00888
Autor:
Chopra, Mudit, Barnawal, Abhinav, Vagadia, Harshil, Banerjee, Tamajit, Tuli, Shreshth, Chakraborty, Souvik, Paul, Rohan
Given the task of positioning a ball-like object to a goal region beyond direct reach, humans can often throw, slide, or rebound objects against the wall to attain the goal. However, enabling robots to reason similarly is non-trivial. Existing method
Externí odkaz:
http://arxiv.org/abs/2406.00001
When working with 3D facial data, improving fidelity and avoiding the uncanny valley effect is critically dependent on accurate 3D facial performance capture. Because such methods are expensive and due to the widespread availability of 2D videos, rec
Externí odkaz:
http://arxiv.org/abs/2404.09819
Autor:
Kalithasan, Namasivayam, Sachdeva, Sachit, Singh, Himanshu Gaurav, Bindal, Vishal, Tuli, Arnav, Panjeta, Gurarmaan Singh, Aggarwal, Divyanshu, Paul, Rohan, Singla, Parag
Our goal is to enable embodied agents to learn inductively generalizable spatial concepts, e.g., learning staircase as an inductive composition of towers of increasing height. Given a human demonstration, we seek a learning architecture that infers a
Externí odkaz:
http://arxiv.org/abs/2404.07774
Manipulating unseen objects is challenging without a 3D representation, as objects generally have occluded surfaces. This requires physical interaction with objects to build their internal representations. This paper presents an approach that enables
Externí odkaz:
http://arxiv.org/abs/2404.01812
Autor:
Vagadia, Harshil, Chopra, Mudit, Barnawal, Abhinav, Banerjee, Tamajit, Tuli, Shreshth, Chakraborty, Souvik, Paul, Rohan
Given the task of positioning a ball-like object to a goal region beyond direct reach, humans can often throw, slide, or rebound objects against the wall to attain the goal. However, enabling robots to reason similarly is non-trivial. Existing method
Externí odkaz:
http://arxiv.org/abs/2402.15767
Autor:
Moslemi, Zahra, Clark, Logan, Kernal, Sarah, Rehome, Samantha, Sprengel, Scott, Tamizifar, Ahoora, Tuli, Shawna, Chokshi, Vish, Nomeli, Mo, Liang, Ella, Bidgoli, Moury, Lu, Jeff, Dasaur, Manish, Hodgett, Marty
California's significant role as the second-largest consumer of energy in the United States underscores the importance of accurate energy consumption predictions. With a thriving industrial sector, a burgeoning population, and ambitious environmental
Externí odkaz:
http://arxiv.org/abs/2402.04432