Zobrazeno 1 - 10
of 2 241
pro vyhledávání: '"P., Nishanth"'
Autor:
Nakshatri, Nishanth, Roy, Shamik, Das, Rajarshi, Chaidaroon, Suthee, Boytsov, Leonid, Gangadharaiah, Rashmi
Constrained decoding with lookahead heuristics (CDLH) is a highly effective method for aligning LLM generations to human preferences. However, the extensive lookahead roll-out operations for each generated token makes CDLH prohibitively expensive, re
Externí odkaz:
http://arxiv.org/abs/2412.10418
Foundation models trained on internet-scale data, such as Vision-Language Models (VLMs), excel at performing tasks involving common sense, such as visual question answering. Despite their impressive capabilities, these models cannot currently be dire
Externí odkaz:
http://arxiv.org/abs/2411.08253
Autor:
Hong, Guan Zhe, Dikkala, Nishanth, Luo, Enming, Rashtchian, Cyrus, Wang, Xin, Panigrahy, Rina
Large language models (LLMs) have shown amazing performance on tasks that require planning and reasoning. Motivated by this, we investigate the internal mechanisms that underpin a network's ability to perform complex logical reasoning. We first const
Externí odkaz:
http://arxiv.org/abs/2411.04105
Autor:
Bhattacharya, Anish, Cannici, Marco, Rao, Nishanth, Tao, Yuezhan, Kumar, Vijay, Matni, Nikolai, Scaramuzza, Davide
Publikováno v:
Conference on Robot Learning (CoRL), Munich, Germany, 2024
We present the first static-obstacle avoidance method for quadrotors using just an onboard, monocular event camera. Quadrotors are capable of fast and agile flight in cluttered environments when piloted manually, but vision-based autonomous flight in
Externí odkaz:
http://arxiv.org/abs/2411.03303
Autor:
Basava, Nishanth
Publikováno v:
2024 Handbook for the Tennessee Junior Academy of Science
As cancer cases continue to rise, with a 2023 study from Zhejiang and Harvard predicting a 31 percent increase in cases and a 21 percent increase in deaths by 2030, the need to find more effective treatments for cancer is greater than ever before. Tr
Externí odkaz:
http://arxiv.org/abs/2411.00885
Autor:
Liang, Yichao, Kumar, Nishanth, Tang, Hao, Weller, Adrian, Tenenbaum, Joshua B., Silver, Tom, Henriques, João F., Ellis, Kevin
Broadly intelligent agents should form task-specific abstractions that selectively expose the essential elements of a task, while abstracting away the complexity of the raw sensorimotor space. In this work, we present Neuro-Symbolic Predicates, a fir
Externí odkaz:
http://arxiv.org/abs/2410.23156
Publikováno v:
16th International Conference on Advances in Social Networks Analysis and Mining -ASONAM-2024
Recent studies have outlined the accessibility challenges faced by blind or visually impaired, and less-literate people, in interacting with social networks, in-spite of facilitating technologies such as monotone text-to-speech (TTS) screen readers a
Externí odkaz:
http://arxiv.org/abs/2410.19199
Active learning (AL) is for optimizing the selection of unlabeled data for annotation (labeling), aiming to enhance model performance while minimizing labeling effort. The key question in AL is which unlabeled data should be selected for annotation.
Externí odkaz:
http://arxiv.org/abs/2410.15605
In this work, we use a Discrete Element Method (DEM) to explore the viscous to inertial shear thickening transition of dense frictionless non-Brownian suspensions close to jamming. This transition is characterized by a change in the steady state rheo
Externí odkaz:
http://arxiv.org/abs/2410.12140
Autor:
Wang, Zeqiang, Wu, Jiageng, Wang, Yuqi, Wang, Wei, Yang, Jie, Johnson, Jon, Sastry, Nishanth, De, Suparna
Social media is recognized as an important source for deriving insights into public opinion dynamics and social impacts due to the vast textual data generated daily and the 'unconstrained' behavior of people interacting on these platforms. However, s
Externí odkaz:
http://arxiv.org/abs/2410.08352