Zobrazeno 1 - 10
of 1 847
pro vyhledávání: '"Prithviraj, P."'
We consider the problem of team formation within multiagent adversarial games. We propose BERTeam, a novel algorithm that uses a transformer-based deep neural network with Masked Language Model training to select the best team of players from a train
Externí odkaz:
http://arxiv.org/abs/2410.13769
We introduce VARM, variant relationship matcher strategy, to identify pairs of variant products in e-commerce catalogs. Traditional definitions of entity resolution are concerned with whether product mentions refer to the same underlying product. How
Externí odkaz:
http://arxiv.org/abs/2410.02779
Traditionally, reward models used for reinforcement learning from human feedback (RLHF) are trained to directly predict preference scores without leveraging the generation capabilities of the underlying large language model (LLM). This limits the cap
Externí odkaz:
http://arxiv.org/abs/2408.11791
CPS-TaskForge: Generating Collaborative Problem Solving Environments for Diverse Communication Tasks
Teams can outperform individuals; could adding AI teammates further bolster performance of teams solving problems collaboratively? Collaborative problem solving (CPS) research commonly studies teams with two agents (human-human or human-AI), but team
Externí odkaz:
http://arxiv.org/abs/2408.08853
Autor:
Banerjee, Prithviraj, Shkodrani, Sindi, Moulon, Pierre, Hampali, Shreyas, Zhang, Fan, Fountain, Jade, Miller, Edward, Basol, Selen, Newcombe, Richard, Wang, Robert, Engel, Jakob Julian, Hodan, Tomas
We introduce HOT3D, a publicly available dataset for egocentric hand and object tracking in 3D. The dataset offers over 833 minutes (more than 3.7M images) of multi-view RGB/monochrome image streams showing 19 subjects interacting with 33 diverse rig
Externí odkaz:
http://arxiv.org/abs/2406.09598
Learning robust and effective representations of visual data is a fundamental task in computer vision. Traditionally, this is achieved by training models with labeled data which can be expensive to obtain. Self-supervised learning attempts to circumv
Externí odkaz:
http://arxiv.org/abs/2406.02535
Autor:
Beason, Jordan, Novitzky, Michael, Kliem, John, Errico, Tyler, Serlin, Zachary, Becker, Kevin, Paine, Tyler, Benjamin, Michael, Dasgupta, Prithviraj, Crowley, Peter, O'Donnell, Charles, James, John
The objective of this work is to evaluate multi-agent artificial intelligence methods when deployed on teams of unmanned surface vehicles (USV) in an adversarial environment. Autonomous agents were evaluated in real-world scenarios using the Aquaticu
Externí odkaz:
http://arxiv.org/abs/2404.17038
Uncertainty Quantification aims to determine when the prediction from a Machine Learning model is likely to be wrong. Computer Vision research has explored methods for determining epistemic uncertainty (also known as model uncertainty), which should
Externí odkaz:
http://arxiv.org/abs/2403.09228
Autor:
Jang, Joel, Kim, Seungone, Lin, Bill Yuchen, Wang, Yizhong, Hessel, Jack, Zettlemoyer, Luke, Hajishirzi, Hannaneh, Choi, Yejin, Ammanabrolu, Prithviraj
While Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with general, aggregate human preferences, it is suboptimal for learning diverse, individual perspectives. In this work, we study Reinforcement Learning from
Externí odkaz:
http://arxiv.org/abs/2310.11564
Autor:
Chaudhury, Subhajit, Swaminathan, Sarathkrishna, Kimura, Daiki, Sen, Prithviraj, Murugesan, Keerthiram, Uceda-Sosa, Rosario, Tatsubori, Michiaki, Fokoue, Achille, Kapanipathi, Pavan, Munawar, Asim, Gray, Alexander
Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games. On the other hand, neuro-symbolic
Externí odkaz:
http://arxiv.org/abs/2307.02689