Zobrazeno 1 - 10
of 78
pro vyhledávání: '"Jermaine, Chris"'
Autor:
Bourgeois, Daniel, Ding, Zhimin, Jankov, Dimitrije, Li, Jiehui, Sleem, Mahmoud, Tang, Yuxin, Yao, Jiawen, Yao, Xinyu, Jermaine, Chris
We consider the problem of automatically decomposing operations over tensors or arrays so that they can be executed in parallel on multiple devices. We address two, closely-linked questions. First, what programming abstraction should systems for tens
Externí odkaz:
http://arxiv.org/abs/2410.02682
Large language models (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as LLM-based agents)
Externí odkaz:
http://arxiv.org/abs/2409.12294
Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require storing multiple task-specific adapters, creating scalability issues as th
Externí odkaz:
http://arxiv.org/abs/2405.15282
We carefully evaluate a number of algorithms for learning in a federated environment, and test their utility for a variety of image classification tasks. We consider many issues that have not been adequately considered before: whether learning over d
Externí odkaz:
http://arxiv.org/abs/2309.03237
Autor:
Tang, Yuxin, Ding, Zhimin, Jankov, Dimitrije, Yuan, Binhang, Bourgeois, Daniel, Jermaine, Chris
The relational data model was designed to facilitate large-scale data management and analytics. We consider the problem of how to differentiate computations expressed relationally. We show experimentally that a relational engine running an auto-diffe
Externí odkaz:
http://arxiv.org/abs/2306.00088
Large Language Models (LLMs) pre-trained on code have recently emerged as the dominant approach to program synthesis. However, these models are trained using next-token prediction, which ignores the syntax and semantics of code. We propose RLCF, that
Externí odkaz:
http://arxiv.org/abs/2305.18341
Recent work on the Lottery Ticket Hypothesis (LTH) shows that there exist ``\textit{winning tickets}'' in large neural networks. These tickets represent ``sparse'' versions of the full model that can be trained independently to achieve comparable acc
Externí odkaz:
http://arxiv.org/abs/2210.16169
Asynchronous learning protocols have regained attention lately, especially in the Federated Learning (FL) setup, where slower clients can severely impede the learning process. Herein, we propose \texttt{AsyncDrop}, a novel asynchronous FL framework t
Externí odkaz:
http://arxiv.org/abs/2210.16105
Autor:
Mukherjee, Rohan, Wen, Yeming, Chaudhari, Dipak, Reps, Thomas W., Chaudhuri, Swarat, Jermaine, Chris
State-of-the-art neural models of source code tend to be evaluated on the generation of individual expressions and lines of code, and commonly fail on long-horizon tasks such as the generation of entire method bodies. We propose to address this defic
Externí odkaz:
http://arxiv.org/abs/2111.01633
Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification. We take this hypothesis to its logical conclusion, and suggest the use of an ensemble of high-quality, pre-train
Externí odkaz:
http://arxiv.org/abs/2101.00562