Zobrazeno 1 - 10
of 2 024
pro vyhledávání: '"Miller Heather"'
Autor:
Szymanski, Annalisa, Ziems, Noah, Eicher-Miller, Heather A., Li, Toby Jia-Jun, Jiang, Meng, Metoyer, Ronald A.
The potential of using Large Language Models (LLMs) themselves to evaluate LLM outputs offers a promising method for assessing model performance across various contexts. Previous research indicates that LLM-as-a-judge exhibits a strong correlation wi
Externí odkaz:
http://arxiv.org/abs/2410.20266
LoRA and its variants have become popular parameter-efficient fine-tuning (PEFT) methods due to their ability to avoid excessive computational costs. However, an accuracy gap often exists between PEFT methods and full fine-tuning (FT), and this gap h
Externí odkaz:
http://arxiv.org/abs/2405.15525
Autor:
Huang, Yuning, Hassan, Mohamed Abul, He, Jiangpeng, Higgins, Janine, McCrory, Megan, Eicher-Miller, Heather, Thomas, Graham, Sazonov, Edward O, Zhu, Fengqing Maggie
Detecting an ingestion environment is an important aspect of monitoring dietary intake. It provides insightful information for dietary assessment. However, it is a challenging problem where human-based reviewing can be tedious, and algorithm-based re
Externí odkaz:
http://arxiv.org/abs/2405.07827
In microservice applications, ensuring resilience during database or service disruptions constitutes a significant challenge. While several tools address resilience testing for service failures, there is a notable gap in tools specifically designed f
Externí odkaz:
http://arxiv.org/abs/2404.01886
Autor:
Titzer, Ben L., Gilbert, Elizabeth, Teo, Bradley Wei Jie, Anand, Yash, Takayama, Kazuyuki, Miller, Heather
A key strength of managed runtimes over hardware is the ability to gain detailed insight into the dynamic execution of programs with instrumentation. Analyses such as code coverage, execution frequency, tracing, and debugging, are all made easier in
Externí odkaz:
http://arxiv.org/abs/2403.07973
Autor:
Khattab, Omar, Singhvi, Arnav, Maheshwari, Paridhi, Zhang, Zhiyuan, Santhanam, Keshav, Vardhamanan, Sri, Haq, Saiful, Sharma, Ashutosh, Joshi, Thomas T., Moazam, Hanna, Miller, Heather, Zaharia, Matei, Potts, Christopher
The ML community is rapidly exploring techniques for prompting language models (LMs) and for stacking them into pipelines that solve complex tasks. Unfortunately, existing LM pipelines are typically implemented using hard-coded "prompt templates", i.
Externí odkaz:
http://arxiv.org/abs/2310.03714
Deep learning based food recognition has achieved remarkable progress in predicting food types given an eating occasion image. However, there are two major obstacles that hinder deployment in real world scenario. First, as new foods appear sequential
Externí odkaz:
http://arxiv.org/abs/2307.00183
Conflict-free Replicated Data Types (CRDTs) allow collaborative access to an app's data. We describe a novel CRDT operation, for-each on the list of CRDTs, and demonstrate its use in collaborative apps. Our for-each operation applies a given mutation
Externí odkaz:
http://arxiv.org/abs/2304.03141