Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Rühle, Victor"'
Autor:
Zhang, Shaokun, Zhang, Jieyu, Ding, Dujian, Garcia, Mirian Hipolito, Mallick, Ankur, Madrigal, Daniel, Xia, Menglin, Rühle, Victor, Wu, Qingyun, Wang, Chi
Recent advancements have enabled Large Language Models (LLMs) to function as agents that can perform actions using external tools. This requires registering, i.e., integrating tool information into the LLM context prior to taking actions. Current met
Externí odkaz:
http://arxiv.org/abs/2411.01643
Autor:
Shandilya, Shivam, Xia, Menglin, Ghosh, Supriyo, Jiang, Huiqiang, Zhang, Jue, Wu, Qianhui, Rühle, Victor
The increasing prevalence of large language models (LLMs) such as GPT-4 in various applications has led to a surge in the size of prompts required for optimal performance, leading to challenges in computational efficiency. Prompt compression aims to
Externí odkaz:
http://arxiv.org/abs/2409.13035
Autor:
Jain, Kunal, Parayil, Anjaly, Mallick, Ankur, Choukse, Esha, Qin, Xiaoting, Zhang, Jue, Goiri, Íñigo, Wang, Rujia, Bansal, Chetan, Rühle, Victor, Kulkarni, Anoop, Kofsky, Steve, Rajmohan, Saravan
Large Language Model (LLM) workloads have distinct prefill and decode phases with different compute and memory requirements which should ideally be accounted for when scheduling input queries across different LLM instances in a cluster. However exist
Externí odkaz:
http://arxiv.org/abs/2408.13510
Transformer-based models have emerged as one of the most widely used architectures for natural language processing, natural language generation, and image generation. The size of the state-of-the-art models has increased steadily reaching billions of
Externí odkaz:
http://arxiv.org/abs/2405.10480
Autor:
Pan, Zhuoshi, Wu, Qianhui, Jiang, Huiqiang, Xia, Menglin, Luo, Xufang, Zhang, Jue, Lin, Qingwei, Rühle, Victor, Yang, Yuqing, Lin, Chin-Yew, Zhao, H. Vicky, Qiu, Lili, Zhang, Dongmei
This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. Considering the redundancy in natural language, existing approaches compress prompts by removing tokens or lexical units according to their information
Externí odkaz:
http://arxiv.org/abs/2403.12968
Autor:
Zanella-Béguelin, Santiago, Wutschitz, Lukas, Tople, Shruti, Salem, Ahmed, Rühle, Victor, Paverd, Andrew, Naseri, Mohammad, Köpf, Boris, Jones, Daniel
Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that such algorithms guarantee in theory and the protection they afford in pr
Externí odkaz:
http://arxiv.org/abs/2206.05199
Autor:
Mireshghallah, Fatemehsadat, Inan, Huseyin A., Hasegawa, Marcello, Rühle, Victor, Berg-Kirkpatrick, Taylor, Sim, Robert
Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy implications when training models on user content such as email correspondence. Differential privacy (DP), a popular choice t
Externí odkaz:
http://arxiv.org/abs/2103.07567
Autor:
Inan, Huseyin A., Ramadan, Osman, Wutschitz, Lukas, Jones, Daniel, Rühle, Victor, Withers, James, Sim, Robert
Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with the ability
Externí odkaz:
http://arxiv.org/abs/2101.05405
Autor:
Zanella-Béguelin, Santiago, Wutschitz, Lukas, Tople, Shruti, Rühle, Victor, Paverd, Andrew, Ohrimenko, Olga, Köpf, Boris, Brockschmidt, Marc
To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update can reveal
Externí odkaz:
http://arxiv.org/abs/1912.07942
Publikováno v:
Journal of Chemical Physics; 4/7/2010, Vol. 132 Issue 13, p134103, 9p, 1 Diagram, 3 Charts, 5 Graphs
