Zobrazeno 1 - 10
of 2 350
pro vyhledávání: '"Zaharia, P"'
Autor:
Biswal, Asim, Patel, Liana, Jha, Siddarth, Kamsetty, Amog, Liu, Shu, Gonzalez, Joseph E., Guestrin, Carlos, Zaharia, Matei
AI systems that serve natural language questions over databases promise to unlock tremendous value. Such systems would allow users to leverage the powerful reasoning and knowledge capabilities of language models (LMs) alongside the scalable computati
Externí odkaz:
http://arxiv.org/abs/2408.14717
Autor:
Davis, Jared Quincy, Hanin, Boris, Chen, Lingjiao, Bailis, Peter, Stoica, Ion, Zaharia, Matei
As practitioners seek to surpass the current reliability and quality frontier of monolithic models, Compound AI Systems consisting of many language model inference calls are increasingly employed. In this work, we construct systems, which we call Net
Externí odkaz:
http://arxiv.org/abs/2407.16831
The semantic capabilities of language models (LMs) have the potential to enable rich analytics and reasoning over vast knowledge corpora. Unfortunately, existing systems lack high-level abstractions to perform semantic queries at scale. We introduce
Externí odkaz:
http://arxiv.org/abs/2407.11418
Gesture is an important mean of non-verbal communication, with visual modality allows human to convey information during interaction, facilitating peoples and human-machine interactions. However, it is considered difficult to automatically recognise
Externí odkaz:
http://arxiv.org/abs/2406.12440
Autor:
Opsahl-Ong, Krista, Ryan, Michael J, Purtell, Josh, Broman, David, Potts, Christopher, Zaharia, Matei, Khattab, Omar
Language Model Programs, i.e. sophisticated pipelines of modular language model (LM) calls, are increasingly advancing NLP tasks, but they require crafting prompts that are jointly effective for all modules. We study prompt optimization for LM progra
Externí odkaz:
http://arxiv.org/abs/2406.11695
Autor:
Elmaaroufi, Karim, Shanker, Devan, Cismaru, Ana, Vazquez-Chanlatte, Marcell, Sangiovanni-Vincentelli, Alberto, Zaharia, Matei, Seshia, Sanjit A.
For cyber-physical systems (CPS), including robotics and autonomous vehicles, mass deployment has been hindered by fatal errors that occur when operating in rare events. To replicate rare events such as vehicle crashes, many companies have created lo
Externí odkaz:
http://arxiv.org/abs/2405.03709
Cyber security attacks have become increasingly complex over time, with various phases of their kill chain, involving binaries, scripts, documents, executed commands, vulnerabilities, or network traffic. We propose a tool, GView, that is designed to
Externí odkaz:
http://arxiv.org/abs/2404.09058
Autor:
Zhang, Tianjun, Patil, Shishir G., Jain, Naman, Shen, Sheng, Zaharia, Matei, Stoica, Ion, Gonzalez, Joseph E.
Pretraining Large Language Models (LLMs) on large corpora of textual data is now a standard paradigm. When using these LLMs for many downstream applications, it is common to additionally bake in new knowledge (e.g., time-critical news, or private dom
Externí odkaz:
http://arxiv.org/abs/2403.10131
Autor:
Liu, Shu, Biswal, Asim, Cheng, Audrey, Mo, Xiangxi, Cao, Shiyi, Gonzalez, Joseph E., Stoica, Ion, Zaharia, Matei
Analytical database providers (e.g., Redshift, Databricks, BigQuery) have rapidly added support for invoking Large Language Models (LLMs) through native user-defined functions (UDFs) to help users perform natural language tasks, such as classificatio
Externí odkaz:
http://arxiv.org/abs/2403.05821
Autor:
Santhanam, Keshav, Raghavan, Deepti, Rahman, Muhammad Shahir, Venkatesh, Thejas, Kunjal, Neha, Thaker, Pratiksha, Levis, Philip, Zaharia, Matei
We present ALTO, a network orchestrator for efficiently serving compound AI systems such as pipelines of language models. ALTO achieves high throughput and low latency by taking advantage of an optimization opportunity specific to generative language
Externí odkaz:
http://arxiv.org/abs/2403.04311