research
∙
08/17/2023
Accelerating Aggregation Queries on Unstructured Streams of Data
Analysts and scientists are interested in querying streams of video, aud...
share
research
∙
07/18/2023
How is ChatGPT's behavior changing over time?
GPT-3.5 and GPT-4 are the two most widely used large language model (LLM...
research
∙
05/09/2023
FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
There is a rapidly growing number of large language models (LLMs) that u...
research
∙
05/05/2023
Zelda: Video Analytics using Vision-Language Models
Advances in ML have motivated the design of video analytics systems that...
research
∙
02/11/2023
Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Recent advances in instruction-following large language models (LLMs) ha...
research
∙
12/29/2022
Transactions Make Debugging Easy
We propose TROD, a novel transaction-oriented framework for debugging mo...
research
∙
12/28/2022
Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP
Retrieval-augmented in-context learning has emerged as a powerful approa...
research
∙
12/02/2022
Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking
Neural information retrieval (IR) systems have progressed rapidly in rec...
research
∙
11/29/2022
MegaBlocks: Efficient Sparse Training with Mixture-of-Experts
We present MegaBlocks, a system for efficient Mixture-of-Experts (MoE) t...
research
∙
09/18/2022
HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions
Commercial ML APIs offered by providers such as Google, Amazon and Micro...
research
∙
09/18/2022
Estimating and Explaining Model Performance When Both Covariates and Labels Shift
Deployed machine learning (ML) models often encounter new user data that...
research
∙
08/27/2022
Apiary: A DBMS-Backed Transactional Function-as-a-Service Framework
Developers are increasingly using function-as-a-service (FaaS) platforms...
research
∙
05/19/2022
PLAID: An Efficient Engine for Late Interaction Retrieval
Pre-trained language models are increasingly important components across...
research
∙
04/28/2022
Extricating IoT Devices from Vendor Infrastructure with Karl
Most consumer IoT devices are vertically integrated with cloud-side infr...
research
∙
01/15/2022
Finding Label and Model Errors in Perception Data With Learned Observation Assertions
ML is being deployed in complex, real-world scenarios where errors have ...
research
∙
12/13/2021
What can Data-Centric AI Learn from Data and ML Engineering?
Data-centric AI is a new and exciting research topic in the AI community...
research
∙
12/02/2021
ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
Neural information retrieval (IR) has greatly advanced search and other ...
research
∙
11/19/2021
Toward Compact Parameter Representations for Architecture-Agnostic Neural Network Compression
This paper investigates deep neural network (DNN) compression from the p...
research
∙
11/09/2021
DistIR: An Intermediate Representation and Simulator for Efficient Neural Network Distribution
The rapidly growing size of deep neural network (DNN) models and dataset...
research
∙
10/22/2021
Solving Large-Scale Granular Resource Allocation Problems Efficiently with POP
Resource allocation problems in many computer systems can be formulated ...
research
∙
10/14/2021
Hindsight: Posterior-guided training of retrievers for improved open-ended generation
Many text generation systems benefit from using a retriever to retrieve ...
research
∙
07/29/2021
Did the Model Change? Efficiently Assessing Machine Learning API Shifts
Machine learning (ML) prediction APIs are increasingly widely used. An M...
research
∙
04/13/2021
Don't Give Up on Large Optimization Problems; POP Them!
Resource allocation problems in many computer systems can be formulated ...
research
∙
04/09/2021
Efficient Large-Scale Language Model Training on GPU Clusters
Large language models have led to state-of-the-art accuracies across a r...
research
∙
04/01/2021
Allocation of Fungible Resources via a Fast, Scalable Price Discovery Method
We consider the problem of assigning or allocating resources to a set of...
research
∙
02/18/2021
FrugalMCT: Efficient Online ML API Selection for Multi-Label Classification Tasks
Multi-label classification tasks such as OCR and multi-object recognitio...
research
∙
01/02/2021
Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrieval
Multi-hop reasoning (i.e., reasoning across two or more documents) at sc...
research
∙
09/09/2020
Task-agnostic Indexes for Deep Learning-based Queries over Unstructured Data
Unstructured data is now commonly queried by using target deep neural ne...
research
∙
08/20/2020
Heterogeneity-Aware Cluster Scheduling Policies for Deep Learning Workloads
Specialized accelerators such as GPUs, TPUs, FPGAs, and custom ASICs hav...
research
∙
07/25/2020
Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics
While deep neural networks (DNNs) are an increasingly popular way to que...
research
∙
07/21/2020
DBOS: A Proposal for a Data-Centric Operating System
Current operating systems are complex systems that were designed before ...
research
∙
07/01/2020
Relevance-guided Supervision for OpenQA with ColBERT
Systems for Open-Domain Question Answering (OpenQA) generally depend on ...
research
∙
06/30/2020
Similarity Search for Efficient Active Learning and Search of Rare Concepts
Many active learning and search approaches are intractable for industria...
research
∙
06/22/2020
Overlook: Differentially Private Exploratory Visualization for Big Data
Data exploration systems that provide differential privacy must manage a...
research
∙
06/18/2020
Sparse GPU Kernels for Deep Learning
Scientific workloads have traditionally exploited high levels of sparsit...
research
∙
06/16/2020
Memory-Efficient Pipeline-Parallel DNN Training
Many state-of-the-art results in domains such as NLP and computer vision...
research
∙
06/12/2020
FrugalML: How to Use ML Prediction APIs More Accurately and Cheaply
Prediction APIs offered for a fee are a fast-growing industry and an imp...
research
∙
04/27/2020
ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
Recent progress in Natural Language Understanding (NLU) is driving fast-...
research
∙
04/02/2020
Approximate Selection with Guarantees using Proxies
Due to the falling costs of data acquisition and storage, researchers an...
research
∙
03/03/2020
Model Assertions for Monitoring and Improving ML Model
ML models are increasingly deployed in settings with real world interact...
research
∙
03/03/2020
Model Assertions for Monitoring and Improving ML Models
ML models are increasingly deployed in settings with real world interact...
research
∙
11/20/2019
Express: Lowering the Cost of Metadata-hiding Communication with Cryptographic Privacy
Existing systems for metadata-hiding messaging that provide cryptographi...
research
∙
10/02/2019
MLPerf Training Benchmark
Machine learning is experiencing an explosion of software and hardware s...
research
∙
09/21/2019
Automated Lower Bounds on the I/O Complexity of Computation Graphs
We consider the problem of finding lower bounds on the I/O complexity of...
research
∙
06/26/2019
Selection Via Proxy: Efficient Data Selection For Deep Learning
Data selection methods such as active learning and core-set selection ar...
research
∙
06/03/2019
Willump: A Statistically-Aware End-to-end Optimizer for Machine Learning Inference
Machine learning (ML) has become increasingly important and performance-...
research
∙
03/29/2019
SysML: The New Frontier of Machine Learning Systems
Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
research
∙
10/29/2018
Splitability Annotations: Optimizing Black-Box Function Composition in Existing Libraries
Data movement is a major bottleneck in parallel data-intensive applicati...
research
∙
10/02/2018
LIT: Block-wise Intermediate Representation Training for Model Compression
Knowledge distillation (KD) is a popular method for reducing the computa...
research
∙
07/14/2018