Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Publication
Observer Effect in Social Media Use
Tool
Federated Learning under Distributed Concept Drift (FedDrift)
This repository is the source code for our paper: Federated Learning under Distributed Concept Drift (AISTATS’23) (opens in new tab).
Microsoft Research Blog
LLM profiling guides KV cache optimization
LLMs rely on memory-intensive mechanisms like the key-value (KV) cache to store and quickly retrieve data. FastGen optimizes KV cache usage, reducing LLM memory demands by up to 50% while maintaining performance.
Tool
NeMoEval: A Benchmark Tool for Natural Language-based Network Management
This is a benchmark tool to evaluate natural language-based network management using LLM-generated code.
Tool
Yatesbury: A Benchmark for East-West Network Security
This dataset serves as a benchmark for evaluting the performance and efficiency of anomaly detectors in east-west data center network traffic.
Microsoft Research Blog
LoftQ: Reimagining LLM fine-tuning with smarter initialization
LoftQ boosts LLM efficiency by streamlining the fine-tuning process, reducing computational demands while preserving high performance. Innovations like this can help make AI technology more energy-efficient.
