Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Junghwan Seo

dblp:380/6646 · DBLP profile ↗
← Back
1ranked-venue papers
0as first author
1since 2021 · last 2024
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Software engineering, systems software and programming languages · 1 · 1 since 2021

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Efficient and distributed learning · 87% Language models and text generation · 13%
Computer architecture, parallel and distributed computing, and storage systems
1 paper
Memory systems · 100%

Topics — the 4 heaviest of 4, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Machine learning › Efficient and distributed learning › inference efficiency
inference optimization
0.812024
InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management · OSDI 2024
Machine learning › Efficient and distributed learning
KV cache management
0.812024
InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management · OSDI 2024
Memory systems
cache management
0.812024
InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management · OSDI 2024
Natural language and speech › Language models and text generation
generative inference
0.212024
InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management · OSDI 2024

Methods — techniques the papers use, named apart from their topics

dynamic cache management · 1.5
YearPublicationVenuePosition
2024 InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management
Wonbeom Lee, Junghwan Seo, Jaewoong Sim
OSDI3