Agora | Research Hub

Citations & Impact

All-time

Citations

5,347

H-index

34

i10-index

58

Publications

20

Co-authors

11

list available

Contact

Emailjunchenj@uchicago.edu CVOpen ↗GitHubOpen ↗LinkedInOpen ↗

Publications

17 items

The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project

2026

Cited

0

FleetOpt: Analytical Fleet Provisioning for LLM Inference with Compress-and-Route as Implementation Mechanism

2026

Cited

0

The 1/W Law: An Analytical Study of Context-Length Routing Topology and GPU Generation Gains for LLM Inference Energy Efficiency

2026

Cited

0

inference-fleet-sim: A Queueing-Theory-Grounded Fleet Capacity Planner for LLM Inference

2026

Cited

0

Outcome-Aware Tool Selection for Semantic Routers: Latency-Constrained Learning Without LLM Inference

2026

Cited

0

EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving

2025

Cited

0

When to Reason: Semantic Router for vLLM

2025

Cited

0

LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference

2025

Cited

0

Resume (English only)

Academic Achievements

Paper 'CacheBlend' awarded Best Paper at ACM EuroSys 2025
Recipient of the Google ML and Systems Junior Faculty Award (2025)
NSF CAREER Award (2022)
Best Paper and Best Paper Runner-up at ACM/IEEE Symposium on Edge Computing (SEC) in 2020 and 2021, respectively
Google Faculty Research Award (2019)
CMU SCS Doctoral Dissertation Award (2017) and nominee for ACM Doctoral Dissertation Award
Published multiple papers at top-tier systems conferences including NSDI, SOSP, EuroSys, and ASPLOS (e.g., 'LMPrefill' at SOSP 2025, 'METIS' at SOSP 2025, 'Earth+' at ASPLOS 2025)

Co-authors

11 total