SR
Siddhant Ray
cs.LGcs.NIcs.AIcs.CLcs.IRcs.MAcs.OS
On Valency
published · living versionsW_472urbcs·v1 · currentpublished
FrontierCS 2: A Benchmark for Computer Science R&D
with Qiuyang Mang, Wenhao Chai, Runyuan He, Dongruixuan Li +56
1 version
Preprints & journals
10 papers in the corpus · 2022–2026FrontierCS 2: A Benchmark for Computer Science R&D2610.29932v1 · Qiuyang Mang, Wenhao Chai, Runyuan He et al.2026 · 0 citationsarXivon Valency
An Internet for the KV Cache: Rethinking Classical Infrastructure Boundaries in the LLM Inference Age2608.01526v1 · Siddhant Ray, Nick Feamster, Junchen Jiang2026 · 0 citationsarXiv
Argo: Efficient Importance Labeling for Enterprise Email Systems2605.21604v1 · Siddhant Ray, Ganesh Ananthanarayanan, Kevin Chian et al.2026 · 0 citationsarXiv
AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Serving2509.00105v2 · Shaoting Feng, Hanchen Li, Kuntai Du et al.2025 · 0 citationsarXiv
METIS: Fast Quality-Aware RAG Systems with Configuration Adaptation2412.10543v3 · Siddhant Ray, Rui Pan, Zhuohan Gu et al.2024 · 9 citationsarXiv
SwiftQueue: Optimizing Low-Latency Applications with Swift Packet Queuing2410.06112v2 · Siddhant Ray, Xi Jiang, Jack Luo et al.2024 · 1 citationarXiv
CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion2405.16444v3 · Jiayi Yao, Hanchen Li, Yuhan Liu et al.2024 · 76 citationsarXiv
Eloquent: A More Robust Transmission Scheme for LLM Token Streaming2401.12961v2 · Hanchen Li, Yuhan Liu, Yihua Cheng et al.2024 · 8 citationsarXiv
CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving2310.07240v6 · Yuhan Liu, Hanchen Li, Yihua Cheng et al.2023 · 117 citationsarXiv
A new hope for network model generalization2207.05843v2 · Alexander Dietmuller, Siddhant Ray, Romain Jacob et al.2022 · 21 citationsarXiv
Career total: 19 works. 10 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.