JY
Jiangnan Yu
cs.ARcs.CLcs.LGcs.OScs.AIcs.DCcs.SE
On Valency
published · living versionsW_432u5yk4·v1 · currentpublished
FlagRot: Selective Rotation for Low-Bit KV Caches
with Kunming Shao, Xijie Huang, Jierun Chen, Jiaqi Shao +5
1 version
Preprints & journals
8 papers in the corpus · 2025–2026EfficientAgent: What Makes KV Cache Offloading Work for Concurrent Agents?2609.33762v1 · Kunming Shao, Jierun Chen, Jiangnan Yu et al.2026 · 0 citationsarXiv
TomasuLLM: Out-of-Order Speculative Execution for LLM Agents2609.38201v2 · Jiangnan Yu, Ceyu Xu, Mengming Li et al.2026 · 0 citationsarXiv
Memory Compression for High-Fanout Agent Sandboxes2609.11294v1 · Mengming Li, Ceyu XU, Qijun Zhang et al.2026 · 0 citationsarXiv
WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems2605.24579v1 · Jiangnan Yu, Kisson Songqi Lin, Jilong Wu2026 · 0 citationsarXiv
STS: Efficient Sparse Attention with Speculative Token Sparsity2605.15508v3 · Jiangnan Yu, Ceyu Xu, Yongji Wu et al.2026 · 0 citationsarXiv
DS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models2601.06724v1 · Kunming Shao, Liang Zhao, Jiangnan Yu et al.2026 · 0 citationsarXiv
A Memory-Efficient Retrieval Architecture for RAG-Enabled Wearable Medical LLMs-Agents2510.27107v1 · Zhipeng Liao, Kunming Shao, Jiangnan Yu et al.2025 · 1 citationarXiv
DIRC-RAG: Accelerating Edge RAG with Robust High-Density and High-Loading-Bandwidth Digital In-ReRAM Computation2510.25278v1 · Kunming Shao, Zhipeng Liao, Jiangnan Yu et al.2025 · 2 citationsarXiv
Career total: 11 works. 8 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.