Scholar
Jiangnan Yu
Google Scholar ID: msX1lXcAAAAJ
The Hong Kong University of Science and Technology
LLM acceleration
AI accelerator
Network on Chip
MoE
Emerging Non-Volatile-Memory
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
6
H-index
2
i10-index
0
Publications
3
Co-authors
2
list available
Publications
8 items
EfficientAgent: What Makes KV Cache Offloading Work for Concurrent Agents?
2026
Cited
0
TomasuLLM: Out-of-Order Speculative Execution for LLM Agents
2026
Cited
0
Memory Compression for High-Fanout Agent Sandboxes
2026
Cited
0
WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems
2026
Cited
0
STS: Efficient Sparse Attention with Speculative Token Sparsity
2026
Cited
0
DS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models
arXiv.org · 2026
Cited
0
A Memory-Efficient Retrieval Architecture for RAG-Enabled Wearable Medical LLMs-Agents
2025
Cited
0
DIRC-RAG: Accelerating Edge RAG with Robust High-Density and High-Loading-Bandwidth Digital In-ReRAM Computation
2025
Cited
0
Co-authors
1 total
Xiaoling Yi
MICAS - ESAT, KU Leuven, Belgium
