Scholar
Jianyu Wei
Google Scholar ID: zJvjtRsAAAAJ
USTC & MSRA Joint PhD
LLM Infra
Inference System
Quantization
Kernel
Co-design
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
380
H-index
7
i10-index
6
Publications
9
Co-authors
0
Publications
11 items
HySparse2: Hybrid Sparse Attention with Two-Level KV Sharing
2026
Cited
0
MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
2026
Cited
0
HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing
2026
Cited
0
MiMo-V2-Flash Technical Report
arXiv.org · 2026
Cited
11
Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices
2025
Cited
0
T-MAN: Enabling End-to-End Low-Bit LLM Inference on NPUs via Unified Table Lookup
2025
Cited
0
AdaNav: Adaptive Reasoning with Uncertainty for Vision-Language Navigation
2025
Cited
0
Scaling LLM Test-Time Compute with Mobile NPU on Smartphones
2025
Cited
0
Load more
