Scholar

Jianyu Wei

Google Scholar ID: zJvjtRsAAAAJ

USTC & MSRA Joint PhD

LLM InfraInference SystemQuantizationKernelCo-design

Google Scholar↗

Citations & Impact

All-time

Citations

380

H-index

7

i10-index

6

Publications

9

Co-authors

0

Contact

No contact links provided.

Publications

9 items

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

Bitnet.cpp: Efficient Edge Inference for Ternary LLMs

2025

Cited

0

LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference

2024

Cited

0

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)