Scholar

Peisong Wang

Google Scholar ID: UYFZpk4AAAAJ

CASIA

Deep Neural Network Acceleration and Compression

Google Scholar↗

Citations & Impact

All-time

Citations

2,035

H-index

21

i10-index

32

Publications

20

Co-authors

4

list available

Publications

27 items

Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning

2026

Cited

0

You Only Need 2/3 of the Chosen Experts: An Empirical Study of Dynamic Expert Pruning in Fine-Grained MoE LLMs

2026

Cited

0

From Splats to Silicon: Rethinking Computational Efficiency of 3DGS

2026

Cited

0

$R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets

2026

Cited

0

BiSCo-LLM: Lookup-Free Binary Spherical Coding for Extreme Low-Bit Large Language Model Compression

2026

Cited

0

MODE: Modality-Decomposed Expert-Level Mixed-Precision Quantization for MoE Multimodal LLMs

2026

Cited

0

ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models

2026

Cited

0

Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation

2026

Cited

0

Co-authors

3 total

Institute of Automation, Chinese Academy of Sciences

Institute of Automation, Chinese Academy of Sciences

Beijing Jiaotong University