Scholar

Xing Hu

Google Scholar ID: 43VmtLIAAAAJ

houmo.ai

Neural network compressionquantizationpruning

Google Scholar↗

Citations & Impact

All-time

Citations

109

H-index

5

i10-index

4

Publications

13

Co-authors

4

list available

Contact

No contact links provided.

Publications

5 items

TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization

2026

Cited

0

MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization

2026

Cited

0

TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization

2026

Cited

0

SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression

2026

Cited

0

NLI:Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference

2026

Cited

0

Resume (English only)

Co-authors

4 total

Southeast University