Mengzhao Chen

PhD student@University of Hong Kong·中国香港·OpenReview

研究方向

Model Quantization for Large Language Models · Network compression and acceleration · Dynamic Network · Network Architecture Design · Model Quantization

5.0

Scaling Law for Quantization-Aware Training

ICLR 2026Rejected

一作

4.0

Enhance-A-Video: Better Generated Video for Free

ICLR 2026Withdrawn

三作

2.5

HSA: Head-wise Sparse Attention for Efficient and Accurate Long-context Inference

ICLR 2026Withdrawn

-1

PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs

合作者 (20)

Mengzhao Chen

Scaling Law for Quantization-Aware Training

Enhance-A-Video: Better Generated Video for Free

HSA: Head-wise Sparse Attention for Efficient and Accurate Long-context Inference

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

Model Merging in Pre-training of Large Language Models

WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception

LLaMA Decoder As Vision Transformer

EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs