Zukang Xu
5 papers · 2025–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
⭐
Rising Star
(5)
Top co-authors
Research topics
Keywords
post-training quantization
(3)
model compression
(3)
quantization
(2)
sparse activation
(1)
weight quantization
(1)
orthogonal transformation
(1)
large language model quantization
(1)
rotation method
(1)
distribution fitting
(1)
element-wise multiplication
(1)
low-bit activation
(1)
variance alignment
(1)
scaling transformation
(1)
mixture-of-experts
(1)
affinity guidance
(1)
expert-balanced sampling
(1)
codebook optimization
(1)
hybrid scalar vector
(1)
proxy-guided
(1)
uniformity assessment
(1)
Papers
BWLA: Breaking the Barrier of W1AX Post-Training Quantization for LLMs
ACL 2026
MambaQuant: Quantizing the Mamba Family with Variance Aligned Rotation Methods
ICLR 2025
MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance
ICML 2025
OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
ICLR 2025
RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization
ICML 2025