← Search

Xingyu Yu

2 accepted papers

2026

LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization

ICML 2026poster

Quantization-aware training (QAT) is essential for extremely low-bit large language models (LLMs). Current QAT methods are mainly based on scalar quantization (SQ), which enables efficient optimization but suffers from severe performance degradation at 2-bit precision. On the other hand, vector quan…

Cited by 0SourceScholar
2026

UniSVQ: 2-bit Unified Scalar-Vector Quantization

ICML 2026poster

Post-training quantization at the 2-bit level enables low-cost deployment and inference acceleration for large language models (LLMs). Scalar quantization (SQ) and vector quantization (VQ) are two primary quantization methods, however, the former suffers from significant performance degradation, and…

Cited by 0SourceScholar