XY
Xianglong Yan
cs.AIcs.LGcs.CVcs.CL
On Valency
published · living versionsW_abjnt43j·v1 · currentpublished
ProQuant: Preserving Expert Quality over Quantity in Ultra-Low-Bit Quantization of Mixture-of-Experts Models
with Jiaqi Chen, Chengzhu Bao, Xie Chen, Yulun Zhang
1 version
Preprints & journals
13 papers in the corpus · 2024–2026HGA-Quant: Heterogeneity-Aware Quantization for AutoRegressive Visual Generation Models2610.15297v1 · Xinmeng Liu, Xianglong Yan, Kaicheng Yang et al.2026 · 0 citationsarXiv
SAGE: Pushing 2-Bit Vector-Quantized LLMs toward Real-World Usability2610.14745v1 · Xianglong Yan, Zenan Wu, Kewei Zhang et al.2026 · 0 citationsarXiv
RATIO: Reasoning Analysis and Token-level Inference Optimization for Quantized Reasoning Models2609.39801v1 · Chengzhu Bao, Xianglong Yan, Tianao Zhang et al.2026 · 0 citationsarXiv
JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization2609.33601v1 · Kaicheng Yang, Kaisen Yang, Chunyu Liu et al.2026 · 0 citationsarXiv
FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling2608.01847v1 · Xianglong Yan, Hong Liu, Chengzhu Bao et al.2026 · 0 citationsarXiv
SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization2605.12245v1 · Chengzhu Bao, Xianglong Yan, Zhiteng Li et al.2026 · 0 citationsarXiv
AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization2602.09883v1 · Shaoqiu Zhang, Zizhong Ding, Kaicheng Yang et al.2026 · 0 citationsarXiv
DQuant: Accurate Low-bit Post-Training Weight Quantization for LLMs2602.02546v2 · Xianglong Yan, ChengZhu Bao, Zhiteng Li et al.2026 · 0 citationsarXiv
RobuQ: Pushing DiTs to W1.58A2 via Robust Activation Quantization2509.23582v2 · Kaicheng Yang, Xun Zhang, Haotong Qin et al.2025 · 0 citationsarXiv
PT-LLM: Post-Training Ternarization for Large Language Models2510.03267v2 · Xianglong Yan, Chengzhu Bao, Zhiteng Li et al.2025 · 0 citationsarXiv
Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models2510.03274v1 · Tianao Zhang, Zhiteng Li, Xianglong Yan et al.2025 · 0 citationsarXiv
Progressive Binarization with Semi-Structured Pruning for LLMs2502.01705v4 · Xianglong Yan, Tianao Zhang, Zhiteng Li et al.2025 · 0 citationsarXiv
ARB-LLM: Alternating Refined Binarizations for Large Language Models2410.03129v3 · Zhiteng Li, Xianglong Yan, Tianao Zhang et al.2024 · 1 citationarXiv
Career total: 16 works. 13 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.