collaborators

9 papers

cs.LG2026

SPRI: SVD-Partitioned Residual Initialization for Data-Constrained MoE Upcycling

Weiqiao Shan, Ruixiang Mao, Yuang Li +10

Mixture-of-Experts (MoE) models enable efficient scaling, but training them from scratch remains prohibitively expensive. MoE upcycling mitigates this cost by converting pretrained…

cs.LG2026

Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation

Zhongzhu Zhou, Qingyang Wu, Junxiong Wang +4

Hybrid linear attention models offer an appealing path to faster long-context inference: they reduce the quadratic cost and KV-cache burden of full softmax attention while retainin…

cs.LG2026

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

Jiangyong Yu, Xiaomeng Han, Xing Hu +3

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks, but their deployment is often constrained by substantial memory footprints and c…

cs.CL2025

DLLMQuant: Quantizing Diffusion-based Large Language Models

Chen Xu, Dawei Yang

Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computat…

cs.CV2025

MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization

JiangYong Yu, Sifan Zhou, Dawei Yang +7

Multimodal large language models (MLLMs) have garnered widespread attention due to their ability to understand multimodal input. However, their large parameter sizes and substantia…

cs.LG2025

MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance

Xing Hu, Zhixuan Chen, Dawei Yang +5

Mixture-of-Experts (MoE) large language models (LLMs), which leverage dynamic routing and sparse activation to enhance efficiency and scalability, have achieved higher performance…