collaborators

8 papers

cs.LG2026

Learnable Permutation for Structured Sparsity on Transformer Models

Zekai Li, Ji Liu, Guanchen Li +5

Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language mod…

cs.CL2026

Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates

Yixing Xu, Chao Li, Xuanwu Yin +4

Low-rank adaptation (LoRA) is one of the most popular methods among parameter-efficient fine-tuning (PEFT) methods to adapt pre-trained large language models (LLMs) to specific dow…

cs.CL2025

Training-Free Loosely Speculative Decoding: Accepting Semantically Correct Drafts Beyond Exact Match

Jinze Li, Yixing Xu, Guanchen Li +6

Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive generation. Speculative Decoding (SP…

cs.CV2025

SpecVLM: Fast Speculative Decoding in Vision-Language Models

Haiduo Huang, Fuwei Yang, Zhenhua Liu +4

Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs), but directly porting it to vision-language models (VLMs) faces unique systems cons…

cs.CL2025

SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning

Huanxuan Liao, Yixing Xu, Shizhu He +6

Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention com…

cs.CL2025

Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding

Jinze Li, Yixing Xu, Haiduo Huang +4

Speculative decoding (SPD) aims to accelerate the auto-regressive token generation process of a target Large Language Model (LLM). Some approaches employ a draft model with multipl…