collaborators

9 papers

cs.CL2025

Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation

Shiwei Li, Xiandi Luo, Haozhao Wang +6

Low-rank adaptation (LoRA) is a parameter-efficient fine-tuning (PEFT) method widely used in large language models (LLMs). LoRA essentially describes the projection of an input spa…

cs.LG2025

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics

Shiwei Li, Xiandi Luo, Xing Tang +6

Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method. In standard LoRA layers, one of the matrices, or , is initialized to zero, ensuring that…

cs.LG2025

The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning

Shiwei Li, Xiandi Luo, Haozhao Wang +6

To improve the training efficiency of federated learning (FL), previous research has employed low-rank decomposition techniques to reduce communication overhead. In this paper, we…

cs.LG2025

BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity

Shiwei Li, Xiandi Luo, Haozhao Wang +6

Low-rank adaptation (LoRA) is a parameter-efficient fine-tuning (PEFT) method widely used in large language models (LLMs). It approximates the update of a pretrained weight matrix…

cs.IR2025

A Systematic Survey on Federated Sequential Recommendation

Yichen Li, Qiyu Qin, Gaoyang Zhu +5

Sequential recommendation is an advanced recommendation technique that utilizes the sequence of user behaviors to generate personalized suggestions by modeling the temporal depende…

cs.CL2025

Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models

You Li, Heyu Huang, Chi Chen +8

The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multip…