activity
20232026
most citedWiFi-Diffusion: Achieving Fine-Grained WiFi Radio Map Estimation With Ultra-Low Sampling Rate by Diffusion Models

22 citations · 23 across the 8 of their papers we have counts for

collaborators

8 papers

cs.SI2026

Multi-Granularity Position Embedding of Graphs via Granular-Ball for Link Prediction

Sen Zhao, Cheng Liu, Shuyin Xia +4

Link prediction aims to identify potential or future connections within a given graph structure. Position information is essential for link prediction, as it distinguishes homogene…

cond-mat.str-el2025

Symmetry-Projected Spin-AGP Methods Applied to Spin Systems

Zhiyuan Liu, Thomas M. Henderson, Gustavo E. Scuseria

Symmetry-projected wave function methods capture static correlation by breaking and restoring the symmetries of a system. In this article, we present the symmetry-projected spin an…

cs.LG2025

OThink-MR1: Stimulating multimodal generalized reasoning capabilities via dynamic reinforcement learning

Zhiyuan Liu, Yuting Zhang, Feng Liu +3

Multimodal Large Language Models (MLLMs) have gained significant traction for their ability to process diverse input data types and generate coherent, contextually relevant outputs…

eess.SP2025★ 22 cited

WiFi-Diffusion: Achieving Fine-Grained WiFi Radio Map Estimation With Ultra-Low Sampling Rate by Diffusion Models

Zhiyuan Liu, Shuhang Zhang, Qingyu Liu +2

Fine-grained radio map presents communication parameters of interest, e.g., received signal strength, at every point across a large geographical region. It can be leveraged to impr…

cs.LG2024

Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Training

Shuyin Xia, Xinjun Ma, Zhiyuan Liu +3

Graph Neural Networks (GNNs) have demonstrated significant achievements in processing graph data, yet scalability remains a substantial challenge. To address this, numerous graph c…

cs.CL2024

LLM-Oriented Retrieval Tuner

Si Sun, Hanqing Zhang, Zhiyuan Liu +2

Dense Retrieval (DR) is now considered as a promising tool to enhance the memorization capacity of Large Language Models (LLM) such as GPT3 and GPT-4 by incorporating external memo…

math.DS2023

A Remark on the Topology of the Regular Loci of Some Complexified Hamiltonian Systems

Zhiyuan Liu

We study the topology of the regular loci of two complexified Hamiltonian integrable systems using the Zariski-van Kampen method. In particular, we show that the fundamental group…

cs.CV2023★ 1 cited

Universal Photorealistic Style Transfer: A Lightweight and Adaptive Approach

Rong Liu, Enyu Zhao, Zhiyuan Liu +2

Photorealistic style transfer aims to apply stylization while preserving the realism and structure of input content. However, existing methods often encounter challenges such as co…