activity
20222026
most citedTraining-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis

6 citations · 8 across the 5 of their papers we have counts for

collaborators

5 papers

cs.SD2026

From Textural Counterpoint to Feature Encoding: A Multi-Dimensional Machine Representation Study of Haydn's "The Lark" Integrating Electroacoustic Analysis

Yakun Liu, Zhiyu Jin, Hai Luan +2

Chamber music, as a highly precise multi-part interactive system, contains a logic of "role assignment and dynamic interaction" that provides an extremely valuable blueprint for ex…

cs.SD2026

LK Jam: System Architecture and Implementation of a Real-Time Human-AI Interactive Music Generation System using Role-Aware GRU

Yakun Liu, Zhiyu Jin, Dong Liu +1

As artificial intelligence advances into the era of Embodied AI, live musical interaction urgently needs to break free from the limitations of offline, unidirectional generation, a…

cs.SD2026

ChladniSonify: A Visual-Acoustic Mapping Method for Chladni Patterns in New Media Art Creation

Yakun Liu, Hai Luan, Dong Liu +1

In new media art creation, the mapping between vision and hearing is often subjective. As a classic carrier of sound visualization, Chladni patterns have great potential in buildin…

cs.CV2023★ 6 cited

Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis

Zhiyu Jin, Xuli Shen, Bin Li +1

Diffusion models (DMs) have recently gained attention with state-of-the-art performance in text-to-image synthesis. Abiding by the tradition in deep learning, DMs are trained and e…

cs.CV2022★ 2 cited

Style Spectroscope: Improve Interpretability and Controllability through Fourier Analysis

Zhiyu Jin, Xuli Shen, Bin Li +1

Universal style transfer (UST) infuses styles from arbitrary reference images into content images. Existing methods, while enjoying many practical successes, are unable of explaini…