3 papers
cs.CV2025
Prompt-Guided Dual Latent Steering for Inversion Problems
Yichen Wu, Xu Liu, Chenxuan Zhao +1
Inverting corrupted images into the latent space of diffusion models is challenging. Current methods, which encode an image into a single latent vector, struggle to balance structu…
cs.CV2025
Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation
Xu Liu, Yibo Lu, Xinxian Wang +1
We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of…
cs.CL2025
VoxRole: A Comprehensive Benchmark for Evaluating Speech-Based Role-Playing Agents
Weihao Wu, Liang Cao, Xinyu Wu +4
Recent significant advancements in Large Language Models (LLMs) have greatly propelled the development of Role-Playing Conversational Agents (RPCAs). These systems aim to create im…