12 papers
Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models
Boyang Guo, Liang Li, Lin Peng +3
Prompt learning has emerged as an efficient alternative to fine-tuning pre-trained vision-language models (VLMs). Despite its promise, current methods still struggle to maintain ta…
HAM: A Training-Free Style Transfer Approach via Heterogeneous Attention Modulation for Diffusion Models
Yeqi He, Liang Li, Zhiwen Yang +3
Diffusion models have demonstrated remarkable performance in image generation, particularly within the domain of style transfer. Prevailing style transfer approaches typically leve…
Few-Shot Generative Model Adaption via Identity Injection and Preservation
Yeqi He, Liang Li, Jiehua Zhang +4
Training generative models with limited data presents severe challenges of mode collapse. A common approach is to adapt a large pretrained generative model upon a target domain wit…
Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning
Jiong Yin, Liang Li, Jiehua Zhang +3
Audio-visual multi-task incremental learning aims to continuously learn from multiple audio-visual tasks without the need for joint training on all tasks. The challenge of the prob…
Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation
Peihua Deng, Jiehua Zhang, Xichun Sheng +4
This paper explores the Class-Incremental Source-Free Unsupervised Domain Adaptation (CI-SFUDA) problem, where the unlabeled target data come incrementally without access to labele…
Prosody-Enhanced Acoustic Pre-training and Acoustic-Disentangled Prosody Adapting for Movie Dubbing
Zhedong Zhang, Liang Li, Chenggang Yan +3
Movie dubbing describes the process of transforming a script into speech that aligns temporally and emotionally with a given movie clip while exemplifying the speaker's voice demon…