10 papers
SafeGene: Reusable Adapters for Transferable Safety Alignment
Yanghan Wang, Zhiqiang Kou, Fu Feng +2
Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts…
Constraint-based Pre-training: From Structured Constraints to Scalable Model Initialization
Fu Feng, Yucheng Xie, Ruixiao Shi +2
The pre-training and fine-tuning paradigm has become the dominant approach for model adaptation. However, conventional pre-training typically yields models at a fixed scale, wherea…
A Creative Agent is Worth a 64-Token Template
Ruixiao Shi, Fu Feng, Yucheng Xie +3
Text-to-image (T2I) models have substantially improved image fidelity and prompt adherence, yet their creativity remains constrained by reliance on discrete natural language prompt…
FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models
Yucheng Xie, Fu Feng, Ruixiao Shi +4
The training of diffusion models is computationally intensive, making effective pre-training essential. However, real-world deployments often demand models of variable sizes due to…
Self-Supervised Weight Templates for Scalable Vision Model Initialization
Yucheng Xie, Fu Feng, Ruixiao Shi +3
The increasing scale and complexity of modern model parameters underscore the importance of pre-trained models. However, deployment often demands architectures of varying sizes, ex…
Knowledge Diversion for Efficient Morphology Control and Policy Transfer
Fu Feng, Ruixiao Shi, Yucheng Xie +3
Universal morphology control aims to learn a universal policy that generalizes across heterogeneous agent morphologies, with Transformer-based controllers emerging as a popular cho…