FeRA: Frequency-Energy Constrained Routing for Effective Diffusion Adaptation Fine-Tuning

Bo Yin, Xiaobin Hu, Xingyu Zhou, Peng-Tao Jiang, Yue Liao, Junwei Zhu, Jiangning Zhang, Ying Tai, Chengjie Wang, Shuicheng Yan

We present a novel fine-tuning approach for diffusion models, termed Frequency-Energy constrained Routing Adaptation (FeRA), which uses frequency-domain analysis to guide the fine-tuning process, enhancing both efficiency and effectiveness.

VPD-100K: Towards Generalizable and Fine-grained Visual Privacy Protection

Xiaobin Hu, Enpu Zuo, Lanping Hu, Kaiwen Yang, Dianshu Liao, Tianyi Zhang, Bo Yin, Yinsi Zhou, Shidong Pan, Xiaoyu Sun

We present VPD-100K, a large-scale fine-grained visual privacy dataset with 100,000 images, 33 classes, and over 190,000 object instances, together with a frequency-enhanced lightweight mechanism for robust privacy detection.

Dual Latent Memory for Visual Multi-agent System

Xinlei Yu, Chengming Xu, Zhangquan Chen, Bo Yin, Cheng Yang, Yongbo He, Yihao Hu, Jiangning Zhang, Cheng Tan, Xiaobin Hu, Shuicheng Yan

We introduce L²-VMAS, a model-agnostic framework that enables visual multi-agent collaboration through dual latent memories, improving scalability while reducing token-heavy text communication.

Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms

Qi Li^*, Bo Yin^*, Weiqi Huang^*, Ruhao Liu^*, Bojun Zou, Runpeng Yu, Jingwen Ye, Weihao Yu, Xinchao Wang

^* Equal contribution.

We survey VLA safety across threats, defenses, evaluation, and deployment, highlighting the unique risks introduced by embodied vision-language-action systems.

Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior

Bo Yin, Qi Li, Runpeng Yu, Xinchao Wang

We propose an instance-level auditing method that infers, from a model’s behavior, whether it was trained on an original prompt or an LLM-refined version of that prompt within a mixed training corpus.

Don’t Forget the Nonlinearity: Unlocking Activation Functions in Efficient Fine-Tuning

Bo Yin, Xingyi Yang, Xinchao Wang

We propose a novel and effective fine-tuning paradigm that introduces learnable activation functions to adapt large pre-trained models to downstream tasks while preserving their computational efficiency.

LacaDM: A Latent Causal Diffusion Model for Multiobjective Reinforcement Learning

Xueming Yan, Bo Yin, Yaochu Jin

We propose a novel multi-objective reinforcement learning framework that leverages latent temporal causal structures to enhance generalization and significantly outperform state-of-the-art baselines in complex dynamic environments.