7 papers · 1 filter
When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities
Weiduo Liao, Yunqiao Yang, Ying Wei
Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes…
Enhancing Interpretability for Vision Models via Shapley Value Optimization
Kanglong Fan, Yunqiao Yang, Chen Ma
Deep neural networks have demonstrated remarkable performance across various domains, yet their decision-making processes remain opaque. Although many explanation methods are dedic…
Communication-Efficient Multi-Agent 3D Detection via Hybrid Collaboration
Yue Hu, Juntong Peng, Yunqiao Yang +1
Collaborative 3D detection can substantially boost detection performance by allowing agents to exchange complementary information. It inherently results in a fundamental trade-off…
Hiding Images in Diffusion Models by Editing Learned Score Functions
Haoyu Chen, Yunqiao Yang, Nan Zhong +1
Hiding data using neural networks (i.e., neural steganography) has achieved remarkable success across both discriminative classifiers and generative adversarial networks. However,…
Learning Where to Edit Vision Transformers
Yunqiao Yang, Long-Kai Huang, Shengzhuang Chen +2
Model editing aims to data-efficiently correct predictive errors of large pre-trained models while ensuring generalization to neighboring failures and locality to minimize unintend…
Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts
Shengzhuang Chen, Jihoon Tack, Yunqiao Yang +3
Recent successes suggest that parameter-efficient fine-tuning of foundation models as the state-of-the-art method for transfer learning in vision, replacing the rich literature of…