Dynamic head pruning in Vision Transformers (ViTs) improves efficiency by removing redundant attention heads, but existing pruning policies are often difficult to interpret and control. In this work, we propose a novel framework by integrating Sparse Autoencoders (SAEs) with dynamic pruning, leveraging their ability to disentangle dense embeddings into interpretable and controllable sparse latents. Specifically, we train an SAE on the final-layer residual embedding of the ViT and amplify the sparse latents with different strategies to alter pruning decisions. Among them, per-class steering reveals compact, class-specific head subsets that preserve accuracy. For example, bowl improves accuracy (76% to 82%) while reducing head usage (0.72 to 0.33) via heads h2 and h5. These results show that sparse latent features enable class-specific control of dynamic pruning, effectively bridging pruning efficiency and mechanistic interpretability in ViTs.
We introduce ADMM-pruned Compressive AutoEncoder (CAE-ADMM) that uses Alternative Direction Method of Multipliers (ADMM) to optimize the trade-off between distortion and efficiency of lossy image compression. Specifically, ADMM in our method is to promote sparsity to implicitly optimize the bitrate, different from entropy estimators used in the previous research. The experiments on public datasets show that our method outperforms the original CAE and some traditional codecs in terms of SSIM/MS-SSIM metrics, at reasonable inference speed.
D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders
Pivotal Research；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Schmidt Sciences（施密特科学）；Stanford University（斯坦福大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Spectral Complex Autoencoder Pruning: A Fidelity-Guided Criterion for Extreme Structured Channel Compression
School of Computer, Jiangsu University of Science and Technology（江苏科技大学计算机学院）；Department of Electrical and Computer Engineering, University of Nevada, Las Vegas（内华达大学拉斯维加斯分校电子与计算机工程系）
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University)（东南大学新一代人工智能技术及其交叉应用关键实验室）；Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所基础模型研究中心）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Wuhan University of Technology（武汉理工大学）；National University of Singapore（新加坡国立大学）
SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination
Department of Electrical and Computer Engineering, Seoul National University（电子与计算机工程系，首尔国立大学）；Daegu Gyeongbuk Institute of Science and Technology（大邱庆州科学技术院）；IPAI, AIIS, ASRI, INMC, and ISRC, Seoul National University（IPAI、AIIS、ASRI、INMC 和 ISRC，首尔国立大学）
Universal Boosts, Specific Suppressors: Sparse Autoencoder Steering of Medical Vision-Language Models
University of Zurich and University Hospital of Zurich（苏黎世大学及苏黎世大学医院）；Kobe University（Kobe大学）；ETH AI Center（苏黎世联邦理工学院人工智能中心）；ETH Zurich（苏黎世联邦理工学院）；Stanford University（斯坦福大学）；Zurich University of Applied Sciences（苏黎世应用科学大学）
