Skip to content
conftrace_

activation manipulation

8 papers

Explore in graph

Also known as

ACTMAN

Co-occurring keywords · papers mentioning both

large language model (3) language model (3) adversarial attack (2) model reliability (1) image-level annotation (1) weakly supervised semantic segmentation (1) multilingual model (1) interpretability method (1) activation steering (1) steering method (1)

Papers

Activation Manipulation Attack: Penetrating and Harmful Jailbreak Attack Against Large Vision-Language Models AAAI 2026 Do Transformer Interpretability Methods Transfer to RNNs? AAAI 2025 Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation IJCNLP 2025 Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens ICLR 2025 Steering off Course: Reliability Challenges in Steering Language Models ACL 2025 Understanding the Repeat Curse in Large Language Models from a Feature Perspective ACL 2025 Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization NeurIPS 2024 Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholds CVPR 2022