Skip to content
conftrace_

model control

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

inference-time control (1) activation steering (1) trigger generation (1) sparse autoencoder (1) hallucination mitigation (1) vision-language model (1) language model (1) adversarial attack (1) backdoor attack (1) feature disentanglement (1)

Papers

SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models EMNLP 2025 Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control ICLR 2025 Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control IJCAI 2024