ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “activation steering”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.CRcs.CLMar 25, 2026

Analysing the Safety Pitfalls of Steering Vectors

Yuxiao Li, Alina Fastowski, Efstratios Zaradoukas, Bardh Prenkaj +1 more

This paper systematically audits the safety implications of activation steering vectors, finding that these vectors significantly influence the success rate of jailbreak attacks by overlapping with la…

View →
cs.LGcs.MAEmpiricalRecentJul 30, 2026

Policy Gradient Steering: Interventions from Behavioral Objectives

Yoann Poupart, Aurélie Beynier, Nicolas Maudet

This paper proposes Policy Gradient Steering (PGS), a new method for dynamically changing a large language model's behavior at inference time using reinforcement learning.

View →
cs.SDcs.AIcs.LGEmpiricalRecentJun 17, 2026

Closing the Loop: PID Feedback Control for Interpretable Activation Steering in Symbolic Music Generation

Ioannis Prokopiou, Pantelis Vikatos, Maximos Kaliakatsos-Papakostas, Theodoros Giannakopoulos +1 more

This paper proposes a framework for deterministic attribute modulation in transformer-based architectures.

View →
cs.CRcs.LGRecentMay 23, 2026

Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation

Luoyu Chen, Weiqi Wang, Zhiyi Tian, Chenhan Zhang +4 more

The paper proposes an unsupervised bi-level adversarial training framework to enhance LLM safety steering, achieving strong zero-shot defense against unseen and evolving jailbreak prompts.

View →
cs.CLRecentMay 28, 2026

Cross-Lingual Steering for Figurative Language Generation

Linfeng Liu, Tiffany Zhan, Louie Hong Yao, Saptarshi Ghosh +1 more

The paper demonstrates that the internal signals governing figurative language generation are reusable across multiple languages, showing that a steering direction learned in one language can effectiv…

View →
cs.CRApr 30, 2026

MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks

Jona te Lintelo, Lichao Wu, Marina Krček, Sengim Karayalçin +1 more

MASCing is a novel framework that enables flexible, non-retraining reconfiguration of Mixture-of-Experts (MoE) models for specific safety objectives by applying activation steering masks to control ex…

View →
cs.LGEmpiricalRecentJun 9, 2026

Predicting Future Behaviors in Reasoning Models Enables Better Steering

Evgenii Kortukov, Piotr Komorowski, Florian Klein, Paula Engl +4 more

This paper introduces a new method for controlling the behavior of large reasoning models with minimal output quality degradation.

View →
cs.SDcs.AIcs.IRRecentMay 29, 2026

Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation

Ioannis Prokopiou, Pantelis Vikatos, Maximos Kaliakatsos-Papakostas, Theodoros Giannakopoulos +1 more

The paper proposes an inference-time activation steering framework, utilizing orthogonalization, to achieve fine-grained, deterministic control over discrete musical attributes like Pitch and Duration…

View →
cs.CREmpiricalRecentOct 26, 2026

Steering for Safety, Hijacking for Profit: Trojan Threats in the LLM Activation Steering Supply Chain

Yu Yan, Jiahao Chen, Siqi Lu, Yongjuan Wang +3 more

This paper investigates security risks in Steering plugins for large language models and proposes a malicious plugin and a runtime defense framework to counter such threats.

View →
cs.AIRecentMay 28, 2026

Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers

Zihao Xue, Yan Wang, Zhen Bi, Long Ma +6 more

The paper proposes SafeDIG, a robust safety steering framework that adapts Diffusion Transformers for text-to-image generation by treating safety control as position-aware sparse feature transfer, ens…

View →
cs.CLcs.AIeess.ASEmpiricalRecentJun 9, 2026

Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering

Cheng-Kuang Chang, Kai-Wei Chang, Alexander H. Liu, James Glass

This paper analyzes the internal mechanism of full-duplex spoken language models and proposes a method to improve their ability to handle interruptions.

View →
cs.SDcs.AIeess.ASEmpiricalRecentJun 9, 2026

Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models

Tsung-En Lin, Hung-Yi Lee

This paper introduces instruction-based vector steering to redistribute attention in Large Audio-Language Models (LALMs) and demonstrates its effectiveness in recovering sound event locations.

View →
cs.CLcs.AIcs.LGRecentMay 29, 2026

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines

Mikkel Godsk Jørgensen, Lars Kai Hansen

This paper demonstrates that Sparse Autoencoders (SAEs) can effectively steer Large Language Models (LLMs) on the AxBench benchmark, achieving performance comparable to LoRA baselines when combined wi…

View →
cs.AIRecentMay 29, 2026

Closed-Loop Neural Activation Control in Vision-Language-Action Models

Abhijith Babu, Ramneet Kaur, Nathaniel D. Bastian, Olivera Kotevska +4 more

The paper proposes CTRL-STEER, a closed-loop framework that adaptively adjusts intervention strength to stabilize concept regulation and improve task success in Vision-Language-Action models without r…

View →
cs.CRcs.LGMay 19, 2026

Adaptive Probe-based Steering for Robust LLM Jailbreaking

Junxi Chen, Junhao Dong, Xiaohua Xie

The paper introduces an adaptive probe-based steering method that significantly improves the robustness and effectiveness of LLM jailbreaking without requiring extra prompts or manual tuning.

View →
cs.ROEmpiricalRecentJun 11, 2026

Improving Robotic Generalist Policies via Flow Reversal Steering

Andy Tang, William Chen, Andrew Wagenmaker, Chelsea Finn +1 more

This paper proposes a method called Flow Reversal Steering (FRS) to improve generalist policies in robots by inferring and invoking appropriate actions from their behavioral prior.

View →
cs.ROcs.HCcs.LGEmpiricalRecentOct 26, 2026

Dream to Assist: Intent-Conditioned World Models for Shared Vehicle Control

Jonathan DeCastro, Thomas Balch, Emily Sumner, Deepak Gopinath +8 more

The paper presents a model-based reinforcement learning framework for assistive agents in shared-control settings that addresses the challenges of proactive assistance and human legibility.

View →
cs.ROcs.AIEmpiricalRecentJun 9, 2026

Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving

Zehan Zhang, Neng Zhang, Yaoyi Li, Jia Cai +1 more

The paper proposes a diffusion-based planning framework called Diffusion Forcing Planner (DFP) to stabilize motion plans in autonomous driving.

View →
cs.CLcs.AIRecentMay 31, 2026

Low-Resource Safety Failures Are Action Failures, Not Representation Failures

Rashad Aziz, Ikhlasul Akmal Hanif, Fajri Koto

The paper shows that safety failures in low-resource languages are due to a failure in the model's safety decision calibration, not a lack of underlying knowledge, and proposes a recalibration method…

View →