Steering

Ask about this topic

Momentum

41 papers in the last four weeks, up 242% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 236

All topics
CardsList

  1. Steer-to-Detect: Probing Hidden Representations for Detection of LLM-Generated Texts

    May 13, 2026Luxu Liang, Xiang LiMachine-Generated Text DetectionLarge Language Model Hallucination

    Tsinghua University · University of Pennsylvania

  2. WriteSAE: Sparse Autoencoders for Recurrent State

    May 12, 2026Jack YoungRecurrent StateGated Deltanet

    Indiana University

  3. Steerable Neural ODEs on Homogeneous Spaces

    May 11, 2026Emma Andersdotter, Daniel Persson, Fredrik OhlssonNeural Ordinary Differential EquationsOrdinary Differential Equations

    Department of Mathematics and Mathematical Statistics Umeå University Umeå SE-901 87, Sweden · Department of Mathematical Sciences2026 Chalmers University of Technology and Gothenburg University Gothenburg SE-412 96, Sweden · Department of Mathematics and Mathematical Statistics 11 Umeå University Umeå SE-901 87, Sweden

  4. Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values

    May 11, 2026Haonan Dong, Qiguan Feng, Kehan Jiang +3Human ValuesValue

    State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · Key Laboratory of Machine Perception (Ministry of Education), Peking University · School of Software and Microelectronics, Peking University +1

  5. Exploitation Without Deception: Dark Triad Feature Steering Reveals Separable Antisocial Circuits in Language Models

    May 10, 2026Cameron Berg, Roshni LullaDeceptionLarge Language Model Bias

    1Reciprocal Research · 2Brain & Creativity Institute, University of Southern California

  6. SwordBench: Evaluating Orthogonality of Steering Image Representations

    May 10, 2026Vladimir Zaigrajew, Dawid Pludowski, Hubert Baniecki +1SteeringEvaluation Benchmarks

    Centre for Credible AI Warsaw University of Technology Warsaw, Poland · University of Warsaw Warsaw, Poland

  7. Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas

    May 9, 2026Nils A. Herrmann, Leander Girrbach, Kirill Bykov +1LLM Reasoning StrategiesArtificial Intelligence Personas

    1Technical University of Munich · 2Helmholtz Munich · 3Munich

  8. When Is Rank-1 Steering Cheap? Geometry, Granularity, and Budgeted Search

    May 9, 2026John T. Robertson, Jianing Zhu, Haris Vikalo +1Linear Activation SteeringSteering

    The University of Texas at Austin

  9. Can Revealed Preferences Clarify LLM Alignment and Steering?

    May 8, 2026Khurram Yamin, Jingjing Tang, Eric Horvitz +1Large Language Model AlignmentLarge Language Model Decisions

    1Carnegie Mellon University · 2Microsoft Research

  10. Steering Without Breaking: Mechanistically Informed Interventions for Discrete Diffusion Language Models

    May 8, 2026Hanhan Zhou, Shamik Roy, Rashmi GangadharaiahDiffusion Language ModelsSteering

    AWS AI Labs Santa Clara, CA 95054

  11. WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation

    May 8, 2026Zhichao Liu, Wenbo Pan, Haining Yu +3HijackingBrowser Agent

    Harbin Institute of Technology · City University of Hong Kong · City University of Macau

  12. Don't Lose Focus: Activation Steering via Key-Orthogonal Projections

    May 7, 2026Haoyan Luo, Mateo Espinosa Zarlenga, Mateja JamnikLinear Activation SteeringSteering

    University of Cambridge · University of Oxford

  13. Molecules Meet Language: Confound-Aware Representation Learning and Chemical Property Steering in Transformer-VAE Latent Spaces

    May 7, 2026Zakaria Elabid, Jan Andrzejewski, Bartosz Brzoza +1Molecular Representation LearningMolecular Generation

    Helmholtz-Zentrum Dresden-Rossendorf Center for Advanced Systems Understanding

  14. P-Guide: Parameter-Efficient Prior Steering for Single-Pass CFG Inference

    May 7, 2026Xin Peng, Ang GaoClassifier-Free GuidanceGenerative Flow Networks

    School of Physical Science and Technology, Beijing University of Posts and Telecommunications, Beijing, China

  15. Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions

    May 7, 2026Yuntai Bao, Qinfeng Li, Xinyan Yu +6SteeringSupervised Finetuning

    Zhejiang University · Innovation and Management Center, School of Software Technology (Ningbo), Zhejiang University · Ant Group

  16. Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention

    May 7, 2026Zehao Jin, Ruixuan Deng, Junran Wang +2Linear Activation SteeringSteering

    Georgia Institute of Technology

  17. Steering Visual Generation in Unified Multimodal Models with Understanding Supervision

    May 7, 2026Zeyu Liu, Zanlin Ni, Yang Yue +5Multimodal GenerationMultimodal Model

    1Tsinghua University · 2Kolors Team, Kuaishou Technology

  18. Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes

    May 7, 2026Ming LiuLarge Language Models FailDecoding

    Amazon

  19. Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior

    May 6, 2026Daniel Wurgaft, Can Rager, Matthew Kowal +13Neural Network RepresentationsLinear Activation Steering

    Stanford University · University College London · Northeastern University +2

  20. Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime

    May 6, 2026Tianshu Zhu, Wenyu Zhang, Xiaoying Zuo +8RolloutPass-Rate Evaluation

    Baidu

  21. Conceptors for Semantic Steering

    May 6, 2026Ilias Triantafyllopoulos, Young-Min Cho, Ren Tao +6Linear Activation SteeringSteering

    1New York University · University of Pennsylvania

  22. Steer Like the LLM: Activation Steering that Mimics Prompting

    May 5, 2026Geert Heyman, Frederik VandeputteLinear Activation SteeringInstruction-Tuned Models

    Nokia Bell Labs, Belgium.

  23. Pairwise matrices for sparse autoencoders: single-feature inspection mislabels causal axes

    May 4, 2026Michael A. Riegler, Birk Sebastian Frostelid Torpmann-HagenImproving Sparse AutoencodersModel Activations

    SimulaMet, Norway · Simula, Norway

  24. The Cylindrical Representation Hypothesis for Language Model Steering

    May 3, 2026Lang Gao, Jinghui Zhang, Wei Liu +7Linear Activation SteeringSteering

    Department of Natural Language Processing, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE · Department of Computer Science, National University of Singapore, Singapore

  25. Referring Multiple Regions with Large Multimodal Models via Contextual Latent Steering

    May 3, 2026Yun Xing, Hanyuan Liu, Jiahao Nie +1Large Multimodal ModelsRegion

    Nanyang Technological University

  26. Controlled Steering-Based State Preparation for Adversarial-Robust Quantum Machine Learning

    Apr 30, 2026Sahan Sanjaya, Hari Krishna Parvatham, Emma Andrews +1Quantum Machine LearningQuantum Error Correction

    University of Florida, Gainesville, FL, USA

  27. Investigating Linguistic Steering: An Analysis of Adjectival Effects Across Large Language Model Architectures

    Apr 28, 2026Lars MalmqvistLinguisticsFrozen Language Model

    Research and Implementation

  28. ASAP: An Azimuth-Priority Strip-Based Search Approach to Planar Microphone Array DOA Estimation in 3D

    Apr 28, 2026Ming Huang, Shuting Xu, Leying Yang +6Microphone ArraySteering

    Southern University of Science and Technology, Shenzhen, China · Institute of Science Tokyo, Japan

  29. UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems

    Apr 25, 2026Jingyu Zhang, Jacky Wai Keung, Yan Xiao +3Black-Box Adversarial AttacksSteering

    Department of Computer Science, City University of Hong Kong, Hong Kong SAR · School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China

  30. From Concept-Aligned Tokens to Vulnerable Features: Mechanistic Localization of Jailbreaks

    Apr 25, 2026Nilanjana Das, Mathew Dawit, Aman Chadha +1Jailbreak Success RatesUnsafe

    UMBC, Maryland, U.S.A. · Apple, California, U.S.A.

  31. Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization

    Apr 24, 2026Weixu Zhang, Ye Yuan, Changjiang Han +7Large Language Model PersonalizationPersonalization

    McGill University · Mila - Quebec AI Institute · MBZUAI +2

  32. From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models

    Apr 20, 2026Qidong Wang, Junjie Hu, Ming JiangRecent Vision-Language ModelsNeurons

    Tongji University · University of Wisconsin-Madison

  33. SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models

    Apr 18, 2026Yifu Huo, Chenglong Wang, Ziming Zhu +9LLM Reasoning StrategiesLarge Language Model Reinforcement Learning

    1Northeastern University, Shenyang, China · 2CAS Key Laboratory of Behavioral Science, Beijing, China · 3Independent Researcher, Beijing, China +1

  34. Structural Instability of Feature Composition

    Apr 18, 2026Yunpeng ZhouFeature LearningSteering

    Whiteknights House, Whiteknights, Reading, RG6 6UR

  35. RankGuide: Tensor-Rank-Guided Routing and Steering for Efficient Reasoning

    Apr 17, 2026Jiayi Tian, Yupeng Su, Ryan Solgi +2Reasoning BenchmarkInference Latency

    University of California, Santa Barbara · Intel Labs

  36. MidSteer: Optimal Affine Framework for Steering Generative Models

    Apr 17, 2026Tatiana Gaintseva, Andrew Stepanov, Ziquan Liu +4SteeringGenerative Models

    Queen Mary University of London, London, UK · Huawei Noah’s Ark, London, UK · QuantumLight Capital, London, UK +2

  37. Predicting Where Steering Vectors Succeed

    Apr 16, 2026Jayadev BillaLinear Activation SteeringSteering

  38. FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models

    Apr 16, 2026Zixuan Weng, Jinghuai Zhang, Kunlin Cai +3Inference-Time SteeringSteering

    University of California, Los Angeles

  39. What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal

    Apr 9, 2026Stephen Cheng, Sarah Wiegreffe, Dinesh ManochaLinear Activation SteeringSteering

    University of Maryland, College Park

  40. Persona Matters: Effects of Activation Steering on Short Answer Generation and Scoring

    Apr 8, 2026Yongchao Wu, Aron HenrikssonArtificial Intelligence PersonasPersona Consistency

    Stockholm University, NOD-huset, Borgarfjordsgatan 12, 16455 Stockholm, Sweden

  41. AViS-Mamba: Adaptive Visual Steering of Audio State-Space Dynamics for Violence Detection

    Apr 2, 2026Damith Chamalke Senadeera, Dimitrios Kollias, Gregory SlabaughAudio-Visual ReasoningFine-Grained Video Understanding

    Queen Mary University of London, UK · Digital Environment Research Institute (DERI), London, UK

  42. NOUS: Video-Driven 3D Human Reaction Generation via Observation-Reaction Mutual Steering

    Mar 20, 2026Yuan Zhou, Luanyuan Dai, Yongzhi Li +7SteeringComplementary Modalities

    College of Computing and Data Science, Nanyang Technological University, Singapore 639798 · School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China · School of Computer Science and Information Engineering (School of Artificial Intelligence), Hefei University of Technology, Hefei 230601, China +1

  43. From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions

    Mar 9, 2026Rishab Alagharu, Ishneet Sukhvinder Singh, Shaibi Shamsudeen +2RefusalsLarge Language Model Safety

    Algoverse AI Research · Carnegie Mellon University · University of Maryland

  44. Observing and Controlling Features in Vision-Language-Action Models

    Mar 5, 2026Hugo Buurmeijer, Carmen Amo Alonso, Aiden Swann +1Vision-Language-Action FrameworkEmbodied Artificial Intelligence

    Dept. of Aeronautics and Astronautics, Stanford University · Dept. of Mechanical Engineering, Stanford University · NVIDIA Research

  45. Watch the Model Think: On-Policy Extraction of Activation Steering Vectors

    Feb 15, 2026Xuanbo Su, Yingfang Zhang, Hao Luo +3Linear Activation SteeringReasoning Trajectory

    Bairong Inc., Beijing, China · School of Mathematics, Harbin Institute of Technology, Harbin, China

  46. Towards Understanding Steering Strength

    Feb 2, 2026Magamed Taimeskhanov, Samuel Vaiter, Damien GarreauSteeringFuture Latent Representations

    University of Würzburg, Center for Artificial Intelligence and Data Science · Universit´e Cˆote d’Azur - CNRS

  47. White-Box Sensitivity Auditing with Steering Vectors

    Jan 23, 2026Hannah Cyberey, Yangfeng Ji, David EvansModel AuditingLarge Language Model Evaluation

    University of Virginia

  48. Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering

    Oct 14, 2025Tsung-En Lin, Kuan-Yi Lee, Hung-Yi LeeLarge Audio Language ModelsSteering

    National Taiwan University, Taipei, Taiwan · ASUS Open Cloud Infrastructure Software Center, Taipei, Taiwan

  49. VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models

    Sep 29, 2025Ravikumar Balakrishnan, Mansi PhuteRecent Vision-Language ModelsSteering

    HiddenLayer, USA · Georgia Institute of Technology, USA

  50. EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering

    Sep 29, 2025Haolei Xu, Xinyu Mei, Yuchen Yan +5SteeringUnified Framework

    1Zhejiang University

  51. Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators

    Sep 3, 2025Dani Roytburg, Matthew Bozoukov, Matthew Nguyen +3Large Language Model BiasSteering

    School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 · Martian Research San Francisco, CA, 94105

  52. Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection

    Aug 28, 2025Harethah Abu Shairah, Hasan Abed Al Kader Hammoud, George Turkiyyah +1Safety AlignmentLarge Language Model Alignment

    King Abdullah University of Science and Technology (KAUST)

  53. VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models

    Aug 11, 2025Mansi Phute, Ravikumar BalakrishnanSteering

    Georgia Institute of Technology · HiddenLayer, Inc

  54. Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders

    Jul 31, 2025Carolina Zheng, Nicolas Beltran-Velez, Sweta Karlekar +5Topic ModelingSteering

    Columbia University · Independent · Google Research

  55. Exploring Context-aware and LLM-driven Locomotion for Immersive Virtual Reality

    Apr 24, 2025Suleyman Ozdel, Kadir Burak Buldu, Enkelejda Kasneci +1Virtual RealityLocomotion

    Human-Centered Technologies for Learning, Technical University of Munich, Germany · Munich Center for Machine Learning, Munich, Germany

  56. A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting

    Date pendingJunlin Li, Xinhao Song, Siqi Wang +2Text-To-Motion GenerationCross-Embodiment Retargeting

    ByteDance, San Jose, USA