{"total":68,"rows":[{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46,"area":"mechinterp"},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2602.17560","title":"ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment","created":"2026-02-19","cited_by_count":19,"area":"alignment"},{"id":"2603.05487","title":"Observing and Controlling Features in Vision-Language-Action Models","created":"2026-03-05","cited_by_count":16,"area":"vla"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2503.10679","title":"LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss","created":"2025-03-11","cited_by_count":14,"area":"mechinterp"},{"id":"2503.01751","title":"SAKE: Steering Activations for Knowledge Editing","created":"2025-03-03","cited_by_count":13,"area":null},{"id":"2506.07891","title":"Video Unlearning via Low-Rank Refusal Vector","created":"2025-06-09","cited_by_count":13,"area":"safety"},{"id":"2502.15639","title":"Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language Models","created":"2025-02-21","cited_by_count":11,"area":null},{"id":"2604.19018","title":"Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control","created":"2026-04-21","cited_by_count":9,"area":"alignment"},{"id":"2510.26769","title":"SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models","created":"2025-10-30","cited_by_count":8,"area":"mllm"},{"id":"2603.06495","title":"COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics","created":"2026-03-06","cited_by_count":8,"area":"mechinterp"},{"id":"2501.19066","title":"Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations","created":"2025-01-31","cited_by_count":7,"area":"mechinterp"},{"id":"2602.12418","title":"Sparse Autoencoders are Capable LLM Jailbreak Mitigators","created":"2026-02-12","cited_by_count":6,"area":"safety"},{"id":"2603.02237","title":"Concept Heterogeneity-aware Representation Steering","created":"2026-02-13","cited_by_count":6,"area":"mechinterp"},{"id":"2605.05892","title":"Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention","created":"2026-05-07","cited_by_count":6,"area":"mechinterp"},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2509.16820","title":"DISCO: Disentangled Communication Steering for Large Language Models","created":"2025-09-20","cited_by_count":5,"area":"mechinterp"},{"id":"2603.13249","title":"Steering at the Source: Style Modulation Heads for Robust Persona Control","created":"2026-02-24","cited_by_count":5,"area":"mechinterp"},{"id":"2508.15094","title":"Evaluating Sparse Autoencoders for Monosemantic Representation","created":"2025-08-20","cited_by_count":4,"area":"mechinterp"},{"id":"2602.05539","title":"Steering Large Reasoning Models towards Concise Reasoning via Flow Matching","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2602.11910","title":"TADA! Tuning Audio Diffusion Models through Activation Steering","created":"2026-02-12","cited_by_count":4,"area":"diffusion"},{"id":"2507.08967","title":"Self-Improving Model Steering","created":"2025-07-11","cited_by_count":3,"area":"synth"},{"id":"2512.15926","title":"DSO: Direct Steering Optimization for Bias Mitigation","created":"2025-12-17","cited_by_count":3,"area":"mllm"},{"id":"2603.03163","title":"Conditioned Activation Transport for T2I Safety Steering","created":"2026-03-03","cited_by_count":3,"area":"mechinterp"},{"id":"2604.03867","title":"Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment","created":"2026-04-04","cited_by_count":3,"area":"alignment"},{"id":"2604.14602","title":"CausalDetox: Causal Head Selection and Intervention for Language Model Detoxification","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2605.06342","title":"Don't Lose Focus: Activation Steering via Key-Orthogonal Projections","created":"2026-05-07","cited_by_count":3,"area":"mechinterp"},{"id":"2606.04775","title":"Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control","created":"2026-06-03","cited_by_count":3,"area":"mechinterp"},{"id":"2606.08454","title":"Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior","created":"2026-06-07","cited_by_count":3,"area":"mechinterp"},{"id":"2607.00946","title":"A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models","created":"2026-07-01","cited_by_count":3,"area":"mechinterp"},{"id":"2607.14943","title":"Steering Robustness into World Action Models via Mechanistic Interpretability and Optimal Control","created":"2026-07-16","cited_by_count":3,"area":"wm"},{"id":"2601.05637","title":"GenCtrl -- A Formal Controllability Toolkit for Generative Models","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2601.22010","title":"Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering","created":"2026-01-29","cited_by_count":2,"area":"mechinterp"},{"id":"2602.10216","title":"ELROND: Exploring and decomposing intrinsic capabilities of diffusion models","created":"2026-02-10","cited_by_count":2,"area":"diffusion"},{"id":"2606.05290","title":"Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2607.10517","title":"Conditional Optimal Bridge for Riemannian Activation Steering","created":"2026-07-12","cited_by_count":2,"area":"mechinterp"},{"id":"2608.11735","title":"Locating and Controlling Implicit Personalization in Large Language Models","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2603.04355","title":"Efficient Refusal Ablation in LLM through Optimal Transport","created":"2026-03-04","cited_by_count":1,"area":"alignment"},{"id":"2604.09213","title":"SHIFT: Steering Hidden Intermediates in Flow Transformers","created":"2026-04-10","cited_by_count":1,"area":"diffusion"},{"id":"2606.12234","title":"On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2606.15092","title":"High-Dimensional Random Projection for Activation Steering in Language Models","created":"2026-06-13","cited_by_count":1,"area":"mechinterp"},{"id":"2607.14280","title":"DiMaS: Distribution Matching for Steering Vision-Language-Action Models","created":"2026-07-15","cited_by_count":1,"area":"vla"},{"id":"2608.12829","title":"Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers","created":"2026-08-13","cited_by_count":1,"area":"diffusion"},{"id":"2608.29458","title":"Reference-Grafting Matches Fine-Tuning at Eliciting Sandbagged Capabilities","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2608.29461","title":"A Causal Model for Locating and Unlocking Sandbagging in Model Organisms","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2609.01878","title":"GAPS: Dimension-Level Gates for Conditional Activation Steering","created":"2026-09-01","cited_by_count":1,"area":"mechinterp"},{"id":"2502.15090","title":"ExpertLens: Activation steering features are highly interpretable","created":"2025-02-20","cited_by_count":0,"area":"mechinterp"},{"id":"2508.17540","title":"Activation Transport Operators","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2605.08254","title":"HyperTransport: Amortized Conditioning of T2I Generative Models","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2606.08408","title":"TimpaTeks: Automatic In-place Text Sequence Modification via Diffusion Language Model Steering","created":"2026-06-07","cited_by_count":0,"area":"diffusion"},{"id":"2608.02957","title":"Inverted Detection and Control in Steering Vectors","created":"2026-08-03","cited_by_count":0,"area":"mechinterp"},{"id":"2609.10658","title":"GEOSTEER: Geodesic Optimization for Activation Steering in Large Language Models","created":"2026-09-09","cited_by_count":0,"area":"mechinterp"},{"id":"2609.10723","title":"AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow","created":"2026-09-09","cited_by_count":0,"area":"diffusion"},{"id":"2609.31122","title":"LocUS: Head Selection and Subspace Projection for Targeted Activation Steering","created":"2026-09-25","cited_by_count":0,"area":"mechinterp"},{"id":"2609.34771","title":"When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.36388","title":"Persona Dosing: Calibrated Activation Steering for Graded Trait Control","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"id":"2609.39573","title":"Steering Fields: Adaptive Vector Fields for Safe Image Generation and Beyond","created":"2026-09-30","cited_by_count":0,"area":"safety"},{"id":"2610.01062","title":"Kernelized Activation Steering","created":"2026-10-01","cited_by_count":0,"area":"mechinterp"},{"id":"2610.02391","title":"Hesitation Has a Geometry: Entropy-Trained Hyperbolic Probes for Sparse Activation Steering","created":"2026-10-01","cited_by_count":0,"area":"mechinterp"},{"id":"2610.04183","title":"Language Model Activations Inhabit Privileged Error-Correcting Basins","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.04283","title":"First-Order Steering: Translating Weight Adaptation into Activation Steering","created":"2026-10-03","cited_by_count":0,"area":"mechinterp"},{"id":"2610.04967","title":"One Token Can Be Enough: Bridging Prompting and Activation Steering with Prefix Steering","created":"2026-10-04","cited_by_count":0,"area":"mechinterp"},{"id":"2610.05894","title":"Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering","created":"2026-10-05","cited_by_count":0,"area":"diffusion"},{"id":"2610.06945","title":"Beyond the Linear Representation Hypothesis: Non-Linear Activation Steering in Text-to-Image Models","created":"2026-10-03","cited_by_count":0,"area":"mechinterp"},{"id":"2610.14025","title":"Contrastive Covariance Subspaces for Activation Steering","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"},{"id":"2610.16325","title":"When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19892","title":"On the Limits of Representation-Based Test-Time Adaptation for Multimodal LLMs","created":"2026-10-14","cited_by_count":0,"area":"mllm"}],"next_cursor":null}