{"total":56,"rows":[{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2507.03724","title":"MemOS: A Memory OS for AI System","created":"2025-07-04","cited_by_count":138,"area":"rag"},{"id":"2510.26243","title":"Angular Steering: Behavior Control via Rotation in Activation Space","created":"2025-10-30","cited_by_count":53,"area":null},{"id":"2505.22637","title":"Understanding (Un)Reliability of Steering Vectors in Language Models","created":"2025-05-28","cited_by_count":47,"area":"mechinterp"},{"id":"2410.00153","title":"Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution","created":"2024-09-30","cited_by_count":27,"area":null},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24,"area":null},{"id":"2509.22067","title":"The Rogue Scalpel: Activation Steering Compromises LLM Safety","created":"2025-09-26","cited_by_count":21,"area":"safety"},{"id":"2405.15454","title":"LiSeCo: Linear Semantic Control for Language Generation","created":"2024-05-24","cited_by_count":20,"area":null},{"id":"2503.22048","title":"ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Models","created":"2025-03-27","cited_by_count":17,"area":"lr"},{"id":"2604.03147","title":"Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control","created":"2026-04-03","cited_by_count":16,"area":null},{"id":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2510.04309","title":"Activation Steering with a Feedback Controller","created":"2025-10-05","cited_by_count":15,"area":"alignment"},{"id":"2505.20925","title":"Multi-objective Large Language Model Alignment with Hierarchical Experts","created":"2025-05-27","cited_by_count":13,"area":"alignment"},{"id":"2406.11624","title":"Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2512.24143","title":"Activation Steering for Masked Diffusion Language Models","created":"2025-12-30","cited_by_count":9,"area":"diffusion"},{"id":"2602.02343","title":"Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics","created":"2026-02-02","cited_by_count":9,"area":null},{"id":"2505.12826","title":"Mitigating Hallucination in VideoLLMs via Temporal-Aware Activation Engineering","created":"2025-05-19","cited_by_count":8,"area":"mllm"},{"id":"2602.00333","title":"Efficient and accurate steering of Large Language Models through attention-guided feature learning","created":"2026-01-30","cited_by_count":8,"area":null},{"id":"2503.02989","title":"Effectively Steer LLM To Follow Preference via Building Confident Directions","created":"2025-03-04","cited_by_count":7,"area":"alignment"},{"id":"2601.22873","title":"EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis","created":"2026-01-30","cited_by_count":7,"area":"mechinterp"},{"id":"2602.04428","title":"Fine-Grained Activation Steering: Steering Less, Achieving More","created":"2026-02-04","cited_by_count":7,"area":"mechinterp"},{"id":"2602.07276","title":"Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs","created":"2026-02-07","cited_by_count":7,"area":"mechinterp"},{"id":"2503.17482","title":"What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models","created":"2025-03-21","cited_by_count":6,"area":null},{"id":"2510.12851","title":"Silence is Golden: Mitigating Hallucinations in Large Audio-Language Models via Layer-Weighted Vector Steering","created":"2025-10-14","cited_by_count":6,"area":null},{"id":"2601.21505","title":"The Effectiveness of Style Vectors for Steering Large Language Models: A Human Evaluation","created":"2026-01-29","cited_by_count":4,"area":"mechinterp"},{"id":"2505.16950","title":"Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning","created":"2025-05-22","cited_by_count":3,"area":"lr"},{"id":"2509.22510","title":"We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2510.03567","title":"Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs","created":"2025-10-03","cited_by_count":3,"area":"safety"},{"id":"2508.14076","title":"PersRM-R1: Enhance Personalized Reward Modeling with Reinforcement Learning","created":"2025-08-12","cited_by_count":2,"area":"alignment"},{"id":"2602.10437","title":"Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features","created":"2026-02-11","cited_by_count":2,"area":"mechinterp"},{"id":"2606.09850","title":"Mechanistic Analysis of Alignment Algorithms in Language Models","created":"2026-05-09","cited_by_count":2,"area":"alignment"},{"id":"2409.14206","title":"AI Assistants for Spaceflight Procedures: Combining Generative Pre-Trained Transformer and Retrieval-Augmented Generation on Knowledge Graphs With Augmented Reality Cues","created":"2024-09-21","cited_by_count":1,"area":null},{"id":"2505.22572","title":"Fusion Steering: Prompt-Specific Activation Control","created":"2025-05-28","cited_by_count":1,"area":"mechinterp"},{"id":"2506.19140","title":"Command-V: Pasting LLM Behaviors via Activation Profiles","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2509.25533","title":"VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models","created":"2025-09-29","cited_by_count":1,"area":"mllm"},{"id":"2510.24772","title":"Confidence is Not Competence","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2602.09784","title":"Circuit Fingerprints: How Answer Tokens Encode Their Geometrical Path","created":"2026-02-10","cited_by_count":1,"area":"mechinterp"},{"id":"2603.18893","title":"Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation","created":"2026-03-19","cited_by_count":1,"area":"mechinterp"},{"id":"2604.06377","title":"The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2606.11400","title":"Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language Models","created":"2026-06-09","cited_by_count":1,"area":"mechinterp"},{"id":"2607.20469","title":"DecodeShare: Tracing the Shared Subspace of LLM Decode-Time Decisions","created":"2026-05-21","cited_by_count":1,"area":"inference"},{"id":"2609.22135","title":"Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models","created":"2026-08-24","cited_by_count":1,"area":"mechinterp"},{"id":"2503.01553","title":"Co-creation for Sign Language Processing and Machine Translation","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2505.24292","title":"Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2508.08521","title":"VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models","created":"2025-08-11","cited_by_count":0,"area":"mllm"},{"id":"2602.06692","title":"Evaluating Prompt Engineering Strategies for Sentiment Control in AI-Generated Texts","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2602.19157","title":"Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs","created":"2026-02-22","cited_by_count":0,"area":"mechinterp"},{"id":"2607.17994","title":"HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization","created":"2026-07-20","cited_by_count":0,"area":"mllm"},{"id":"2607.18259","title":"Probabilistic Concept-Aware Steering for Trustworthy LLM Inference","created":"2026-05-15","cited_by_count":0,"area":"mechinterp"},{"id":"2608.06417","title":"Latent Fact-Checking: Detecting Misinformation through Activation Engineering","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.14797","title":"Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models","created":"2026-08-14","cited_by_count":0,"area":"mllm"},{"id":"2608.17102","title":"Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.20374","title":"VA-DPO: Valence-Arousal Direct Preference Optimization for Controllable Emotion Generation in Language Models","created":"2026-06-23","cited_by_count":0,"area":"alignment"},{"id":"2608.20393","title":"Knowledge-Graph-Gated Defactualization for Style-Controllable and Fact-Preserving Generation in Agentic Conversational AI","created":"2026-07-01","cited_by_count":0,"area":"agents"},{"id":"2608.29215","title":"Attribute-Based Activation Steering of LLMs for Group-Specific Explanation Generation","created":"2026-08-29","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"}],"next_cursor":null}