{"total":59,"rows":[{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206,"area":"mechinterp"},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159,"area":null},{"id":"2407.12404","title":"Analyzing the Generalization and Reliability of Steering Vectors","created":"2024-07-17","cited_by_count":143,"area":"mechinterp"},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49,"area":"mechinterp"},{"id":"2403.17064","title":"Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions","created":"2024-03-25","cited_by_count":41,"area":"diffusion"},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35,"area":"alignment"},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2510.09782","title":"The Geometry of Reasoning: Flowing Logics in Representation Space","created":"2025-10-10","cited_by_count":21,"area":"lr"},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2310.17611","title":"Uncovering Meanings of Embeddings via Partial Orthogonality","created":"2023-10-26","cited_by_count":15,"area":null},{"id":"2404.12488","title":"Global Counterfactual Directions","created":"2024-04-18","cited_by_count":15,"area":"diffusion"},{"id":"2502.04549","title":"Mechanisms of Projective Composition of Diffusion Models","created":"2025-02-06","cited_by_count":14,"area":"diffusion"},{"id":"2410.06303","title":"Compositional Risk Minimization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2505.18651","title":"On the Emergence of Linear Analogies in Word Embeddings","created":"2025-05-24","cited_by_count":13,"area":null},{"id":"2507.07102","title":"Does Data Scaling Lead to Visual Compositional Generalization?","created":"2025-07-09","cited_by_count":13,"area":null},{"id":"2506.07883","title":"Diffusion Counterfactual Generation with Semantic Abduction","created":"2025-06-09","cited_by_count":10,"area":"diffusion"},{"id":"2506.13298","title":"Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention","created":"2025-06-16","cited_by_count":9,"area":"diffusion"},{"id":"2409.07594","title":"Automated Discovery of Pairwise Interactions from Unstructured Data","created":"2024-09-11","cited_by_count":8,"area":null},{"id":"2502.09863","title":"Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models","created":"2025-02-14","cited_by_count":8,"area":null},{"id":"2505.15427","title":"Responsible Diffusion Models via Constraining Text Embeddings within Safe Regions","created":"2025-05-21","cited_by_count":8,"area":"diffusion"},{"id":"2510.22851","title":"Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models","created":"2025-10-26","cited_by_count":8,"area":"diffusion"},{"id":"2406.18534","title":"Towards Compositionality in Concept Learning","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2403.19837","title":"Concept-based Analysis of Neural Networks via Vision-Language Models","created":"2024-03-28","cited_by_count":6,"area":"mllm"},{"id":"2406.01300","title":"pOps: Photo-Inspired Diffusion Operators","created":"2024-06-03","cited_by_count":6,"area":"diffusion"},{"id":"2502.03429","title":"On Fairness of Unified Multimodal Large Language Model for Image Generation","created":"2025-02-05","cited_by_count":6,"area":"mllm"},{"id":"2507.13328","title":"Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It","created":"2025-07-17","cited_by_count":6,"area":null},{"id":"2311.16176","title":"Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles","created":"2023-11-23","cited_by_count":4,"area":null},{"id":"2411.04987","title":"Few-Shot Task Learning through Inverse Generative Modeling","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2504.02828","title":"Concept Lancet: Image Editing with Compositional Representation Transplant","created":"2025-04-03","cited_by_count":4,"area":"diffusion"},{"id":"2507.19894","title":"Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols","created":"2025-07-26","cited_by_count":4,"area":"safety"},{"id":"2503.17416","title":"Debugging and Runtime Analysis of Neural Networks with VLMs (A Case Study)","created":"2025-03-21","cited_by_count":3,"area":null},{"id":"2505.24023","title":"Multi-Group Proportional Representation for Text-to-Image Models","created":"2025-05-29","cited_by_count":3,"area":null},{"id":"2507.06547","title":"Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution","created":"2025-07-09","cited_by_count":3,"area":"diffusion"},{"id":"2512.03749","title":"Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models","created":"2025-12-03","cited_by_count":3,"area":"diffusion"},{"id":"2603.03163","title":"Conditioned Activation Transport for T2I Safety Steering","created":"2026-03-03","cited_by_count":3,"area":"mechinterp"},{"id":"2504.21307","title":"The Linear Geometry of Interpretable Tokens: Jailbreaking Attacks and Defenses for Unlearned Diffusion Models","created":"2025-04-30","cited_by_count":2,"area":"diffusion"},{"id":"2508.16989","title":"Unveiling the Latent Directions of Reflection in Large Language Models","created":"2025-08-23","cited_by_count":2,"area":"mechinterp"},{"id":"2511.13750","title":"SCALEX: Scalable Concept and Latent Exploration for Diffusion Models","created":"2025-11-13","cited_by_count":2,"area":"diffusion"},{"id":"2605.22596","title":"Factored Diffusion Policies:Compositionally Generalized Robot Control with a Single Score Network","created":"2026-05-21","cited_by_count":2,"area":"diffusion"},{"id":"2407.11002","title":"MoESD: Mixture of Experts Stable Diffusion to Mitigate Gender Bias","created":"2024-06-25","cited_by_count":1,"area":"diffusion"},{"id":"2410.21314","title":"Decoding Diffusion: A Scalable Framework for Unsupervised Analysis of Latent Space Biases and Representations Using Natural Language Prompts","created":"2024-10-25","cited_by_count":1,"area":"diffusion"},{"id":"2510.09790","title":"Mapping Semantic & Syntactic Relationships with Geometric Rotation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2512.15984","title":"Lifting Biomolecular Data Acquisition","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2601.21702","title":"Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities","created":"2026-01-29","cited_by_count":1,"area":"safety"},{"id":"2606.23920","title":"Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate","created":"2026-06-22","cited_by_count":1,"area":"diffusion"},{"id":"2403.06394","title":"FSViewFusion: Few-Shots View Generation of Novel Objects","created":"2024-03-11","cited_by_count":0,"area":"diffusion"},{"id":"2406.03582","title":"Understanding the Limitations of Diffusion Concept Algebra Through Food","created":"2024-06-05","cited_by_count":0,"area":"diffusion"},{"id":"2411.13867","title":"Generative Fuzzy System for Sequence Generation","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2412.13847","title":"A Concept-Centric Approach to Multi-Modality Learning","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2505.19313","title":"Concept Reachability in Diffusion Models: Beyond Dataset Constraints","created":"2025-05-25","cited_by_count":0,"area":"diffusion"},{"id":"2603.11795","title":"Intrinsic Concept Extraction Based on Compositional Interpretability","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.08846","title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2604.18167","title":"Embedding Arithmetic: A Lightweight, Tuning-Free Framework for Post-hoc Bias Mitigation in Text-to-Image Models","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.23861","title":"Leveraging Foundation Models for Causal Generative Modeling","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.14347","title":"When Language Representations Interact: Separability and Cross-Lingual Effects in LLMs","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.15656","title":"Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphs","created":"2026-04-21","cited_by_count":0,"area":null}],"next_cursor":null}