{"total":196,"rows":[{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435,"area":null},{"id":"2406.11944","title":"Transcoders Find Interpretable LLM Feature Circuits","created":"2024-06-17","cited_by_count":200,"area":"mechinterp"},{"id":"2411.16724","title":"Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens","created":"2024-11-23","cited_by_count":143,"area":"mllm"},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2410.07149","title":"Towards Interpreting Visual Information Processing in Vision-Language Models","created":"2024-10-09","cited_by_count":122,"area":"mllm"},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2407.12442","title":"ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference","created":"2024-07-17","cited_by_count":113,"area":"mllm"},{"id":"2410.02762","title":"Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations","created":"2024-10-03","cited_by_count":104,"area":"mllm"},{"id":"2405.08366","title":"Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control","created":"2024-05-14","cited_by_count":86,"area":"mechinterp"},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"area":"mllm"},{"id":"2403.10949","title":"SelfIE: Self-Interpretation of Large Language Model Embeddings","created":"2024-03-16","cited_by_count":67,"area":null},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62,"area":"mechinterp"},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2412.02104","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","created":"2024-12-03","cited_by_count":52,"area":"mllm"},{"id":"2502.04320","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","created":"2025-02-06","cited_by_count":52,"area":"diffusion"},{"id":"2412.08686","title":"LatentQA: Teaching LLMs to Decode Activations Into Natural Language","created":"2024-12-11","cited_by_count":51,"area":null},{"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":"2410.11842","title":"MoH: Multi-Head Attention as Mixture-of-Head Attention","created":"2024-10-15","cited_by_count":44,"area":"moe"},{"id":"2505.22654","title":"VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models","created":"2025-05-28","cited_by_count":41,"area":"lr"},{"id":"2402.17417","title":"CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification","created":"2024-02-27","cited_by_count":40,"area":null},{"id":"2406.08074","title":"A Concept-Based Explainability Framework for Large Multimodal Models","created":"2024-06-12","cited_by_count":39,"area":"mllm"},{"id":"2504.08729","title":"Steering CLIP's vision transformer with sparse autoencoders","created":"2025-04-11","cited_by_count":38,"area":"mechinterp"},{"id":"2406.04341","title":"Interpreting the Second-Order Effects of Neurons in CLIP","created":"2024-06-06","cited_by_count":36,"area":null},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35,"area":"mllm"},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2404.03214","title":"LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity","created":"2024-04-04","cited_by_count":33,"area":null},{"id":"2403.05846","title":"Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines","created":"2024-03-09","cited_by_count":30,"area":"diffusion"},{"id":"2406.11193","title":"MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model","created":"2024-06-17","cited_by_count":26,"area":"mllm"},{"id":"2506.11976","title":"How Visual Representations Map to Language Feature Space in Multimodal LLMs","created":"2025-06-13","cited_by_count":25,"area":"lr"},{"id":"2404.05729","title":"Finding Visual Task Vectors","created":"2024-04-08","cited_by_count":24,"area":null},{"id":"2406.10995","title":"Concept-skill Transferability-based Data Selection for Large Vision-Language Models","created":"2024-06-16","cited_by_count":24,"area":"mllm"},{"id":"2409.17143","title":"Attention Prompting on Image for Large Vision-Language Models","created":"2024-09-25","cited_by_count":23,"area":"mllm"},{"id":"2504.21447","title":"Multimodal Language Models See Better When They Look Shallower","created":"2025-04-30","cited_by_count":23,"area":"mllm"},{"id":"2504.19475","title":"Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video","created":"2025-04-28","cited_by_count":21,"area":"mechinterp"},{"id":"2406.01583","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2411.16198","title":"Interpreting Object-level Foundation Models via Visual Precision Search","created":"2024-11-25","cited_by_count":20,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2404.09941","title":"Evolving Interpretable Visual Classifiers with Large Language Models","created":"2024-04-15","cited_by_count":18,"area":null},{"id":"2410.08113","title":"Robust AI-Generated Text Detection by Restricted Embeddings","created":"2024-10-10","cited_by_count":18,"area":null},{"id":"2510.21518","title":"Head Pursuit: Probing Attention Specialization in Multimodal Transformers","created":"2025-10-24","cited_by_count":17,"area":"mllm"},{"id":"2411.00743","title":"Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models","created":"2024-11-01","cited_by_count":16,"area":"mechinterp"},{"id":"2412.18645","title":"Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings","created":"2024-12-24","cited_by_count":15,"area":null},{"id":"2510.04819","title":"Visual Representations inside the Language Model","created":"2025-10-06","cited_by_count":15,"area":"mllm"},{"id":"2511.22697","title":"Mechanistic Finetuning of Vision-Language-Action Models via Few-Shot Demonstrations","created":"2025-11-27","cited_by_count":15,"area":"mllm"},{"id":"2602.00462","title":"LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs","created":"2026-01-31","cited_by_count":15,"area":"mllm"},{"id":"2501.06751","title":"Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models","created":"2025-01-12","cited_by_count":13,"area":"diffusion"},{"id":"2510.21323","title":"VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set","created":"2025-10-24","cited_by_count":13,"area":"lr"},{"id":"2310.10591","title":"Interpreting and Controlling Vision Foundation Models via Text Explanations","created":"2023-10-16","cited_by_count":11,"area":null},{"id":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"area":null},{"id":"2411.10950","title":"Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering","created":"2024-11-17","cited_by_count":11,"area":"mllm"},{"id":"2507.17657","title":"Attention (as Discrete-Time Markov) Chains","created":"2025-07-23","cited_by_count":11,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2407.18999","title":"Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models","created":"2024-07-26","cited_by_count":10,"area":"mllm"},{"id":"2508.11277","title":"Probing the Representational Power of Sparse Autoencoders in Vision Models","created":"2025-08-15","cited_by_count":10,"area":"diffusion"},{"id":"2402.11816","title":"Learning the Unlearned: Mitigating Feature Suppression in Contrastive Learning","created":"2024-02-19","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2503.15234","title":"CoE: Chain-of-Explanation via Automatic Visual Concept Circuit Description and Polysemanticity Quantification","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2407.05578","title":"FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance","created":"2024-07-08","cited_by_count":8,"area":null},{"id":"2505.03500","title":"VLAs are Confined yet Capable of Generalizing to Novel Instructions","created":"2025-05-06","cited_by_count":8,"area":"vla"},{"id":"2509.14837","title":"V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models","created":"2025-09-18","cited_by_count":8,"area":"mllm"},{"id":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2411.12044","title":"ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements","created":"2024-11-18","cited_by_count":7,"area":"mllm"},{"id":"2412.18123","title":"AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models","created":"2024-12-24","cited_by_count":7,"area":null},{"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":"2504.12027","title":"Understanding Attention Mechanism in Video Diffusion Models","created":"2025-04-16","cited_by_count":7,"area":"diffusion"},{"id":"2505.20271","title":"In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation","created":"2025-05-26","cited_by_count":7,"area":"diffusion"},{"id":"2512.03276","title":"Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval","created":"2025-12-02","cited_by_count":7,"area":"mllm"},{"id":"2411.00132","title":"Beyond Accuracy: Ensuring Correct Predictions With Correct Rationales","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2411.00246","title":"ResiDual Transformer Alignment with Spectral Decomposition","created":"2024-10-31","cited_by_count":6,"area":null},{"id":"2505.20229","title":"From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance","created":"2025-05-26","cited_by_count":6,"area":"mechinterp"},{"id":"2506.10978","title":"Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models","created":"2025-06-12","cited_by_count":6,"area":"diffusion"},{"id":"2506.13831","title":"Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2508.05430","title":"Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions","created":"2025-08-07","cited_by_count":6,"area":"mllm"},{"id":"2509.20345","title":"General Synthetic-Powered Inference","created":"2025-09-24","cited_by_count":6,"area":null},{"id":"2510.07115","title":"Enhancing Concept Localization in CLIP-based Concept Bottleneck Models","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2312.11548","title":"Learning Interpretable Queries for Explainable Image Classification with Information Pursuit","created":"2023-12-16","cited_by_count":5,"area":null},{"id":"2406.18344","title":"AlignedCut: Visual Concepts Discovery on Brain-Guided Universal Feature Space","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2502.10450","title":"Trustworthy AI: Safety, Bias, and Privacy -- A Survey","created":"2025-02-11","cited_by_count":5,"area":"safety"},{"id":"2503.15699","title":"Representational Similarity via Interpretable Visual Concepts","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2504.05342","title":"MASS: MoErging through Adaptive Subspace Selection","created":"2025-04-06","cited_by_count":5,"area":null},{"id":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2505.15217","title":"Multimodal Conditional Information Bottleneck for Generalizable AI-Generated Image Detection","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2509.22518","title":"REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Model","created":"2025-09-26","cited_by_count":5,"area":"lr"},{"id":"2510.04564","title":"Conditional Representation Learning for Customized Tasks","created":"2025-10-06","cited_by_count":5,"area":null},{"id":"2512.08560","title":"BrainExplore: Large-Scale Discovery of Interpretable Visual Representations in the Human Brain","created":"2025-12-09","cited_by_count":5,"area":null},{"id":"2606.14703","title":"Gaze Heads: How VLMs Look at What They Describe","created":"2026-06-12","cited_by_count":5,"area":"mllm"},{"id":"2401.16459","title":"Bridging Generative and Discriminative Models for Unified Visual Perception with Diffusion Priors","created":"2024-01-29","cited_by_count":4,"area":"diffusion"},{"id":"2407.12161","title":"Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent","created":"2024-07-16","cited_by_count":4,"area":"agents"},{"id":"2409.17663","title":"Explanation Bottleneck Models","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2503.20301","title":"Attribute-formed Class-specific Concept Space: Endowing Language Bottleneck Model with Better Interpretability and Scalability","created":"2025-03-26","cited_by_count":4,"area":null},{"id":"2505.17425","title":"Debiasing CLIP: Interpreting and Correcting Bias in Attention Heads","created":"2025-05-23","cited_by_count":4,"area":null},{"id":"2506.00698","title":"Concept-Centric Token Interpretation for Vector-Quantized Generative Models","created":"2025-05-31","cited_by_count":4,"area":null},{"id":"2508.16652","title":"Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability","created":"2025-08-20","cited_by_count":4,"area":"mllm"},{"id":"2602.20423","title":"MedCLIPSeg: Probabilistic Vision-Language Adaptation for Data-Efficient and Generalizable Medical Image Segmentation","created":"2026-02-23","cited_by_count":4,"area":"mllm"},{"id":"2603.29676","title":"A Comprehensive Information-Decomposition Analysis of Large Vision-Language Models","created":"2026-03-31","cited_by_count":4,"area":"mllm"},{"id":"2404.02949","title":"The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2405.19146","title":"I Bet You Did Not Mean That: Testing Semantic Importance via Betting","created":"2024-05-29","cited_by_count":3,"area":null},{"id":"2406.09166","title":"Fine-Grained Domain Generalization with Feature Structuralization","created":"2024-06-13","cited_by_count":3,"area":null}],"next_cursor":"100"}