{"list":"other","total":57,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"1605.01713","title":"Not Just a Black Box: Learning Important Features Through Propagating Activation Differences","created":"2016-05-05","cited_by_count":297},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282},{"id":"2310.05916","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","created":"2023-10-09","cited_by_count":196},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179},{"id":"2007.06309","title":"Part-aware Prototype Network for Few-shot Semantic Segmentation","created":"2020-07-13","cited_by_count":162},{"id":"2409.14507","title":"A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders","created":"2024-09-22","cited_by_count":160},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147},{"id":"2201.11114","title":"Natural Language Descriptions of Deep Visual Features","created":"2022-01-26","cited_by_count":137},{"id":"2412.06410","title":"BatchTopK Sparse Autoencoders","created":"2024-12-09","cited_by_count":130},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119},{"id":"2501.16615","title":"Sparse Autoencoders Trained on the Same Data Learn Different Features","created":"2025-01-28","cited_by_count":93},{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91},{"id":"2206.14754","title":"Distilling Model Failures as Directions in Latent Space","created":"2022-06-29","cited_by_count":82},{"id":"2207.09615","title":"Overlooked factors in concept-based explanations: Dataset choice, concept learnability, and human capability","created":"2022-07-20","cited_by_count":46},{"id":"2005.02000","title":"On Interpretability of Deep Learning based Skin Lesion Classifiers using Concept Activation Vectors","created":"2020-05-05","cited_by_count":39},{"id":"2410.22366","title":"One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models","created":"2024-10-28","cited_by_count":33},{"id":"2311.13594","title":"Labeling Neural Representations with Inverse Recognition","created":"2023-11-22","cited_by_count":32},{"id":"2202.04178","title":"VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming","created":"2022-02-07","cited_by_count":31},{"id":"2209.07046","title":"Exploring Visual Interpretability for Contrastive Language-Image Pre-training","created":"2022-09-15","cited_by_count":30},{"id":"2410.03334","title":"An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation","created":"2024-10-04","cited_by_count":25},{"id":"2402.13914","title":"Position: Explain to Question not to Justify","created":"2024-02-21","cited_by_count":20},{"id":"2406.01583","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","created":"2024-06-03","cited_by_count":20},{"id":"2405.20331","title":"CoSy: Evaluating Textual Explanations of Neurons","created":"2024-05-30","cited_by_count":17},{"id":"2206.09753","title":"Visualizing and Understanding Contrastive Learning","created":"2022-06-20","cited_by_count":7},{"id":"2310.13040","title":"Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts","created":"2023-10-19","cited_by_count":6},{"id":"2406.18334","title":"Efficient and Accurate Explanation Estimation with Distribution Compression","created":"2024-06-26","cited_by_count":4}],"next_cursor":null}