{"list":"other","total":59,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"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":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"1509.06321","title":"Evaluating the visualization of what a Deep Neural Network has learned","created":"2015-09-21","cited_by_count":419},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"1512.02479","title":"Explaining NonLinear Classification Decisions with Deep Taylor Decomposition","created":"2015-12-08","cited_by_count":250},{"id":"1604.00825","title":"Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers","created":"2016-04-04","cited_by_count":199},{"id":"1605.09304","title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","created":"2016-05-30","cited_by_count":181},{"id":"2305.14196","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","created":"2023-05-23","cited_by_count":176},{"id":"2202.06861","title":"Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond","created":"2022-02-14","cited_by_count":171},{"id":"1805.10820","title":"Local Rule-Based Explanations of Black Box Decision Systems","created":"2018-05-28","cited_by_count":166},{"id":"1702.08591","title":"The Shattered Gradients Problem: If resnets are the answer, then what is the question?","created":"2017-02-28","cited_by_count":157},{"id":"1704.01444","title":"Learning to Generate Reviews and Discovering Sentiment","created":"2017-04-05","cited_by_count":148},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148},{"id":"1807.08024","title":"Explaining Image Classifiers by Counterfactual Generation","created":"2018-07-20","cited_by_count":144},{"id":"2206.03208","title":"From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation","created":"2022-06-07","cited_by_count":141},{"id":"2003.07258","title":"Ground Truth Evaluation of Neural Network Explanations with CLEVR-XAI","created":"2020-03-16","cited_by_count":126},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88},{"id":"2010.10907","title":"Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation","created":"2020-10-21","cited_by_count":71},{"id":"2106.13200","title":"Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy","created":"2021-06-24","cited_by_count":55},{"id":"2102.10936","title":"Shapley values for feature selection: The good, the bad, and the axioms","created":"2021-02-22","cited_by_count":54},{"id":"2012.10425","title":"Towards Robust Explanations for Deep Neural Networks","created":"2020-12-18","cited_by_count":43},{"id":"2111.10493","title":"Discrete Representations Strengthen Vision Transformer Robustness","created":"2021-11-20","cited_by_count":35},{"id":"2312.05491","title":"Using Captum to Explain Generative Language Models","created":"2023-12-09","cited_by_count":33},{"id":"2301.08110","title":"AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation","created":"2023-01-19","cited_by_count":31},{"id":"2401.06654","title":"Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks","created":"2024-01-12","cited_by_count":28},{"id":"2211.17174","title":"Optimizing Explanations by Network Canonization and Hyperparameter Search","created":"2022-11-30","cited_by_count":11},{"id":"2303.01538","title":"Feature Perturbation Augmentation for Reliable Evaluation of Importance Estimators in Neural Networks","created":"2023-03-02","cited_by_count":9}],"next_cursor":null}