{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"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":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1609.07843","title":"Pointer Sentinel Mixture Models","created":"2016-09-26","cited_by_count":3096},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1606.06031","title":"The LAMBADA dataset: Word prediction requiring a broad discourse context","created":"2016-06-20","cited_by_count":992},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"1710.05381","title":"A systematic study of the class imbalance problem in convolutional neural networks","created":"2017-10-15","cited_by_count":513},{"id":"2103.03404","title":"Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth","created":"2021-03-05","cited_by_count":419},{"id":"2006.04884","title":"On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines","created":"2020-06-08","cited_by_count":255},{"id":"1708.08559","title":"DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars","created":"2017-08-28","cited_by_count":251},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126},{"id":"1910.11015","title":"Taxonomy of Real Faults in Deep Learning Systems","created":"2019-10-24","cited_by_count":90},{"id":"1805.05206","title":"DeepMutation: Mutation Testing of Deep Learning Systems","created":"2018-05-14","cited_by_count":67},{"id":"1906.01388","title":"A Comprehensive Study on Deep Learning Bug Characteristics","created":"2019-06-03","cited_by_count":65},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51},{"id":"2103.03376","title":"DeepLocalize: Fault Localization for Deep Neural Networks","created":"2021-03-04","cited_by_count":38},{"id":"1902.05974","title":"DeepFault: Fault Localization for Deep Neural Networks","created":"2019-02-15","cited_by_count":30},{"id":"2003.12236","title":"Piecewise linear activations substantially shape the loss surfaces of neural networks","created":"2020-03-27","cited_by_count":19},{"id":"2112.04036","title":"DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs","created":"2021-12-07","cited_by_count":19},{"id":"2205.01938","title":"DeepFD: Automated Fault Diagnosis and Localization for Deep Learning Programs","created":"2022-05-04","cited_by_count":16},{"id":"2410.11720","title":"ATTNChecker: Highly-Optimized Fault Tolerant Attention for Large Language Model Training","created":"2024-10-15","cited_by_count":12},{"id":"2312.09783","title":"Keep the Faith: Faithful Explanations in Convolutional Neural Networks for Case-Based Reasoning","created":"2023-12-15","cited_by_count":10},{"id":"2105.08095","title":"Automatic Fault Detection for Deep Learning Programs Using Graph Transformations","created":"2021-05-17","cited_by_count":9},{"id":"2409.13642","title":"A Multi-Agent Approach to Fault Localization via Graph-Based Retrieval and Reflexion","created":"2024-09-20","cited_by_count":9},{"id":"2405.12731","title":"From Today's Code to Tomorrow's Symphony: The AI Transformation of Developer's Routine by 2030","created":"2024-05-21","cited_by_count":8},{"id":"2504.02211","title":"FT-Transformer: Resilient and Reliable Transformer with End-to-End Fault Tolerant Attention","created":"2025-04-03","cited_by_count":8},{"id":"2303.01576","title":"DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction","created":"2023-03-02","cited_by_count":6},{"id":"2601.15232","title":"When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling","created":"2026-01-21","cited_by_count":6},{"id":"2301.05651","title":"Mutation Testing of Deep Reinforcement Learning Based on Real Faults","created":"2023-01-13","cited_by_count":4},{"id":"2411.08172","title":"Fault Localization in Deep Learning-based Software: A System-level Approach","created":"2024-11-12","cited_by_count":4},{"id":"2501.12560","title":"Improved Detection and Diagnosis of Faults in Deep Neural Networks Using Hierarchical and Explainable Classification","created":"2025-01-22","cited_by_count":3},{"id":"2502.13966","title":"Where's the Bug? Attention Probing for Scalable Fault Localization","created":"2025-02-19","cited_by_count":3},{"id":"2204.00694","title":"Testing Feedforward Neural Networks Training Programs","created":"2022-04-01","cited_by_count":2},{"id":"2307.08947","title":"An Effective Data-Driven Approach for Localizing Deep Learning Faults","created":"2023-07-18","cited_by_count":2},{"id":"2502.07712","title":"Mock Deep Testing: Toward Separate Development of Data and Models for Deep Learning","created":"2025-02-11","cited_by_count":1},{"id":"2601.21695","title":"AtPatch: Debugging Transformers via Hot-Fixing Over-Attention","created":"2026-01-29","cited_by_count":1}],"next_cursor":null}