{"list":"other","total":56,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"2004.04696","title":"BLEURT: Learning Robust Metrics for Text Generation","created":"2020-04-09","cited_by_count":1203},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818},{"id":"1909.05207","title":"Introduction to Online Convex Optimization","created":"2019-09-07","cited_by_count":803},{"id":"1711.07846","title":"Functional Map of the World","created":"2017-11-21","cited_by_count":338},{"id":"2209.12356","title":"News Summarization and Evaluation in the Era of GPT-3","created":"2022-09-26","cited_by_count":327},{"id":"1804.11283","title":"Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies","created":"2018-04-30","cited_by_count":294},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1909.00889","title":"Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data","created":"2019-09-02","cited_by_count":246},{"id":"2003.06054","title":"Deep Domain-Adversarial Image Generation for Domain Generalisation","created":"2020-03-12","cited_by_count":231},{"id":"2102.01951","title":"Mind the Gap: Assessing Temporal Generalization in Neural Language Models","created":"2021-02-03","cited_by_count":230},{"id":"2201.00299","title":"Improving Out-of-Distribution Robustness via Selective Augmentation","created":"2022-01-02","cited_by_count":202},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190},{"id":"2006.06657","title":"Directional convergence and alignment in deep learning","created":"2020-06-11","cited_by_count":178},{"id":"2312.06795","title":"Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks","created":"2023-12-11","cited_by_count":133},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122},{"id":"1910.07454","title":"An Exponential Learning Rate Schedule for Deep Learning","created":"2019-10-16","cited_by_count":121},{"id":"1905.00075","title":"On the Use of ArXiv as a Dataset","created":"2019-04-30","cited_by_count":103},{"id":"2405.21015","title":"The rising costs of training frontier AI models","created":"2024-05-31","cited_by_count":95},{"id":"2403.19522","title":"Model Stock: All we need is just a few fine-tuned models","created":"2024-03-28","cited_by_count":92},{"id":"2405.14768","title":"WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models","created":"2024-05-23","cited_by_count":92},{"id":"2111.07408","title":"Time Waits for No One! Analysis and Challenges of Temporal Misalignment","created":"2021-11-14","cited_by_count":91},{"id":"2211.14238","title":"Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time","created":"2022-11-25","cited_by_count":90},{"id":"2010.12230","title":"Coping with Label Shift via Distributionally Robust Optimisation","created":"2020-10-23","cited_by_count":70},{"id":"2106.07171","title":"Examining and Combating Spurious Features under Distribution Shift","created":"2021-06-14","cited_by_count":65},{"id":"1511.02575","title":"A Century of Portraits: A Visual Historical Record of American High School Yearbooks","created":"2015-11-09","cited_by_count":54},{"id":"2209.11429","title":"News Category Dataset","created":"2022-09-23","cited_by_count":43},{"id":"2010.09697","title":"Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient Descent","created":"2020-10-19","cited_by_count":40},{"id":"2406.06811","title":"Learning Continually by Spectral Regularization","created":"2024-06-10","cited_by_count":34},{"id":"2205.10664","title":"Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks","created":"2022-05-21","cited_by_count":33},{"id":"2312.13401","title":"Time is Encoded in the Weights of Finetuned Language Models","created":"2023-12-20","cited_by_count":33},{"id":"1604.00400","title":"Revisiting Summarization Evaluation for Scientific Articles","created":"2016-04-01","cited_by_count":31},{"id":"2108.06721","title":"Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time","created":"2021-08-15","cited_by_count":28},{"id":"2405.08460","title":"Is Your LLM Outdated? A Deep Look at Temporal Generalization","created":"2024-05-14","cited_by_count":26},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23},{"id":"2411.08324","title":"Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle","created":"2024-11-13","cited_by_count":19},{"id":"2405.16075","title":"Continuous Temporal Domain Generalization","created":"2024-05-25","cited_by_count":15},{"id":"2403.09066","title":"Hyperparameters in Continual Learning: A Reality Check","created":"2024-03-14","cited_by_count":12},{"id":"2306.05641","title":"Toward Data Efficient Model Merging between Different Datasets without Performance Degradation","created":"2023-06-09","cited_by_count":2}],"next_cursor":null}