{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"1904.12848","title":"Unsupervised Data Augmentation for Consistency Training","created":"2019-04-29","cited_by_count":1060},{"id":"1710.08092","title":"VGGFace2: A dataset for recognising faces across pose and age","created":"2017-10-23","cited_by_count":914},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"1603.05279","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","created":"2016-03-16","cited_by_count":849},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1606.06160","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","created":"2016-06-20","cited_by_count":569},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"1707.07250","title":"Tensor Fusion Network for Multimodal Sentiment Analysis","created":"2017-07-23","cited_by_count":433},{"id":"1910.13580","title":"Domain Generalization via Model-Agnostic Learning of Semantic Features","created":"2019-10-29","cited_by_count":407},{"id":"1806.00064","title":"Efficient Low-rank Multimodal Fusion with Modality-Specific Factors","created":"2018-05-31","cited_by_count":270},{"id":"2011.09468","title":"Gradient Starvation: A Learning Proclivity in Neural Networks","created":"2020-11-18","cited_by_count":267},{"id":"2005.03545","title":"MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis","created":"2020-05-07","cited_by_count":265},{"id":"1902.00113","title":"Episodic Training for Domain Generalization","created":"2019-01-31","cited_by_count":245},{"id":"1606.06259","title":"MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos","created":"2016-06-20","cited_by_count":194},{"id":"2002.04692","title":"Invariant Risk Minimization Games","created":"2020-02-11","cited_by_count":188},{"id":"2203.12208","title":"Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection","created":"2022-03-23","cited_by_count":173},{"id":"1806.06176","title":"Learning Factorized Multimodal Representations","created":"2018-06-16","cited_by_count":171},{"id":"1802.00927","title":"Memory Fusion Network for Multi-view Sequential Learning","created":"2018-02-03","cited_by_count":168},{"id":"2002.03231","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","created":"2020-02-08","cited_by_count":151},{"id":"2008.12839","title":"Learning to Balance Specificity and Invariance for In and Out of Domain Generalization","created":"2020-08-28","cited_by_count":128},{"id":"2211.07089","title":"PMR: Prototypical Modal Rebalance for Multimodal Learning","created":"2022-11-14","cited_by_count":116},{"id":"1510.04373","title":"Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalization","created":"2015-10-15","cited_by_count":96},{"id":"1907.11216","title":"Domain Generalization via Multidomain Discriminant Analysis","created":"2019-07-25","cited_by_count":69},{"id":"2005.06870","title":"Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers","created":"2020-05-14","cited_by_count":68},{"id":"2210.00055","title":"MaskTune: Mitigating Spurious Correlations by Forcing to Explore","created":"2022-09-30","cited_by_count":66},{"id":"2105.12002","title":"Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization","created":"2021-05-25","cited_by_count":56},{"id":"2304.04494","title":"Improved Test-Time Adaptation for Domain Generalization","created":"2023-04-10","cited_by_count":47},{"id":"2106.11059","title":"Improving Multi-Modal Learning with Uni-Modal Teachers","created":"2021-06-21","cited_by_count":41},{"id":"2308.07092","title":"Masked Motion Predictors are Strong 3D Action Representation Learners","created":"2023-08-14","cited_by_count":41},{"id":"2203.13006","title":"Compound Domain Generalization via Meta-Knowledge Encoding","created":"2022-03-24","cited_by_count":40},{"id":"2205.09797","title":"Improving Multi-Task Generalization via Regularizing Spurious Correlation","created":"2022-05-19","cited_by_count":28},{"id":"1909.11366","title":"Accurate and Compact Convolutional Neural Networks with Trained Binarization","created":"2019-09-25","cited_by_count":20},{"id":"2210.07571","title":"Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization","created":"2022-10-14","cited_by_count":20},{"id":"2304.00429","title":"Information Recovery-Driven Deep Incomplete Multiview Clustering Network","created":"2023-04-02","cited_by_count":16},{"id":"2303.07123","title":"Modality-Agnostic Debiasing for Single Domain Generalization","created":"2023-03-13","cited_by_count":14},{"id":"2303.08358","title":"DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification","created":"2023-03-15","cited_by_count":13},{"id":"2306.07024","title":"DRCFS: Doubly Robust Causal Feature Selection","created":"2023-06-12","cited_by_count":12},{"id":"2303.01962","title":"Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery","created":"2023-03-02","cited_by_count":10},{"id":"2310.04724","title":"Activate and Reject: Towards Safe Domain Generalization under Category Shift","created":"2023-10-07","cited_by_count":9}],"next_cursor":null}