{"total":76,"rows":[{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237,"area":null},{"id":"2207.07605","title":"Algorithms to estimate Shapley value feature attributions","created":"2022-07-15","cited_by_count":115,"area":null},{"id":"2306.16842","title":"Tokenization and the Noiseless Channel","created":"2023-06-29","cited_by_count":59,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2102.09267","title":"Sparse-Interest Network for Sequential Recommendation","created":"2021-02-18","cited_by_count":38,"area":null},{"id":"2108.00702","title":"Improving Deep Learning for HAR with shallow LSTMs","created":"2021-08-02","cited_by_count":30,"area":null},{"id":"2308.07192","title":"gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling","created":"2023-08-14","cited_by_count":29,"area":null},{"id":"2108.08983","title":"SMedBERT: A Knowledge-Enhanced Pre-trained Language Model with Structured Semantics for Medical Text Mining","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2211.10844","title":"Learning to Generate Image Embeddings with User-level Differential Privacy","created":"2022-11-20","cited_by_count":23,"area":null},{"id":"2310.05317","title":"Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond","created":"2023-10-09","cited_by_count":23,"area":null},{"id":"2107.07076","title":"An Overview and Experimental Study of Learning-based Optimization Algorithms for Vehicle Routing Problem","created":"2021-07-15","cited_by_count":22,"area":null},{"id":"2109.07306","title":"Allocating Large Vocabulary Capacity for Cross-lingual Language Model Pre-training","created":"2021-09-15","cited_by_count":22,"area":null},{"id":"2407.11606","title":"The Foundations of Tokenization: Statistical and Computational Concerns","created":"2024-07-16","cited_by_count":22,"area":null},{"id":"2106.03044","title":"Emotion-aware Chat Machine: Automatic Emotional Response Generation for Human-like Emotional Interaction","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2101.09469","title":"Training Multilingual Pre-trained Language Model with Byte-level Subwords","created":"2021-01-23","cited_by_count":16,"area":null},{"id":"2102.09269","title":"Dynamic Memory based Attention Network for Sequential Recommendation","created":"2021-02-18","cited_by_count":16,"area":null},{"id":"2112.01047","title":"DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding","created":"2021-12-02","cited_by_count":15,"area":null},{"id":"2303.01980","title":"Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecycle","created":"2023-02-05","cited_by_count":14,"area":null},{"id":"2305.05480","title":"Effects of sub-word segmentation on performance of transformer language models","created":"2023-05-09","cited_by_count":12,"area":null},{"id":"2210.08536","title":"Knowledge Prompting in Pre-trained Language Model for Natural Language Understanding","created":"2022-10-16","cited_by_count":9,"area":null},{"id":"2306.07684","title":"Lookaround Optimizer: $k$ steps around, 1 step average","created":"2023-06-13","cited_by_count":9,"area":null},{"id":"2312.16483","title":"Expressivity and Approximation Properties of Deep Neural Networks with ReLU$^k$ Activation","created":"2023-12-27","cited_by_count":9,"area":null},{"id":"2109.05773","title":"Fast Variational AutoEncoder with Inverted Multi-Index for Collaborative Filtering","created":"2021-09-13","cited_by_count":8,"area":null},{"id":"2502.15054","title":"GiGL: Large-Scale Graph Neural Networks at Snapchat","created":"2025-02-20","cited_by_count":8,"area":null},{"id":"2101.11040","title":"A Comparison of Approaches to Document-level Machine Translation","created":"2021-01-26","cited_by_count":7,"area":null},{"id":"2210.00107","title":"Contrastive Corpus Attribution for Explaining Representations","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2306.06804","title":"Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction","created":"2023-06-11","cited_by_count":7,"area":null},{"id":"2107.12203","title":"Revisiting Negation in Neural Machine Translation","created":"2021-07-26","cited_by_count":6,"area":null},{"id":"2205.10666","title":"MultiBiSage: A Web-Scale Recommendation System Using Multiple Bipartite Graphs at Pinterest","created":"2022-05-21","cited_by_count":6,"area":null},{"id":"2211.08387","title":"AutoTemplate: A Simple Recipe for Lexically Constrained Text Generation","created":"2022-11-15","cited_by_count":6,"area":null},{"id":"2206.00794","title":"Sequential Bayesian Neural Subnetwork Ensembles","created":"2022-06-01","cited_by_count":5,"area":null},{"id":"2206.04730","title":"A Neural Network Architecture for Program Understanding Inspired by Human Behaviors","created":"2022-05-10","cited_by_count":5,"area":null},{"id":"2306.01393","title":"Assessing the Importance of Frequency versus Compositionality for Subword-based Tokenization in NMT","created":"2023-06-02","cited_by_count":5,"area":null},{"id":"2312.08520","title":"Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2103.08802","title":"Parareal Neural Networks Emulating a Parallel-in-time Algorithm","created":"2021-03-16","cited_by_count":4,"area":null},{"id":"2111.10208","title":"Attention based end to end Speech Recognition for Voice Search in Hindi and English","created":"2021-11-15","cited_by_count":4,"area":null},{"id":"2308.09201","title":"TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning","created":"2023-08-17","cited_by_count":4,"area":null},{"id":"2202.03645","title":"NxtPost: User to Post Recommendations in Facebook Groups","created":"2022-02-08","cited_by_count":3,"area":null},{"id":"2203.16868","title":"Memory-Efficient Training of RNN-Transducer with Sampled Softmax","created":"2022-03-31","cited_by_count":3,"area":null},{"id":"2204.09519","title":"A Survey on Neural Abstractive Summarization Methods and Factual Consistency of Summarization","created":"2022-04-20","cited_by_count":3,"area":null},{"id":"2205.06618","title":"The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine Translation","created":"2022-05-13","cited_by_count":3,"area":null},{"id":"2208.05225","title":"How Effective is Byte Pair Encoding for Out-Of-Vocabulary Words in Neural Machine Translation?","created":"2022-08-10","cited_by_count":3,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2203.04888","title":"Efficient Image Representation Learning with Federated Sampled Softmax","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2211.12281","title":"BESS: Balanced Entity Sampling and Sharing for Large-Scale Knowledge Graph Completion","created":"2022-11-22","cited_by_count":2,"area":null},{"id":"2304.05615","title":"Deep Stable Multi-Interest Learning for Out-of-distribution Sequential Recommendation","created":"2023-04-12","cited_by_count":2,"area":null},{"id":"2307.09989","title":"UniMatch: A Unified User-Item Matching Framework for the Multi-purpose Merchant Marketing","created":"2023-07-19","cited_by_count":2,"area":null},{"id":"2402.08023","title":"UGMAE: A Unified Framework for Graph Masked Autoencoders","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2505.10202","title":"VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2608.12026","title":"SoftWater: Class-Aware Rate Allocation for Softmax Quantization","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2109.10602","title":"Context-aware Tree-based Deep Model for Recommender Systems","created":"2021-09-22","cited_by_count":1,"area":null},{"id":"2210.00613","title":"The boundaries of meaning: a case study in neural machine translation","created":"2022-10-02","cited_by_count":1,"area":null},{"id":"2306.02563","title":"Large-Scale Distributed Learning via Private On-Device Locality-Sensitive Hashing","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2307.16400","title":"SelfSeg: A Self-supervised Sub-word Segmentation Method for Neural Machine Translation","created":"2023-07-31","cited_by_count":1,"area":null},{"id":"2409.06468","title":"An Effective Context-Balanced Adaptation Approach for Long-Tailed Speech Recognition","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2510.03425","title":"Memory-Efficient Backpropagation for Fine-Tuning LLMs on Resource-Constrained Mobile Devices","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2103.03108","title":"An empirical analysis of phrase-based and neural machine translation","created":"2021-03-04","cited_by_count":0,"area":null},{"id":"2108.09996","title":"MS-DARTS: Mean-Shift Based Differentiable Architecture Search","created":"2021-08-23","cited_by_count":0,"area":null},{"id":"2202.13616","title":"WSLRec: Weakly Supervised Learning for Neural Sequential Recommendation Models","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2207.00552","title":"Reduce Indonesian Vocabularies with an Indonesian Sub-word Separator","created":"2022-07-01","cited_by_count":0,"area":null},{"id":"2207.07910","title":"Improving Multi-Interest Network with Stable Learning","created":"2022-07-14","cited_by_count":0,"area":null},{"id":"2208.07643","title":"A Review of the Convergence of 5G/6G Architecture and Deep Learning","created":"2022-08-16","cited_by_count":0,"area":null},{"id":"2209.02390","title":"ProjB: An Improved Bilinear Biased ProjE model for Knowledge Graph Completion","created":"2022-08-15","cited_by_count":0,"area":null},{"id":"2305.18023","title":"Abstractive Summarization as Augmentation for Document-Level Event Detection","created":"2023-05-29","cited_by_count":0,"area":null},{"id":"2312.08517","title":"(Debiased) Contrastive Learning Loss for Recommendation (Technical Report)","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2403.05122","title":"Multi-Tower Multi-Interest Recommendation with User Representation Repel","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2406.01233","title":"Multi-word Term Embeddings Improve Lexical Product Retrieval","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2412.10182","title":"Multi-Head Encoding for Extreme Label Classification","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2508.03175","title":"Adaptive Sparse Softmax: An Effective and Efficient Softmax Variant","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2601.22745","title":"Is Softmax Loss All You Need? A Principled Analysis of Softmax-family Loss","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.14358","title":"High Precision Audience Expansion via Extreme Classification in a Two-Sided Marketplace","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2606.01172","title":"Revisiting Neural Processes via Fourier Transform and Volterra Series","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2607.27475","title":"OneShot: Index-in-Ranking with Neural Scoring for Large-Scale Retrieval","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.11061","title":"Batch Size or Negatives? A Selection Rule for Memory-Constrained Recommender Training","created":"2026-08-11","cited_by_count":0,"area":null}],"next_cursor":null}