{"total":36,"rows":[{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471,"area":null},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343,"area":null},{"id":"2304.07803","title":"EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation","created":"2023-04-16","cited_by_count":43,"area":null},{"id":"2105.08810","title":"Sparse Spiking Gradient Descent","created":"2021-05-18","cited_by_count":41,"area":null},{"id":"2108.02347","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","created":"2021-08-05","cited_by_count":26,"area":null},{"id":"2110.04367","title":"Hybrid Random Features","created":"2021-10-08","cited_by_count":25,"area":null},{"id":"2101.08769","title":"Item Recommendation from Implicit Feedback","created":"2021-01-21","cited_by_count":18,"area":null},{"id":"2302.03472","title":"On the Theories Behind Hard Negative Sampling for Recommendation","created":"2023-02-07","cited_by_count":18,"area":null},{"id":"2103.10891","title":"Accelerating SLIDE Deep Learning on Modern CPUs: Vectorization, Quantizations, Memory Optimizations, and More","created":"2021-03-06","cited_by_count":15,"area":null},{"id":"2110.07034","title":"How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies","created":"2021-10-13","cited_by_count":10,"area":null},{"id":"2105.05736","title":"Disentangling Sampling and Labeling Bias for Learning in Large-Output Spaces","created":"2021-05-12","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":"2310.10636","title":"Dual-Encoders for Extreme Multi-Label Classification","created":"2023-10-16","cited_by_count":7,"area":null},{"id":"2406.02847","title":"Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers","created":"2024-06-05","cited_by_count":7,"area":null},{"id":"2206.14649","title":"Cooperative Retriever and Ranker in Deep Recommenders","created":"2022-06-28","cited_by_count":6,"area":null},{"id":"2303.15311","title":"Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2208.00579","title":"Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization","created":"2022-08-01","cited_by_count":4,"area":null},{"id":"2105.02103","title":"Prototype Memory for Large-scale Face Representation Learning","created":"2021-05-05","cited_by_count":3,"area":null},{"id":"2208.03645","title":"Generating Negative Samples for Sequential Recommendation","created":"2022-08-07","cited_by_count":3,"area":null},{"id":"2306.01070","title":"Hierarchical Attention Encoder Decoder","created":"2023-06-01","cited_by_count":3,"area":null},{"id":"2512.00384","title":"Efficient and Programmable Exploration of Synthesizable Chemical Space","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2201.12667","title":"Distributed SLIDE: Enabling Training Large Neural Networks on Low Bandwidth and Simple CPU-Clusters via Model Parallelism and Sparsity","created":"2022-01-29","cited_by_count":2,"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":"2208.01709","title":"Adapting Triplet Importance of Implicit Feedback for Personalized Recommendation","created":"2022-08-02","cited_by_count":2,"area":null},{"id":"2303.17475","title":"Learning distributed representations with efficient SoftMax normalization","created":"2023-03-30","cited_by_count":2,"area":null},{"id":"2404.10575","title":"EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence","created":"2024-04-16","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2103.05638","title":"Beyond Nystr\\\"omformer -- Approximation of self-attention by Spectral Shifting","created":"2021-03-09","cited_by_count":1,"area":null},{"id":"2509.23742","title":"GBSK: Skeleton Clustering via Granular-ball Computing and Multi-Sampling for Large-Scale Data","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2105.04769","title":"Scalable Personalised Item Ranking through Parametric Density Estimation","created":"2021-05-11","cited_by_count":0,"area":null},{"id":"2204.08400","title":"Dynamic Network Adaptation at Inference","created":"2022-04-18","cited_by_count":0,"area":null},{"id":"2409.01890","title":"A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks","created":"2024-09-03","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":"2608.10260","title":"Interpreting Language Model Hidden States at Scale","created":"2026-08-10","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}