{"total":18,"rows":[{"id":"2303.06053","title":"TSMixer: An All-MLP Architecture for Time Series Forecasting","created":"2023-03-10","cited_by_count":240,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2205.12585","title":"TAGPRIME: A Unified Framework for Relational Structure Extraction","created":"2022-05-25","cited_by_count":15,"area":null},{"id":"2203.03691","title":"HyperMixer: An MLP-based Low Cost Alternative to Transformers","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2405.15618","title":"MLPs Learn In-Context on Regression and Classification Tasks","created":"2024-05-24","cited_by_count":13,"area":null},{"id":"2209.06383","title":"Analysis of Quantization on MLP-based Vision Models","created":"2022-09-14","cited_by_count":5,"area":null},{"id":"2307.01482","title":"Contextualizing MLP-Mixers Spatiotemporally for Urban Data Forecast at Scale","created":"2023-07-04","cited_by_count":3,"area":null},{"id":"2407.09790","title":"Team up GBDTs and DNNs: Advancing Efficient and Effective Tabular Prediction with Tree-hybrid MLPs","created":"2024-07-13","cited_by_count":3,"area":null},{"id":"2606.04032","title":"Do Transformers Need Three Projections? Systematic Study of QKV Variants","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2409.01482","title":"Masked Mixers for Language Generation and Retrieval","created":"2024-09-02","cited_by_count":2,"area":null},{"id":"2412.13607","title":"PreMixer: MLP-Based Pre-training Enhanced MLP-Mixers for Large-scale Traffic Forecasting","created":"2024-12-18","cited_by_count":2,"area":null},{"id":"2510.11602","title":"Deconstructing Attention: Investigating Design Principles for Effective Language Modeling","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2210.13118","title":"Unsupervised Term Extraction for Highly Technical Domains","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2512.07854","title":"HieraMix: A Hierarchical MLP-Mixer for Large-Scale Traffic Forecasting","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2310.09512","title":"Attentive Multi-Layer Perceptron for Non-autoregressive Generation","created":"2023-10-14","cited_by_count":0,"area":null},{"id":"2311.05089","title":"Legal-HNet: Mixing Legal Long-Context Tokens with Hartley Transform","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2403.17607","title":"Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUs","created":"2024-03-26","cited_by_count":0,"area":null},{"id":"2406.12921","title":"WindowMixer: Intra-Window and Inter-Window Modeling for Time Series Forecasting","created":"2024-06-14","cited_by_count":0,"area":null}],"next_cursor":null}