{"total":51,"rows":[{"id":"2202.09741","title":"Visual Attention Network","created":"2022-02-20","cited_by_count":210,"area":null},{"id":"2303.03667","title":"Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks","created":"2023-03-07","cited_by_count":130,"area":null},{"id":"2406.00123","title":"Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration","created":"2024-05-31","cited_by_count":38,"area":null},{"id":"2205.14354","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","created":"2022-05-28","cited_by_count":34,"area":null},{"id":"2112.13692","title":"Augmenting Convolutional networks with attention-based aggregation","created":"2021-12-27","cited_by_count":29,"area":null},{"id":"2311.11268","title":"Towards Real-World Writing Assistance: A Chinese Character Checking Benchmark with Faked and Misspelled Characters","created":"2023-11-19","cited_by_count":22,"area":null},{"id":"2402.11100","title":"When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models","created":"2024-02-16","cited_by_count":22,"area":null},{"id":"2502.11493","title":"DAST: Context-Aware Compression in LLMs via Dynamic Allocation of Soft Tokens","created":"2025-02-17","cited_by_count":22,"area":null},{"id":"2302.08774","title":"Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph Alignment","created":"2023-02-17","cited_by_count":19,"area":null},{"id":"2310.09119","title":"A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check","created":"2023-10-13","cited_by_count":15,"area":null},{"id":"2502.07184","title":"Refine Knowledge of Large Language Models via Adaptive Contrastive Learning","created":"2025-02-11","cited_by_count":15,"area":null},{"id":"2307.14878","title":"MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entities","created":"2023-07-27","cited_by_count":13,"area":null},{"id":"2307.11458","title":"Strip-MLP: Efficient Token Interaction for Vision MLP","created":"2023-07-21","cited_by_count":12,"area":null},{"id":"2211.04215","title":"Active Relation Discovery: Towards General and Label-aware Open Relation Extraction","created":"2022-11-08","cited_by_count":10,"area":null},{"id":"2306.12465","title":"Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free Inference","created":"2023-06-21","cited_by_count":7,"area":null},{"id":"2112.04453","title":"MLP Architectures for Vision-and-Language Modeling: An Empirical Study","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2311.11375","title":"ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding","created":"2023-11-19","cited_by_count":6,"area":null},{"id":"2311.16707","title":"Full-resolution MLPs Empower Medical Dense Prediction","created":"2023-11-28","cited_by_count":6,"area":null},{"id":"2406.12220","title":"Hierarchical Associative Memory, Parallelized MLP-Mixer, and Symmetry Breaking","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2205.09120","title":"Fast matrix multiplication for binary and ternary CNNs on ARM CPU","created":"2022-05-18","cited_by_count":4,"area":null},{"id":"2210.16557","title":"Towards Attribute-Entangled Controllable Text Generation: A Pilot Study of Blessing Generation","created":"2022-10-29","cited_by_count":4,"area":null},{"id":"2303.10870","title":"Multi-task Transformer with Relation-attention and Type-attention for Named Entity Recognition","created":"2023-03-20","cited_by_count":4,"area":null},{"id":"2402.11422","title":"Mitigating Catastrophic Forgetting in Multi-domain Chinese Spelling Correction by Multi-stage Knowledge Transfer Framework","created":"2024-02-18","cited_by_count":4,"area":null},{"id":"2206.02734","title":"Global Mixup: Eliminating Ambiguity with Clustering","created":"2022-06-06","cited_by_count":3,"area":null},{"id":"2206.07435","title":"Forecasting of depth and ego-motion with transformers and self-supervision","created":"2022-06-15","cited_by_count":3,"area":null},{"id":"2303.13111","title":"Boosting Convolution with Efficient MLP-Permutation for Volumetric Medical Image Segmentation","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2304.03531","title":"From Retrieval to Generation: Efficient and Effective Entity Set Expansion","created":"2023-04-07","cited_by_count":3,"area":null},{"id":"2304.13061","title":"iMixer: hierarchical Hopfield network implies an invertible, implicit and iterative MLP-Mixer","created":"2023-04-25","cited_by_count":3,"area":null},{"id":"2504.07288","title":"MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2210.15147","title":"A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Ranking","created":"2022-10-27","cited_by_count":2,"area":null},{"id":"2310.11671","title":"MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correction","created":"2023-10-18","cited_by_count":2,"area":null},{"id":"2403.04247","title":"UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2509.13790","title":"Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learning","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2301.08868","title":"Computationally Efficient 3D MRI Reconstruction with Adaptive MLP","created":"2023-01-21","cited_by_count":1,"area":null},{"id":"2304.04718","title":"Investigating Graph Structure Information for Entity Alignment with Dangling Cases","created":"2023-04-10","cited_by_count":1,"area":null},{"id":"2305.14675","title":"TriMLP: Revenge of a MLP-like Architecture in Sequential Recommendation","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2309.04971","title":"Prompt Learning With Knowledge Memorizing Prototypes For Generalized Few-Shot Intent Detection","created":"2023-09-10","cited_by_count":1,"area":null},{"id":"2502.15261","title":"Corrections Meet Explanations: A Unified Framework for Explainable Grammatical Error Correction","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2505.21868","title":"Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2309.03559","title":"An Anchor Learning Approach for Citation Field Learning","created":"2023-09-07","cited_by_count":0,"area":null},{"id":"2311.00143","title":"Two-Stage Classifier for Campaign Negativity Detection using Axis Embeddings: A Case Study on Tweets of Political Users during 2021 Presidential Election in Iran","created":"2023-10-31","cited_by_count":0,"area":null},{"id":"2311.18735","title":"Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2403.06194","title":"On depth prediction for autonomous driving using self-supervised learning","created":"2024-03-10","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":"2412.18437","title":"MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning","created":"2024-12-24","cited_by_count":0,"area":null},{"id":"2504.09076","title":"Exploring Synergistic Ensemble Learning: Uniting CNNs, MLP-Mixers, and Vision Transformers to Enhance Image Classification","created":"2025-04-12","cited_by_count":0,"area":null},{"id":"2506.10084","title":"DeepTraverse: A Depth-First Search Inspired Network for Algorithmic Visual Understanding","created":"2025-06-11","cited_by_count":0,"area":null},{"id":"2509.11328","title":"Toward Next-generation Medical Vision Backbones: Modeling Finer-grained Long-range Visual Dependency","created":"2025-09-14","cited_by_count":0,"area":null},{"id":"2509.13672","title":"CL$^2$GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2511.11754","title":"Batch Transformer Architecture: Case of Synthetic Image Generation for Emotion Expression Facial Recognition","created":"2025-11-13","cited_by_count":0,"area":null},{"id":"2603.01706","title":"Search Multilayer Perceptron-Based Fusion for Efficient and Accurate Siamese Tracking","created":"2026-03-02","cited_by_count":0,"area":null}],"next_cursor":null}