{"total":37,"rows":[{"id":"2105.15183","title":"Efficient and Modular Implicit Differentiation","created":"2021-05-31","cited_by_count":203,"area":null},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88,"area":null},{"id":"2111.05193","title":"A Survey on Green Deep Learning","created":"2021-11-08","cited_by_count":52,"area":null},{"id":"2104.07012","title":"Sparse Attention with Linear Units","created":"2021-04-14","cited_by_count":41,"area":null},{"id":"2109.04552","title":"SPECTRA: Sparse Structured Text Rationalization","created":"2021-09-09","cited_by_count":19,"area":null},{"id":"2410.01537","title":"Attention layers provably solve single-location regression","created":"2024-10-02","cited_by_count":17,"area":null},{"id":"2101.06658","title":"Trilevel Neural Architecture Search for Efficient Single Image Super-Resolution","created":"2021-01-17","cited_by_count":15,"area":null},{"id":"2402.13725","title":"Sparse and Structured Hopfield Networks","created":"2024-02-21","cited_by_count":13,"area":null},{"id":"2203.05997","title":"Towards Self-Supervised Learning of Global and Object-Centric Representations","created":"2022-03-11","cited_by_count":11,"area":null},{"id":"2110.14759","title":"Regularized Frank-Wolfe for Dense CRFs: Generalizing Mean Field and Beyond","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2203.04421","title":"Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction","created":"2022-03-08","cited_by_count":9,"area":null},{"id":"2204.06517","title":"Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation","created":"2022-03-30","cited_by_count":8,"area":null},{"id":"2308.15020","title":"Massively Parallel Continuous Local Search for Hybrid SAT Solving on GPUs","created":"2023-08-29","cited_by_count":8,"area":null},{"id":"2110.14182","title":"Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models","created":"2021-10-27","cited_by_count":6,"area":null},{"id":"2202.07071","title":"A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2405.04923","title":"DataSP: A Differential All-to-All Shortest Path Algorithm for Learning Costs and Predicting Paths with Context","created":"2024-05-08","cited_by_count":6,"area":null},{"id":"2406.01189","title":"MultiMax: Sparse and Multi-Modal Attention Learning","created":"2024-06-03","cited_by_count":5,"area":null},{"id":"2305.16128","title":"Give Me More Details: Improving Fact-Checking with Latent Retrieval","created":"2023-05-25","cited_by_count":4,"area":null},{"id":"2101.07077","title":"Yet Another Representation of Binary Decision Trees: A Mathematical Demonstration","created":"2021-01-18","cited_by_count":2,"area":null},{"id":"2201.00490","title":"Learning with Latent Structures in Natural Language Processing: A Survey","created":"2022-01-03","cited_by_count":2,"area":null},{"id":"2209.15176","title":"Adaptive Sparse and Monotonic Attention for Transformer-based Automatic Speech Recognition","created":"2022-09-30","cited_by_count":2,"area":null},{"id":"2212.08330","title":"Convolution-enhanced Evolving Attention Networks","created":"2022-12-16","cited_by_count":2,"area":null},{"id":"2304.01905","title":"Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition","created":"2023-04-03","cited_by_count":2,"area":null},{"id":"2310.03240","title":"Learning Hierarchical Relational Representations through Relational Convolutions","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2411.13548","title":"MGHF: Multi-Granular High-Frequency Perceptual Loss for Image Super-Resolution","created":"2024-11-20","cited_by_count":2,"area":null},{"id":"2602.08216","title":"Entropy-Generated Attention Beyond Softmax and Entmax: Kaniadakis and Reciprocal-Symmetric Abe Operators","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2205.06530","title":"Modeling Semantic Composition with Syntactic Hypergraph for Video Question Answering","created":"2022-05-13","cited_by_count":1,"area":null},{"id":"2506.00732","title":"Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2511.18876","title":"Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2602.01893","title":"Geometric Analysis of Token Selection in Multi-Head Attention","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2101.11347","title":"Decision Machines: Congruent Decision Trees","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2212.06267","title":"Mortality Prediction Models with Clinical Notes Using Sparse Attention at the Word and Sentence Levels","created":"2022-12-12","cited_by_count":0,"area":null},{"id":"2406.17386","title":"Double Momentum Method for Lower-Level Constrained Bilevel Optimization","created":"2024-06-25","cited_by_count":0,"area":null},{"id":"2503.09873","title":"FDCT: Frequency-Aware Decomposition and Cross-Modal Token-Alignment for Multi-Sensor Target Classification","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2505.02959","title":"Smooth Quadratic Prediction Markets","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2510.00517","title":"Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2609.27092","title":"Local Evidence and Geometric Readout Repair in Trained GNNs","created":"2026-09-22","cited_by_count":0,"area":null}],"next_cursor":null}