{"list":"other","total":63,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1312.4400","title":"Network In Network","created":"2013-12-16","cited_by_count":605},{"id":"1902.00434","title":"Generalized Sliced Wasserstein Distances","created":"2019-02-01","cited_by_count":208},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144},{"id":"2604.01687","title":"CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification","created":"2026-04-02","cited_by_count":128},{"id":"1606.02185","title":"Towards a Neural Statistician","created":"2016-06-07","cited_by_count":121},{"id":"1811.01900","title":"Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs","created":"2018-11-05","cited_by_count":98},{"id":"2506.00641","title":"AgentAuditor: Human-Level Safety and Security Evaluation for LLM Agents","created":"2025-05-31","cited_by_count":90},{"id":"1908.05659","title":"Distributionally Robust Optimization: A Review","created":"2019-08-13","cited_by_count":76},{"id":"1905.10943","title":"Distributionally Robust Optimization and Generalization in Kernel Methods","created":"2019-05-27","cited_by_count":73},{"id":"1906.02795","title":"FSPool: Learning Set Representations with Featurewise Sort Pooling","created":"2019-06-06","cited_by_count":53},{"id":"2407.07880","title":"Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization","created":"2024-07-10","cited_by_count":53},{"id":"2108.06468","title":"Modeling Scale-free Graphs with Hyperbolic Geometry for Knowledge-aware Recommendation","created":"2021-08-14","cited_by_count":38},{"id":"2312.16018","title":"RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation","created":"2023-12-26","cited_by_count":36},{"id":"2303.11700","title":"Dynamically Expandable Graph Convolution for Streaming Recommendation","created":"2023-03-21","cited_by_count":26},{"id":"2401.13870","title":"Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation","created":"2024-01-25","cited_by_count":26},{"id":"1904.01962","title":"Rep the Set: Neural Networks for Learning Set Representations","created":"2019-04-03","cited_by_count":22},{"id":"2110.09140","title":"Learning Prototype-oriented Set Representations for Meta-Learning","created":"2021-10-18","cited_by_count":19},{"id":"2604.12285","title":"GAM: Hierarchical Graph-based Agentic Memory for LLM Agents","created":"2026-04-14","cited_by_count":19},{"id":"2408.06966","title":"DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs","created":"2024-08-13","cited_by_count":17},{"id":"2203.02128","title":"Distributionally Robust Bayesian Optimization with $\\varphi$-divergences","created":"2022-03-04","cited_by_count":16},{"id":"1812.03928","title":"Learning Representations of Sets through Optimized Permutations","created":"2018-12-10","cited_by_count":15},{"id":"2006.03333","title":"Principled learning method for Wasserstein distributionally robust optimization with local perturbations","created":"2020-06-05","cited_by_count":14},{"id":"2109.02046","title":"Attentive Knowledge-aware Graph Convolutional Networks with Collaborative Guidance for Personalized Recommendation","created":"2021-09-05","cited_by_count":12},{"id":"2512.04111","title":"CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding","created":"2025-11-30","cited_by_count":12},{"id":"2401.07212","title":"HiHPQ: Hierarchical Hyperbolic Product Quantization for Unsupervised Image Retrieval","created":"2024-01-14","cited_by_count":11},{"id":"2403.03562","title":"Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyond","created":"2024-03-06","cited_by_count":11},{"id":"2602.03647","title":"Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration","created":"2026-02-03","cited_by_count":11},{"id":"2402.12411","title":"Deep Structural Knowledge Exploitation and Synergy for Estimating Node Importance Value on Heterogeneous Information Networks","created":"2024-02-19","cited_by_count":9},{"id":"2510.10618","title":"Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization","created":"2025-10-12","cited_by_count":9},{"id":"2406.16571","title":"Differentiable Distributionally Robust Optimization Layers","created":"2024-06-24","cited_by_count":8},{"id":"2504.02544","title":"Fourier Sliced-Wasserstein Embedding for Multisets and Measures","created":"2025-04-03","cited_by_count":8},{"id":"2605.22645","title":"AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters","created":"2026-05-21","cited_by_count":8},{"id":"2308.07760","title":"Dynamic Embedding Size Search with Minimum Regret for Streaming Recommender System","created":"2023-08-15","cited_by_count":7},{"id":"2510.10994","title":"Deep Research with Open-Domain Evaluation and Multi-Stage Guardrails for Safety","created":"2025-10-13","cited_by_count":7},{"id":"2602.06714","title":"PrefIx: Understand and Adapt to User Preference in Human-Agent Interaction","created":"2026-02-06","cited_by_count":7},{"id":"1805.00613","title":"Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networks","created":"2018-05-02","cited_by_count":6},{"id":"2407.19524","title":"VersusDebias: Universal Zero-Shot Debiasing for Text-to-Image Models via SLM-Based Prompt Engineering and Generative Adversary","created":"2024-07-28","cited_by_count":6},{"id":"2503.04162","title":"Semantic Retrieval Augmented Contrastive Learning for Sequential Recommendation","created":"2025-03-06","cited_by_count":6},{"id":"2201.13112","title":"Bayesian Optimization for Distributionally Robust Chance-constrained Problem","created":"2022-01-31","cited_by_count":5},{"id":"2305.04832","title":"Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems","created":"2023-05-03","cited_by_count":5},{"id":"2410.00690","title":"Beyond Minimax Rates in Group Distributionally Robust Optimization via a Novel Notion of Sparsity","created":"2024-10-01","cited_by_count":5},{"id":"2510.22095","title":"Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies","created":"2025-10-25","cited_by_count":5},{"id":"2502.12594","title":"PASER: Post-Training Data Selection for Efficient Pruned Large Language Model Recovery","created":"2025-02-18","cited_by_count":4},{"id":"2209.13973","title":"Knowledge-aware Neural Networks with Personalized Feature Referencing for Cold-start Recommendation","created":"2022-09-28","cited_by_count":3},{"id":"2502.08146","title":"Knowledge-Guided Wasserstein Distributionally Robust Optimization","created":"2025-02-12","cited_by_count":3},{"id":"2503.20341","title":"Wasserstein Distributionally Robust Bayesian Optimization with Continuous Context","created":"2025-03-26","cited_by_count":3},{"id":"2602.12172","title":"Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation","created":"2026-02-12","cited_by_count":3},{"id":"2107.10417","title":"LES3: Learning-based Exact Set Similarity Search","created":"2021-07-22","cited_by_count":2},{"id":"2506.08409","title":"FUSE: Measure-Theoretic Compact Fuzzy Set Representation for Taxonomy Expansion","created":"2025-06-10","cited_by_count":2},{"id":"2603.13702","title":"Routing Channel-Patch Dependencies in Time Series Forecasting with Graph Spectral Decomposition","created":"2026-03-14","cited_by_count":2},{"id":"2210.03282","title":"Set2Box: Similarity Preserving Representation Learning of Sets","created":"2022-10-07","cited_by_count":1},{"id":"2407.19469","title":"Interpretable Triplet Importance for Personalized Ranking","created":"2024-07-28","cited_by_count":1},{"id":"2504.02241","title":"Quantum Deep Sets and Sequences","created":"2025-04-03","cited_by_count":1},{"id":"2603.13799","title":"Node Role-Guided LLMs for Dynamic Graph Clustering","created":"2026-03-14","cited_by_count":1},{"id":"2603.19693","title":"Beyong Tokens: Item-aware Attention for LLM-based Recommendation","created":"2026-03-20","cited_by_count":1}],"next_cursor":null}