{"total":167,"rows":[{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2210.12316","title":"Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders","created":"2022-10-22","cited_by_count":112,"area":null},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82,"area":null},{"id":"2109.08685","title":"Self-supervised learning methods and applications in medical imaging analysis: A survey","created":"2021-09-17","cited_by_count":77,"area":null},{"id":"2112.02761","title":"BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery","created":"2021-12-06","cited_by_count":68,"area":null},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64,"area":null},{"id":"2212.12042","title":"Re-basin via implicit Sinkhorn differentiation","created":"2022-12-22","cited_by_count":62,"area":null},{"id":"2209.11142","title":"A Generalist Neural Algorithmic Learner","created":"2022-09-22","cited_by_count":59,"area":null},{"id":"2203.02016","title":"Interventions, Where and How? Experimental Design for Causal Models at Scale","created":"2022-03-03","cited_by_count":49,"area":null},{"id":"2203.08509","title":"Differentiable DAG Sampling","created":"2022-03-16","cited_by_count":47,"area":null},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"area":null},{"id":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44,"area":null},{"id":"2103.12204","title":"Human-like Controllable Image Captioning with Verb-specific Semantic Roles","created":"2021-03-22","cited_by_count":41,"area":null},{"id":"2207.09610","title":"Unsupervised Deep Multi-Shape Matching","created":"2022-07-20","cited_by_count":39,"area":null},{"id":"2304.02146","title":"Structure Learning with Continuous Optimization: A Sober Look and Beyond","created":"2023-04-04","cited_by_count":36,"area":null},{"id":"2205.12209","title":"EdiT5: Semi-Autoregressive Text-Editing with T5 Warm-Start","created":"2022-05-24","cited_by_count":35,"area":null},{"id":"2310.13397","title":"Equivariant Deep Weight Space Alignment","created":"2023-10-20","cited_by_count":35,"area":null},{"id":"2307.13917","title":"BayesDAG: Gradient-Based Posterior Inference for Causal Discovery","created":"2023-07-26","cited_by_count":33,"area":null},{"id":"2105.04019","title":"Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision","created":"2021-05-09","cited_by_count":31,"area":null},{"id":"2205.06688","title":"A Unified Framework for Implicit Sinkhorn Differentiation","created":"2022-05-13","cited_by_count":28,"area":null},{"id":"2305.05080","title":"Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey","created":"2023-05-08","cited_by_count":27,"area":null},{"id":"2109.02363","title":"From Alignment to Assignment: Frustratingly Simple Unsupervised Entity Alignment","created":"2021-09-06","cited_by_count":26,"area":null},{"id":"2202.04235","title":"Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations","created":"2022-02-09","cited_by_count":26,"area":null},{"id":"2306.02866","title":"Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance","created":"2023-06-05","cited_by_count":26,"area":null},{"id":"2203.09630","title":"Monotonic Differentiable Sorting Networks","created":"2022-03-17","cited_by_count":25,"area":null},{"id":"2310.04470","title":"Hierarchical Multi-Marginal Optimal Transport for Network Alignment","created":"2023-10-06","cited_by_count":24,"area":null},{"id":"2303.10971","title":"Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching","created":"2023-03-20","cited_by_count":23,"area":null},{"id":"2412.16577","title":"A Meta-Learning Approach to Bayesian Causal Discovery","created":"2024-12-21","cited_by_count":22,"area":null},{"id":"2110.05651","title":"Learning with Algorithmic Supervision via Continuous Relaxations","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2307.12058","title":"Discovering Spatio-Temporal Rationales for Video Question Answering","created":"2023-07-22","cited_by_count":21,"area":null},{"id":"2302.00796","title":"Unsupervised Entity Alignment for Temporal Knowledge Graphs","created":"2023-02-01","cited_by_count":19,"area":null},{"id":"2105.02274","title":"Rethinking Search: Making Domain Experts out of Dilettantes","created":"2021-05-05","cited_by_count":18,"area":null},{"id":"2204.03640","title":"Equivariance Discovery by Learned Parameter-Sharing","created":"2022-04-07","cited_by_count":18,"area":null},{"id":"2106.03257","title":"Structured Reordering for Modeling Latent Alignments in Sequence Transduction","created":"2021-06-06","cited_by_count":17,"area":null},{"id":"2110.15797","title":"Discovering Non-monotonic Autoregressive Orderings with Variational Inference","created":"2021-10-27","cited_by_count":15,"area":null},{"id":"2103.09879","title":"Self-Supervised Learning of Audio Representations from Permutations with Differentiable Ranking","created":"2021-03-17","cited_by_count":14,"area":null},{"id":"2106.07877","title":"Learning Revenue-Maximizing Auctions With Differentiable Matching","created":"2021-06-15","cited_by_count":14,"area":null},{"id":"2104.08804","title":"Multilingual Knowledge Graph Completion with Joint Relation and Entity Alignment","created":"2021-04-18","cited_by_count":12,"area":null},{"id":"2207.05899","title":"Neural Topological Ordering for Computation Graphs","created":"2022-07-13","cited_by_count":12,"area":null},{"id":"2310.14883","title":"Non-autoregressive Streaming Transformer for Simultaneous Translation","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2310.01362","title":"Robot Fleet Learning via Policy Merging","created":"2023-10-02","cited_by_count":11,"area":null},{"id":"2409.17687","title":"Graph Edit Distance with General Costs Using Neural Set Divergence","created":"2024-09-26","cited_by_count":11,"area":null},{"id":"2503.08998","title":"From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches","created":"2025-03-12","cited_by_count":11,"area":null},{"id":"2602.03067","title":"FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU","created":"2026-02-03","cited_by_count":11,"area":null},{"id":"2106.02206","title":"Stochastic Iterative Graph Matching","created":"2021-06-04","cited_by_count":10,"area":null},{"id":"2107.10254","title":"Neural Fixed-Point Acceleration for Convex Optimization","created":"2021-07-21","cited_by_count":10,"area":null},{"id":"2403.19474","title":"SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2502.07962","title":"ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2301.11898","title":"DAG Learning on the Permutahedron","created":"2023-01-27","cited_by_count":9,"area":null},{"id":"2410.23451","title":"Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints","created":"2024-10-30","cited_by_count":9,"area":null},{"id":"2210.11020","title":"Maximum Common Subgraph Guided Graph Retrieval: Late and Early Interaction Networks","created":"2022-10-20","cited_by_count":8,"area":null},{"id":"2306.01240","title":"Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs","created":"2023-06-02","cited_by_count":8,"area":null},{"id":"2109.04442","title":"FGOT: Graph Distances based on Filters and Optimal Transport","created":"2021-09-09","cited_by_count":7,"area":null},{"id":"2110.15072","title":"Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces","created":"2021-10-28","cited_by_count":7,"area":null},{"id":"2103.05669","title":"Self-Supervision by Prediction for Object Discovery in Videos","created":"2021-03-09","cited_by_count":6,"area":null},{"id":"2103.09656","title":"Set-to-Sequence Methods in Machine Learning: a Review","created":"2021-03-17","cited_by_count":6,"area":null},{"id":"2210.11033","title":"Neural Estimation of Submodular Functions with Applications to Differentiable Subset Selection","created":"2022-10-20","cited_by_count":6,"area":null},{"id":"2306.06119","title":"Doubly Stochastic Graph-based Non-autoregressive Reaction Prediction","created":"2023-06-05","cited_by_count":6,"area":null},{"id":"2201.12868","title":"Anticipation-Free Training for Simultaneous Machine Translation","created":"2022-01-30","cited_by_count":5,"area":null},{"id":"2210.13583","title":"Learning Latent Structural Causal Models","created":"2022-10-24","cited_by_count":5,"area":null},{"id":"2305.16954","title":"Compositional Generalization without Trees using Multiset Tagging and Latent Permutations","created":"2023-05-26","cited_by_count":5,"area":null},{"id":"2308.07480","title":"Order-based Structure Learning with Normalizing Flows","created":"2023-08-14","cited_by_count":5,"area":null},{"id":"2308.13252","title":"Kissing to Find a Match: Efficient Low-Rank Permutation Representation","created":"2023-08-25","cited_by_count":5,"area":null},{"id":"2310.07174","title":"Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2503.08976","title":"Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2510.24039","title":"Geometric Algorithms for Neural Combinatorial Optimization with Constraints","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2101.04041","title":"Evaluating Disentanglement of Structured Representations","created":"2021-01-11","cited_by_count":3,"area":null},{"id":"2303.14470","title":"Compacting Binary Neural Networks by Sparse Kernel Selection","created":"2023-03-25","cited_by_count":3,"area":null},{"id":"2305.16841","title":"Differentiable Random Partition Models","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2311.08191","title":"GEC-DePenD: Non-Autoregressive Grammatical Error Correction with Decoupled Permutation and Decoding","created":"2023-11-14","cited_by_count":3,"area":null},{"id":"2403.05054","title":"A Sinkhorn-type Algorithm for Constrained Optimal Transport","created":"2024-03-08","cited_by_count":3,"area":null},{"id":"2409.04820","title":"FreeAugment: Data Augmentation Search Across All Degrees of Freedom","created":"2024-09-07","cited_by_count":3,"area":null},{"id":"2505.12325","title":"Neural Graduated Assignment for Maximum Common Edge Subgraphs","created":"2025-05-18","cited_by_count":3,"area":null},{"id":"2506.01977","title":"Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2109.12970","title":"Deep Learning Based Resource Assignment for Wireless Networks","created":"2021-09-27","cited_by_count":2,"area":null},{"id":"2205.01324","title":"Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2212.06339","title":"Regularized Optimal Transport Layers for Generalized Global Pooling Operations","created":"2022-12-13","cited_by_count":2,"area":null},{"id":"2306.01920","title":"Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning","created":"2023-06-02","cited_by_count":2,"area":null},{"id":"2308.03291","title":"SynJax: Structured Probability Distributions for JAX","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2308.06869","title":"Shape-Graph Matching Network (SGM-net): Registration for Statistical Shape Analysis","created":"2023-08-14","cited_by_count":2,"area":null},{"id":"2409.04495","title":"Learning to Solve Combinatorial Optimization under Positive Linear Constraints via Non-Autoregressive Neural Networks","created":"2024-09-06","cited_by_count":2,"area":null},{"id":"2410.08787","title":"Efficient Differentiable Discovery of Causal Order","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2410.14388","title":"Unscrambling disease progression at scale: fast inference of event permutations with optimal transport","created":"2024-10-18","cited_by_count":2,"area":null},{"id":"2412.06454","title":"Adaptive Graph Learning from Spatial Information for Surgical Workflow Anticipation","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2505.15661","title":"Deep greedy unfolding: Sorting out argsorting in greedy sparse recovery algorithms","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2507.04164","title":"Structure As Search: Unsupervised Permutation Learning for Combinatorial Optimization","created":"2025-07-05","cited_by_count":2,"area":null},{"id":"2510.22538","title":"Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval","created":"2025-10-26","cited_by_count":2,"area":null},{"id":"2603.20842","title":"A Knowledge-Informed Pretrained Model for Causal Discovery","created":"2026-03-21","cited_by_count":2,"area":null},{"id":"2105.00369","title":"Learning data association without data association: An EM approach to neural assignment prediction","created":"2021-05-02","cited_by_count":1,"area":null},{"id":"2110.04971","title":"A Deep Generative Model for Reordering Adjacency Matrices","created":"2021-10-11","cited_by_count":1,"area":null},{"id":"2110.12204","title":"Cascading Feature Extraction for Fast Point Cloud Registration","created":"2021-10-23","cited_by_count":1,"area":null},{"id":"2206.01370","title":"Towards Improving the Generation Quality of Autoregressive Slot VAEs","created":"2022-06-03","cited_by_count":1,"area":null},{"id":"2210.14897","title":"Searching Dense Point Correspondences via Permutation Matrix Learning","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2302.12050","title":"SPINDLE: Spinning Raw Text into Lambda Terms with Graph Attention","created":"2023-02-23","cited_by_count":1,"area":null},{"id":"2306.03679","title":"Human-imperceptible, Machine-recognizable Images","created":"2023-06-06","cited_by_count":1,"area":null},{"id":"2308.07136","title":"Pairing interacting protein sequences using masked language modeling","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2311.08143","title":"Sinkhorn Transformations for Single-Query Postprocessing in Text-Video Retrieval","created":"2023-11-14","cited_by_count":1,"area":null},{"id":"2407.04992","title":"Scalable Variational Causal Discovery Unconstrained by Acyclicity","created":"2024-07-06","cited_by_count":1,"area":null}],"next_cursor":"100"}