{"total":66,"rows":[{"id":"2209.04836","title":"Git Re-Basin: Merging Models modulo Permutation Symmetries","created":"2022-09-11","cited_by_count":471,"area":null},{"id":"2112.13890","title":"SPViT: Enabling Faster Vision Transformers via Soft Token Pruning","created":"2021-12-27","cited_by_count":167,"area":"inference"},{"id":"2110.14038","title":"Robustness of Graph Neural Networks at Scale","created":"2021-10-26","cited_by_count":100,"area":null},{"id":"2103.17202","title":"GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection","created":"2021-03-31","cited_by_count":66,"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":"2203.08509","title":"Differentiable DAG Sampling","created":"2022-03-16","cited_by_count":47,"area":null},{"id":"2211.08110","title":"HeatViT: Hardware-Efficient Adaptive Token Pruning for Vision Transformers","created":"2022-11-15","cited_by_count":46,"area":"inference"},{"id":"2108.00192","title":"Learning with Noisy Labels via Sparse Regularization","created":"2021-07-31","cited_by_count":39,"area":null},{"id":"2202.07559","title":"Unsupervised Learning of Group Invariant and Equivariant Representations","created":"2022-02-15","cited_by_count":39,"area":null},{"id":"2304.11523","title":"TransFlow: Transformer as Flow Learner","created":"2023-04-23","cited_by_count":32,"area":null},{"id":"2302.01425","title":"Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective","created":"2023-02-02","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":"2104.09856","title":"Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning","created":"2021-04-20","cited_by_count":23,"area":null},{"id":"2206.07290","title":"Differentiable Top-k Classification Learning","created":"2022-06-15","cited_by_count":21,"area":null},{"id":"2307.10780","title":"Learned Thresholds Token Merging and Pruning for Vision Transformers","created":"2023-07-20","cited_by_count":21,"area":"inference"},{"id":"2602.10238","title":"Learning to Evict from Key-Value Cache","created":"2026-02-10","cited_by_count":14,"area":"inference"},{"id":"2301.02009","title":"Learning by Sorting: Self-supervised Learning with Group Ordering Constraints","created":"2023-01-05","cited_by_count":13,"area":null},{"id":"2503.06242","title":"LapSum -- One Method to Differentiate Them All: Ranking, Sorting and Top-k Selection","created":"2025-03-08","cited_by_count":13,"area":null},{"id":"2505.13893","title":"InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2510.16598","title":"VisionSelector: End-to-End Learnable Visual Token Compression for Efficient Multimodal LLMs","created":"2025-10-18","cited_by_count":11,"area":"mllm"},{"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":"2201.13322","title":"Learning to Hash Naturally Sorts","created":"2022-01-31","cited_by_count":4,"area":null},{"id":"2402.02644","title":"Permutation-based Inference for Variational Learning of Directed Acyclic Graphs","created":"2024-02-04","cited_by_count":4,"area":null},{"id":"2410.08125","title":"Generalizing Stochastic Smoothing for Differentiation and Gradient Estimation","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2503.23455","title":"Efficient Token Compression for Vision Transformer with Spatial Information Preserved","created":"2025-03-30","cited_by_count":4,"area":"inference"},{"id":"2305.16841","title":"Differentiable Random Partition Models","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2308.01566","title":"Fast Slate Policy Optimization: Going Beyond Plackett-Luce","created":"2023-08-03","cited_by_count":3,"area":null},{"id":"2502.20012","title":"Learning Classifiers That Induce Markets","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2510.11472","title":"Differentiable Fast Top-K Selection for Large-Scale Recommendation","created":"2025-10-13","cited_by_count":3,"area":null},{"id":"2406.03616","title":"BEACON: A Bayesian Optimization Inspired Strategy for Efficient Novelty Search","created":"2024-06-05","cited_by_count":2,"area":null},{"id":"2410.03292","title":"Demystifying the Token Dynamics of Deep Selective State Space Models","created":"2024-10-04","cited_by_count":2,"area":"ssm"},{"id":"2410.19055","title":"Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2503.09492","title":"Learning Cascade Ranking as One Network","created":"2025-03-12","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":"2506.02203","title":"Constrained Sliced Wasserstein Embedding","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2603.08824","title":"SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients","created":"2026-03-09","cited_by_count":2,"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":"2407.04992","title":"Scalable Variational Causal Discovery Unconstrained by Acyclicity","created":"2024-07-06","cited_by_count":1,"area":null},{"id":"2503.02730","title":"Creating Sorted Grid Layouts with Gradient-based Optimization","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2402.18128","title":"Downstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimization","created":"2024-02-28","cited_by_count":0,"area":null},{"id":"2410.17500","title":"Learning Fair and Preferable Allocations through Neural Network","created":"2024-10-23","cited_by_count":0,"area":null},{"id":"2410.19384","title":"Learning Neural Strategy-Proof Matching Mechanism from Examples","created":"2024-10-25","cited_by_count":0,"area":null},{"id":"2411.03535","title":"The Differentiable Feasibility Pump","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2503.13051","title":"Permutation Learning with Only N Parameters: From SoftSort to Self-Organizing Gaussians","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2506.02694","title":"XicorAttention: Time Series Transformer Using Attention with Nonlinear Correlation","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2508.14180","title":"RewardRank: Optimizing True Learning-to-Rank Utility","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2511.14482","title":"Gradient-Based Join Ordering","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.03424","title":"DM3D: Dynamic Mamba via Offset-Guided Feature Resampling for Point Cloud Understanding","created":"2025-12-03","cited_by_count":0,"area":"ssm"},{"id":"2512.22150","title":"Towards Unsupervised Causal Representation Learning via Latent Additive Noise Model Causal Autoencoders","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2512.22587","title":"Structural Incompatibility of Differentiable Sorting and Within-Vector Rank Normalization","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2601.15133","title":"Building Deep Graph Predictors with Graph Imitation Learning","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.14440","title":"CAIRO: Decoupling Order from Scale in Regression","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2602.23602","title":"Moment Matters: Mean and Variance Causal Graph Discovery from Heteroscedastic Observational Data","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.17353","title":"Learning Permutation Distributions via Reflected Diffusion on Ranks","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.04087","title":"ArrowFlow: Hierarchical Machine Learning in the Space of Permutations","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.05819","title":"Learn to Rank: Visual Attribution by Learning Importance Ranking","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.00915","title":"Learning Dynamic Evidence Routes for Vision Transformer Probing","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.25551","title":"Learning Permutation from Structure Without Supervision","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2606.08565","title":"EinSort: Sorting is All We Need for Tensorizing LLM","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2607.22934","title":"Amortized Bayesian Causal Discovery of Extended Factor Graphs","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.04057","title":"LaPrune: Controllable Differentiable Sparsity at Million Scale","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.06912","title":"Fast LapSum: Exact Differentiable Top-$k$ at Million Scale","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.01807","title":"SPD: Single Pass Decoding for Generative Reranking","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.37122","title":"Learning the Structure of Triangular Transport Maps","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37225","title":"ResComEmb: Effective and Efficient Multimodal Embedding via Residual Homogeneity Compression","created":"2026-09-29","cited_by_count":0,"area":"mllm"}],"next_cursor":null}