{"total":2316,"rows":[{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968,"area":null},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057,"area":null},{"id":"2302.00482","title":"Improving and generalizing flow-based generative models with minibatch optimal transport","created":"2023-02-01","cited_by_count":879,"area":"diffusion"},{"id":"2106.01357","title":"Diffusion Schr\\\"odinger Bridge with Applications to Score-Based Generative Modeling","created":"2021-06-01","cited_by_count":602,"area":"diffusion"},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2304.14772","title":"Multisample Flow Matching: Straightening Flows with Minibatch Couplings","created":"2023-04-28","cited_by_count":278,"area":"diffusion"},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253,"area":null},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214,"area":null},{"id":"2203.08382","title":"Dual Diffusion Implicit Bridges for Image-to-Image Translation","created":"2022-03-16","cited_by_count":213,"area":"diffusion"},{"id":"2105.15183","title":"Efficient and Modular Implicit Differentiation","created":"2021-05-31","cited_by_count":203,"area":null},{"id":"2101.08231","title":"Word Alignment by Fine-tuning Embeddings on Parallel Corpora","created":"2021-01-20","cited_by_count":186,"area":null},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179,"area":null},{"id":"2103.14259","title":"OTA: Optimal Transport Assignment for Object Detection","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2108.08536","title":"A Unified Objective for Novel Class Discovery","created":"2021-08-19","cited_by_count":162,"area":null},{"id":"2210.06044","title":"Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation Learning","created":"2022-10-12","cited_by_count":159,"area":null},{"id":"2303.16852","title":"Diffusion Schr\\\"odinger Bridge Matching","created":"2023-03-29","cited_by_count":153,"area":"diffusion"},{"id":"2110.14076","title":"CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration","created":"2021-10-26","cited_by_count":152,"area":null},{"id":"2311.15937","title":"Optimal Transport Aggregation for Visual Place Recognition","created":"2023-11-27","cited_by_count":152,"area":null},{"id":"2106.09785","title":"Efficient Self-supervised Vision Transformers for Representation Learning","created":"2021-06-17","cited_by_count":149,"area":null},{"id":"2211.01364","title":"An optimal control perspective on diffusion-based generative modeling","created":"2022-11-02","cited_by_count":147,"area":"diffusion"},{"id":"2402.15194","title":"Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control","created":"2024-02-23","cited_by_count":143,"area":"diffusion"},{"id":"2106.02081","title":"Solving Schr\\\"odinger Bridges via Maximum Likelihood","created":"2021-06-03","cited_by_count":141,"area":null},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140,"area":null},{"id":"2110.11773","title":"Sinkformers: Transformers with Doubly Stochastic Attention","created":"2021-10-22","cited_by_count":138,"area":null},{"id":"2207.13532","title":"Contrastive Masked Autoencoders are Stronger Vision Learners","created":"2022-07-27","cited_by_count":133,"area":null},{"id":"2103.16556","title":"Learning Target Candidate Association to Keep Track of What Not to Track","created":"2021-03-30","cited_by_count":131,"area":null},{"id":"2201.02767","title":"QuadTree Attention for Vision Transformers","created":"2022-01-08","cited_by_count":129,"area":null},{"id":"2310.15141","title":"SpecTr: Fast Speculative Decoding via Optimal Transport","created":"2023-10-23","cited_by_count":129,"area":"inference"},{"id":"2103.03606","title":"Unbalanced minibatch Optimal Transport; applications to Domain Adaptation","created":"2021-03-05","cited_by_count":125,"area":null},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109,"area":null},{"id":"2103.09382","title":"SPICE: Semantic Pseudo-labeling for Image Clustering","created":"2021-03-17","cited_by_count":104,"area":null},{"id":"2307.01198","title":"Improved sampling via learned diffusions","created":"2023-07-03","cited_by_count":104,"area":null},{"id":"2201.12324","title":"Optimal Transport Tools (OTT): A JAX Toolbox for all things Wasserstein","created":"2022-01-28","cited_by_count":101,"area":null},{"id":"2310.03725","title":"Stochastic interpolants with data-dependent couplings","created":"2023-10-05","cited_by_count":100,"area":null},{"id":"2210.06662","title":"Action Matching: Learning Stochastic Dynamics from Samples","created":"2022-10-13","cited_by_count":98,"area":null},{"id":"2211.14843","title":"Learning Object-Language Alignments for Open-Vocabulary Object Detection","created":"2022-11-27","cited_by_count":96,"area":null},{"id":"2106.06345","title":"Proximal Optimal Transport Modeling of Population Dynamics","created":"2021-06-11","cited_by_count":93,"area":null},{"id":"2108.08771","title":"Learning to Match Features with Seeded Graph Matching Network","created":"2021-08-19","cited_by_count":92,"area":null},{"id":"2109.12004","title":"Entropic estimation of optimal transport maps","created":"2021-09-24","cited_by_count":90,"area":null},{"id":"2204.13101","title":"Self-Supervised Learning of Object Parts for Semantic Segmentation","created":"2022-04-27","cited_by_count":90,"area":null},{"id":"2210.02025","title":"GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models","created":"2022-10-05","cited_by_count":87,"area":null},{"id":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","cited_by_count":86,"area":"mllm"},{"id":"2204.09667","title":"Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments","created":"2022-04-20","cited_by_count":86,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2302.12247","title":"Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework","created":"2023-02-23","cited_by_count":83,"area":null},{"id":"2307.03672","title":"Simulation-free Schr\\\"odinger bridges via score and flow matching","created":"2023-07-07","cited_by_count":83,"area":"diffusion"},{"id":"2403.13117","title":"Optimal Flow Matching: Learning Straight Trajectories in Just One Step","created":"2024-03-19","cited_by_count":78,"area":"diffusion"},{"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":"2404.00925","title":"LLMs are Good Sign Language Translators","created":"2024-04-01","cited_by_count":77,"area":null},{"id":"2303.01497","title":"Teach a Robot to FISH: Versatile Imitation from One Minute of Demonstrations","created":"2023-03-02","cited_by_count":75,"area":"offlinerl"},{"id":"2307.09955","title":"XSkill: Cross Embodiment Skill Discovery","created":"2023-07-19","cited_by_count":75,"area":"offlinerl"},{"id":"2110.14565","title":"DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations","created":"2021-10-27","cited_by_count":74,"area":"wm"},{"id":"2405.11643","title":"Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology","created":"2024-05-19","cited_by_count":72,"area":null},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71,"area":null},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69,"area":null},{"id":"2305.00054","title":"LAVA: Data Valuation without Pre-Specified Learning Algorithms","created":"2023-04-28","cited_by_count":69,"area":null},{"id":"2103.04737","title":"Low-Rank Sinkhorn Factorization","created":"2021-03-08","cited_by_count":67,"area":null},{"id":"2206.15469","title":"Watch and Match: Supercharging Imitation with Regularized Optimal Transport","created":"2022-06-30","cited_by_count":67,"area":"offlinerl"},{"id":"2306.16156","title":"Recent Advances in Optimal Transport for Machine Learning","created":"2023-06-28","cited_by_count":66,"area":null},{"id":"2310.14228","title":"Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection","created":"2023-10-22","cited_by_count":66,"area":null},{"id":"2101.01792","title":"Minibatch optimal transport distances; analysis and applications","created":"2021-01-05","cited_by_count":65,"area":null},{"id":"2206.14928","title":"Manifold Interpolating Optimal-Transport Flows for Trajectory Inference","created":"2022-06-29","cited_by_count":64,"area":null},{"id":"2210.01253","title":"PLOT: Prompt Learning with Optimal Transport for Vision-Language Models","created":"2022-10-03","cited_by_count":64,"area":"mllm"},{"id":"2202.05722","title":"The Schr\\\"odinger Bridge between Gaussian Measures has a Closed Form","created":"2022-02-11","cited_by_count":63,"area":null},{"id":"2402.12030","title":"Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs","created":"2024-02-19","cited_by_count":63,"area":"distill"},{"id":"2103.13843","title":"OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations","created":"2021-03-25","cited_by_count":62,"area":null},{"id":"2104.12671","title":"Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos","created":"2021-04-26","cited_by_count":62,"area":null},{"id":"2204.11700","title":"ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching","created":"2022-04-25","cited_by_count":62,"area":null},{"id":"2309.09968","title":"Generating and Imputing Tabular Data via Diffusion and Flow-based Gradient-Boosted Trees","created":"2023-09-18","cited_by_count":62,"area":null},{"id":"2106.01128","title":"Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs","created":"2021-06-02","cited_by_count":61,"area":null},{"id":"2206.14262","title":"Supervised Training of Conditional Monge Maps","created":"2022-06-28","cited_by_count":61,"area":null},{"id":"1906.08113","title":"Wasserstein Adversarial Imitation Learning","created":"2019-06-19","cited_by_count":60,"area":"offlinerl"},{"id":"2102.08945","title":"Weakly Supervised Learning of Rigid 3D Scene Flow","created":"2021-02-17","cited_by_count":60,"area":null},{"id":"2110.03237","title":"Score-based Generative Neural Networks for Large-Scale Optimal Transport","created":"2021-10-07","cited_by_count":60,"area":null},{"id":"2302.03133","title":"Domain Adaptation for Time Series Under Feature and Label Shifts","created":"2023-02-06","cited_by_count":60,"area":null},{"id":"2102.07850","title":"Differentiable Particle Filtering via Entropy-Regularized Optimal Transport","created":"2021-02-15","cited_by_count":59,"area":null},{"id":"2203.07858","title":"A Survey of Non-Rigid 3D Registration","created":"2022-03-11","cited_by_count":59,"area":null},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59,"area":null},{"id":"2103.12366","title":"Group-aware Label Transfer for Domain Adaptive Person Re-identification","created":"2021-03-23","cited_by_count":58,"area":null},{"id":"2210.07277","title":"The Hidden Uniform Cluster Prior in Self-Supervised Learning","created":"2022-10-13","cited_by_count":58,"area":null},{"id":"2403.11435","title":"InsCL: A Data-efficient Continual Learning Paradigm for Fine-tuning Large Language Models with Instructions","created":"2024-03-18","cited_by_count":58,"area":null},{"id":"2210.17067","title":"Unified Optimal Transport Framework for Universal Domain Adaptation","created":"2022-10-31","cited_by_count":57,"area":null},{"id":"2503.18278","title":"TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model","created":"2025-03-24","cited_by_count":57,"area":"mllm"},{"id":"2111.10510","title":"Bayesian Learning via Neural Schr\\\"odinger-F\\\"ollmer Flows","created":"2021-11-20","cited_by_count":56,"area":null},{"id":"2111.01177","title":"Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence","created":"2021-11-01","cited_by_count":54,"area":null},{"id":"2106.00774","title":"Optimizing Functionals on the Space of Probabilities with Input Convex Neural Networks","created":"2021-06-01","cited_by_count":53,"area":null},{"id":"2107.01718","title":"Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections","created":"2021-07-04","cited_by_count":53,"area":null},{"id":"2208.11296","title":"Semi-Supervised and Unsupervised Deep Visual Learning: A Survey","created":"2022-08-24","cited_by_count":52,"area":null},{"id":"2102.01752","title":"Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization","created":"2021-02-02","cited_by_count":51,"area":null},{"id":"2204.07346","title":"MVSTER: Epipolar Transformer for Efficient Multi-View Stereo","created":"2022-04-15","cited_by_count":50,"area":null},{"id":"2211.01156","title":"Entropic Neural Optimal Transport via Diffusion Processes","created":"2022-11-02","cited_by_count":50,"area":null},{"id":"2503.01917","title":"Steer LLM Latents for Hallucination Detection","created":"2025-03-01","cited_by_count":50,"area":null},{"id":"2105.13353","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","created":"2021-05-27","cited_by_count":49,"area":null},{"id":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49,"area":null},{"id":"2102.04014","title":"Point-set Distances for Learning Representations of 3D Point Clouds","created":"2021-02-08","cited_by_count":48,"area":null},{"id":"2104.00921","title":"AAformer: Auto-Aligned Transformer for Person Re-Identification","created":"2021-04-02","cited_by_count":48,"area":null},{"id":"2203.12979","title":"Is Geometry Enough for Matching in Visual Localization?","created":"2022-03-24","cited_by_count":48,"area":null},{"id":"2207.00449","title":"Dissecting Self-Supervised Learning Methods for Surgical Computer Vision","created":"2022-07-01","cited_by_count":48,"area":null},{"id":"2412.07081","title":"Sequential Controlled Langevin Diffusions","created":"2024-12-10","cited_by_count":48,"area":null},{"id":"2203.09744","title":"Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation","created":"2022-03-18","cited_by_count":47,"area":null}],"next_cursor":"100"}