{"list":"other","total":63,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"1710.10196","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","created":"2017-10-27","cited_by_count":2988},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"1912.01865","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","created":"2019-12-04","cited_by_count":1098},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2305.13301","title":"Training Diffusion Models with Reinforcement Learning","created":"2023-05-22","cited_by_count":982},{"id":"2108.02938","title":"ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models","created":"2021-08-06","cited_by_count":635},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2309.17400","title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","created":"2023-09-29","cited_by_count":448},{"id":"2302.12192","title":"Aligning Text-to-Image Models using Human Feedback","created":"2023-02-23","cited_by_count":422},{"id":"2005.12320","title":"SCAN: Learning to Classify Images without Labels","created":"2020-05-25","cited_by_count":352},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297},{"id":"2303.14420","title":"Human Preference Score: Better Aligning Text-to-Image Models with Human Preference","created":"2023-03-25","cited_by_count":287},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"1907.10830","title":"U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation","created":"2019-07-25","cited_by_count":186},{"id":"2207.06635","title":"EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations","created":"2022-07-14","cited_by_count":172},{"id":"2402.15194","title":"Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control","created":"2024-02-23","cited_by_count":143},{"id":"2104.05358","title":"UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models","created":"2021-04-12","cited_by_count":133},{"id":"2101.08629","title":"Image-to-Image Translation: Methods and Applications","created":"2021-01-21","cited_by_count":116},{"id":"2408.08872","title":"xGen-MM (BLIP-3): A Family of Open Large Multimodal Models","created":"2024-08-16","cited_by_count":116},{"id":"1809.05852","title":"Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping","created":"2018-09-16","cited_by_count":113},{"id":"1706.00826","title":"One-Sided Unsupervised Domain Mapping","created":"2017-06-02","cited_by_count":91},{"id":"2302.12247","title":"Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework","created":"2023-02-23","cited_by_count":83},{"id":"2104.00854","title":"The Spatially-Correlative Loss for Various Image Translation Tasks","created":"2021-04-02","cited_by_count":66},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63},{"id":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45},{"id":"2210.14889","title":"Perfectly Secure Steganography Using Minimum Entropy Coupling","created":"2022-10-24","cited_by_count":44},{"id":"2302.03792","title":"Information-Theoretic Diffusion","created":"2023-02-07","cited_by_count":44},{"id":"2310.07972","title":"Interpretable Diffusion via Information Decomposition","created":"2023-10-12","cited_by_count":37},{"id":"1611.04035","title":"Entropic Causal Inference","created":"2016-11-12","cited_by_count":27},{"id":"2302.00389","title":"Multimodality Representation Learning: A Survey on Evolution, Pretraining and Its Applications","created":"2023-02-01","cited_by_count":27},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27},{"id":"1905.01752","title":"Understanding urban landuse from the above and ground perspectives: a deep learning, multimodal solution","created":"2019-05-05","cited_by_count":26},{"id":"2309.12458","title":"A Theory of Multimodal Learning","created":"2023-09-21","cited_by_count":25},{"id":"2306.04539","title":"Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications","created":"2023-06-07","cited_by_count":21},{"id":"2406.05191","title":"DiffusionPID: Interpreting Diffusion via Partial Information Decomposition","created":"2024-06-07","cited_by_count":16},{"id":"2308.02154","title":"SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation","created":"2023-08-04","cited_by_count":14},{"id":"2309.06799","title":"When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System","created":"2023-09-13","cited_by_count":13},{"id":"2309.15751","title":"InfraParis: A multi-modal and multi-task autonomous driving dataset","created":"2023-09-27","cited_by_count":12},{"id":"2306.07646","title":"Enhanced Multimodal Representation Learning with Cross-modal KD","created":"2023-06-13","cited_by_count":11},{"id":"2107.08295","title":"Communicating via Markov Decision Processes","created":"2021-07-17","cited_by_count":10},{"id":"2210.03164","title":"InfoOT: Information Maximizing Optimal Transport","created":"2022-10-06","cited_by_count":9},{"id":"2306.04445","title":"Multi-modal Latent Diffusion","created":"2023-06-07","cited_by_count":9},{"id":"2306.04636","title":"GP-UNIT: Generative Prior for Versatile Unsupervised Image-to-Image Translation","created":"2023-06-07","cited_by_count":9},{"id":"2402.01393","title":"ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data","created":"2024-02-02","cited_by_count":8},{"id":"1901.07530","title":"Minimum--Entropy Couplings and their Applications","created":"2019-01-19","cited_by_count":7},{"id":"1701.05243","title":"How to Find a Joint Probability Distribution of Minimum Entropy (almost) given the Marginals","created":"2017-01-18","cited_by_count":6},{"id":"2404.01595","title":"Propensity Score Alignment of Unpaired Multimodal Data","created":"2024-04-02","cited_by_count":6},{"id":"2410.21666","title":"Minimum Entropy Coupling with Bottleneck","created":"2024-10-29","cited_by_count":5},{"id":"1712.06804","title":"Asymptotic Coupling and Its Applications in Information Theory","created":"2017-12-19","cited_by_count":4},{"id":"2203.05108","title":"A Tighter Approximation Guarantee for Greedy Minimum Entropy Coupling","created":"2022-03-10","cited_by_count":4},{"id":"2403.06888","title":"Process signature-driven high spatio-temporal resolution alignment of multimodal data","created":"2024-03-11","cited_by_count":1}],"next_cursor":null}