{"list":"other","total":57,"rows":[{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2209.14687","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","created":"2022-09-29","cited_by_count":1416},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2303.08797","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","created":"2023-03-15","cited_by_count":939},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256},{"id":"2405.14838","title":"From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step","created":"2024-05-23","cited_by_count":235},{"id":"2501.09732","title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","created":"2025-01-16","cited_by_count":234},{"id":"2103.03123","title":"COIN: COmpression with Implicit Neural representations","created":"2021-03-03","cited_by_count":233},{"id":"2306.17775","title":"Practical and Asymptotically Exact Conditional Sampling in Diffusion Models","created":"2023-06-30","cited_by_count":232},{"id":"2501.06848","title":"A General Framework for Inference-time Scaling and Steering of Diffusion Models","created":"2025-01-12","cited_by_count":224},{"id":"2109.15047","title":"Deep Contextual Video Compression","created":"2021-09-30","cited_by_count":221},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"1504.04788","title":"Compressing Neural Networks with the Hashing Trick","created":"2015-04-19","cited_by_count":150},{"id":"2304.02633","title":"HNeRV: A Hybrid Neural Representation for Videos","created":"2023-04-05","cited_by_count":100},{"id":"2503.02819","title":"Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts","created":"2025-03-04","cited_by_count":96},{"id":"2206.08889","title":"Lossy Compression with Gaussian Diffusion","created":"2022-06-17","cited_by_count":90},{"id":"2507.06203","title":"A Survey on Latent Reasoning","created":"2025-07-08","cited_by_count":81},{"id":"2502.20762","title":"Towards Practical Real-Time Neural Video Compression","created":"2025-02-28","cited_by_count":80},{"id":"2011.09704","title":"Causal Contextual Prediction for Learned Image Compression","created":"2020-11-19","cited_by_count":73},{"id":"1810.00440","title":"Minimal Random Code Learning: Getting Bits Back from Compressed Model Parameters","created":"2018-09-30","cited_by_count":58},{"id":"2402.14780","title":"Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models","created":"2024-02-22","cited_by_count":55},{"id":"2212.05458","title":"COOL-CHIC: Coordinate-based Low Complexity Hierarchical Image Codec","created":"2022-12-11","cited_by_count":51},{"id":"2505.23614","title":"Inference-time Scaling of Diffusion Models through Classical Search","created":"2025-05-29","cited_by_count":49},{"id":"2110.12805","title":"Algorithms for the Communication of Samples","created":"2021-10-25","cited_by_count":34},{"id":"2502.06079","title":"Debiasing Guidance for Discrete Diffusion with Sequential Monte Carlo","created":"2025-02-10","cited_by_count":31},{"id":"2409.07414","title":"NVRC: Neural Video Representation Compression","created":"2024-09-11","cited_by_count":29},{"id":"2502.01189","title":"Compressed Image Generation with Denoising Diffusion Codebook Models","created":"2025-02-03","cited_by_count":28},{"id":"2506.10082","title":"LoRA-Edit: Controllable First-Frame-Guided Video Editing via Mask-Aware LoRA Fine-Tuning","created":"2025-06-11","cited_by_count":28},{"id":"2305.19185","title":"Compression with Bayesian Implicit Neural Representations","created":"2023-05-30","cited_by_count":25},{"id":"2501.09815","title":"Lossy Compression with Pretrained Diffusion Models","created":"2025-01-16","cited_by_count":25},{"id":"2505.16177","title":"Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression","created":"2025-05-22","cited_by_count":25},{"id":"2509.21655","title":"DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models","created":"2025-09-25","cited_by_count":23},{"id":"2503.21781","title":"VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models","created":"2025-03-27","cited_by_count":17},{"id":"2506.05668","title":"RNE: plug-and-play diffusion inference-time control and energy-based training","created":"2025-06-06","cited_by_count":17},{"id":"2403.19776","title":"Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation","created":"2024-03-28","cited_by_count":10},{"id":"2503.19604","title":"GIViC: Generative Implicit Video Compression","created":"2025-03-25","cited_by_count":10},{"id":"2511.06424","title":"Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression","created":"2025-11-09","cited_by_count":8},{"id":"2405.12203","title":"Accelerating Relative Entropy Coding with Space Partitioning","created":"2024-05-20","cited_by_count":4},{"id":"2411.00915","title":"Empower Vision Applications with LoRA LMM","created":"2024-11-01","cited_by_count":2}],"next_cursor":null}