{"list":"other","total":74,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2401.08740","title":"SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers","created":"2024-01-16","cited_by_count":737},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449},{"id":"2301.11093","title":"Simple diffusion: End-to-end diffusion for high resolution images","created":"2023-01-26","cited_by_count":422},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1903.00450","title":"Multi-Object Representation Learning with Iterative Variational Inference","created":"2019-03-01","cited_by_count":360},{"id":"1804.03599","title":"Understanding disentangling in $\\beta$-VAE","created":"2018-04-10","cited_by_count":335},{"id":"2303.00848","title":"Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation","created":"2023-03-01","cited_by_count":304},{"id":"2204.00227","title":"Perception Prioritized Training of Diffusion Models","created":"2022-04-01","cited_by_count":303},{"id":"2003.04887","title":"ReZero is All You Need: Fast Convergence at Large Depth","created":"2020-03-10","cited_by_count":264},{"id":"2303.09556","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","created":"2023-03-16","cited_by_count":246},{"id":"2210.04885","title":"What the DAAM: Interpreting Stable Diffusion Using Cross Attention","created":"2022-10-10","cited_by_count":236},{"id":"1907.13052","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","created":"2019-07-30","cited_by_count":227},{"id":"2504.10483","title":"REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers","created":"2025-04-14","cited_by_count":225},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"1901.09321","title":"Fixup Initialization: Residual Learning Without Normalization","created":"2019-01-27","cited_by_count":198},{"id":"2301.10972","title":"On the Importance of Noise Scheduling for Diffusion Models","created":"2023-01-26","cited_by_count":194},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147},{"id":"2312.03606","title":"DiffusionSat: A Generative Foundation Model for Satellite Imagery","created":"2023-12-06","cited_by_count":131},{"id":"1906.03292","title":"On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset","created":"2019-06-07","cited_by_count":100},{"id":"2111.10265","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","created":"2021-11-19","cited_by_count":93},{"id":"2310.09336","title":"Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task","created":"2023-10-13","cited_by_count":93},{"id":"2303.10834","title":"Object-Centric Slot Diffusion","created":"2023-03-20","cited_by_count":90},{"id":"2211.12737","title":"RoentGen: Vision-Language Foundation Model for Chest X-ray Generation","created":"2022-11-23","cited_by_count":89},{"id":"2305.11281","title":"SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models","created":"2023-05-18","cited_by_count":85},{"id":"2311.17901","title":"SODA: Bottleneck Diffusion Models for Representation Learning","created":"2023-11-29","cited_by_count":77},{"id":"2410.19324","title":"Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion","created":"2024-10-25","cited_by_count":75},{"id":"2408.03943","title":"Building Machines that Learn and Think with People","created":"2024-07-22","cited_by_count":73},{"id":"2303.02490","title":"Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later","created":"2023-03-04","cited_by_count":55},{"id":"2212.12990","title":"Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models","created":"2022-12-26","cited_by_count":54},{"id":"2404.02747","title":"Faster Diffusion via Temporal Attention Decomposition","created":"2024-04-03","cited_by_count":54},{"id":"2306.08757","title":"InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models","created":"2023-06-14","cited_by_count":50},{"id":"2305.14229","title":"Provably Learning Object-Centric Representations","created":"2023-05-23","cited_by_count":45},{"id":"2401.11430","title":"Exploring Diffusion Time-steps for Unsupervised Representation Learning","created":"2024-01-21","cited_by_count":36},{"id":"2102.10543","title":"Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View","created":"2021-02-21","cited_by_count":34},{"id":"2301.13721","title":"DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models","created":"2023-01-31","cited_by_count":30},{"id":"2405.17403","title":"A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training","created":"2024-05-27","cited_by_count":30},{"id":"2402.09712","title":"Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement","created":"2024-02-15","cited_by_count":27},{"id":"2403.10348","title":"Denoising Task Difficulty-based Curriculum for Training Diffusion Models","created":"2024-03-15","cited_by_count":27},{"id":"2411.07784","title":"Interaction Asymmetry: A General Principle for Learning Composable Abstractions","created":"2024-11-12","cited_by_count":20},{"id":"2602.17270","title":"Unified Latents (UL): How to train your latents","created":"2026-02-19","cited_by_count":20},{"id":"2502.05743","title":"Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling","created":"2025-02-09","cited_by_count":18},{"id":"2404.07946","title":"Towards Faster Training of Diffusion Models: An Inspiration of A Consistency Phenomenon","created":"2024-03-14","cited_by_count":14},{"id":"2407.17929","title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning","created":"2024-07-25","cited_by_count":14},{"id":"2402.15170","title":"The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling","created":"2024-02-23","cited_by_count":13},{"id":"2405.00646","title":"Learning to Compose: Improving Object Centric Learning by Injecting Compositionality","created":"2024-05-01","cited_by_count":13},{"id":"2411.17616","title":"Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints","created":"2024-11-26","cited_by_count":12},{"id":"2505.20772","title":"MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning","created":"2025-05-27","cited_by_count":11},{"id":"2410.23820","title":"Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models","created":"2024-10-31","cited_by_count":4},{"id":"2504.00220","title":"Can Diffusion Models Disentangle? A Theoretical Perspective","created":"2025-03-31","cited_by_count":3},{"id":"2602.05214","title":"Disentangled Representation Learning via Flow Matching","created":"2026-02-05","cited_by_count":2},{"id":"2510.21402","title":"Disentangled Representation Learning via Modular Compositional Bias","created":"2025-10-24","cited_by_count":1}],"next_cursor":null}