{"list":"other","total":52,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2301.00774","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","created":"2023-01-02","cited_by_count":1121},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2304.05977","title":"ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation","created":"2023-04-12","cited_by_count":1045},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2306.11695","title":"A Simple and Effective Pruning Approach for Large Language Models","created":"2023-06-20","cited_by_count":800},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2310.15110","title":"Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model","created":"2023-10-23","cited_by_count":521},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474},{"id":"2309.06380","title":"InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation","created":"2023-09-12","cited_by_count":395},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"2208.11580","title":"Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning","created":"2022-08-24","cited_by_count":322},{"id":"2405.08748","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","created":"2024-05-14","cited_by_count":298},{"id":"2306.00980","title":"SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds","created":"2023-06-01","cited_by_count":227},{"id":"1705.07565","title":"Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon","created":"2017-05-22","cited_by_count":221},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149},{"id":"2305.18295","title":"RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths","created":"2023-05-29","cited_by_count":142},{"id":"2312.01026","title":"Token Fusion: Bridging the Gap between Token Pruning and Token Merging","created":"2023-12-02","cited_by_count":125},{"id":"2410.19355","title":"FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality","created":"2024-10-25","cited_by_count":122},{"id":"2312.10656","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","created":"2023-12-17","cited_by_count":113},{"id":"2411.02397","title":"Adaptive Caching for Faster Video Generation with Diffusion Transformers","created":"2024-11-04","cited_by_count":108},{"id":"2211.14108","title":"3DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Models","created":"2022-11-25","cited_by_count":57},{"id":"2411.13383","title":"Adversarial Diffusion Compression for Real-World Image Super-Resolution","created":"2024-11-20","cited_by_count":52},{"id":"2312.07330","title":"Learned representation-guided diffusion models for large-image generation","created":"2023-12-12","cited_by_count":40},{"id":"2405.15757","title":"Looking Backward: Streaming Video-to-Video Translation with Feature Banks","created":"2024-05-24","cited_by_count":38},{"id":"2401.05735","title":"Object-Centric Diffusion for Efficient Video Editing","created":"2024-01-11","cited_by_count":31},{"id":"2311.10329","title":"High-fidelity Person-centric Subject-to-Image Synthesis","created":"2023-11-17","cited_by_count":21},{"id":"2303.13126","title":"MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models","created":"2023-03-23","cited_by_count":16},{"id":"2505.10046","title":"Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis","created":"2025-05-15","cited_by_count":16},{"id":"2406.12042","title":"Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models","created":"2024-06-17","cited_by_count":13},{"id":"2409.11923","title":"Agglomerative Token Clustering","created":"2024-09-18","cited_by_count":13},{"id":"2504.05499","title":"Few-shot Personalized Scanpath Prediction","created":"2025-04-07","cited_by_count":5},{"id":"2506.05647","title":"Learning to Weight Parameters for Training Data Attribution","created":"2025-06-06","cited_by_count":3}],"next_cursor":null}