{"list":"other","total":55,"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":"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"2102.09690","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","created":"2021-02-19","cited_by_count":1392},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280},{"id":"2211.04486","title":"Active Example Selection for In-Context Learning","created":"2022-11-08","cited_by_count":196},{"id":"2006.14615","title":"LayoutTransformer: Layout Generation and Completion with Self-attention","created":"2020-06-25","cited_by_count":123},{"id":"1610.02454","title":"Learning What and Where to Draw","created":"2016-10-08","cited_by_count":105},{"id":"1801.05091","title":"Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis","created":"2018-01-16","cited_by_count":101},{"id":"2112.10070","title":"Unified Named Entity Recognition as Word-Word Relation Classification","created":"2021-12-19","cited_by_count":90},{"id":"1908.07500","title":"Image Synthesis From Reconfigurable Layout and Style","created":"2019-08-20","cited_by_count":85},{"id":"2108.00871","title":"Constrained Graphic Layout Generation via Latent Optimization","created":"2021-08-02","cited_by_count":83},{"id":"2305.01278","title":"VPGTrans: Transfer Visual Prompt Generator across LLMs","created":"2023-05-02","cited_by_count":80},{"id":"2101.06462","title":"Dual-Level Collaborative Transformer for Image Captioning","created":"2021-01-16","cited_by_count":71},{"id":"2112.05112","title":"BLT: Bidirectional Layout Transformer for Controllable Layout Generation","created":"2021-12-09","cited_by_count":69},{"id":"1909.00302","title":"READ: Recursive Autoencoders for Document Layout Generation","created":"2019-09-01","cited_by_count":51},{"id":"2004.06295","title":"Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpus","created":"2020-04-14","cited_by_count":49},{"id":"2012.07061","title":"Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network","created":"2020-12-13","cited_by_count":48},{"id":"2304.06248","title":"LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model","created":"2023-04-13","cited_by_count":43},{"id":"1901.00686","title":"Generating Multiple Objects at Spatially Distinct Locations","created":"2019-01-03","cited_by_count":41},{"id":"2103.11897","title":"Context-Aware Layout to Image Generation with Enhanced Object Appearance","created":"2021-03-22","cited_by_count":41},{"id":"2303.15764","title":"X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance","created":"2023-03-28","cited_by_count":37},{"id":"2105.02520","title":"Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledge","created":"2021-05-06","cited_by_count":31},{"id":"2305.12256","title":"Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination","created":"2023-05-20","cited_by_count":27},{"id":"2110.02001","title":"Mastering the Explicit Opinion-role Interaction: Syntax-aided Neural Transition System for Unified Opinion Role Labeling","created":"2021-10-05","cited_by_count":25},{"id":"2203.10796","title":"Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis","created":"2022-03-21","cited_by_count":22},{"id":"2305.11719","title":"Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling","created":"2023-05-19","cited_by_count":16},{"id":"2305.11768","title":"Generating Visual Spatial Description via Holistic 3D Scene Understanding","created":"2023-05-19","cited_by_count":16},{"id":"2305.12260","title":"Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment","created":"2023-05-20","cited_by_count":15},{"id":"2301.03160","title":"Towards Real-Time Panoptic Narrative Grounding by an End-to-End Grounding Network","created":"2023-01-09","cited_by_count":13},{"id":"2008.11932","title":"Attribute-guided image generation from layout","created":"2020-08-27","cited_by_count":10},{"id":"1908.01741","title":"Visual-Relation Conscious Image Generation from Structured-Text","created":"2019-08-05","cited_by_count":8}],"next_cursor":null}