{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2002.08155","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","created":"2020-02-19","cited_by_count":1310},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2301.00704","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","created":"2023-01-02","cited_by_count":648},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2211.05105","title":"Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models","created":"2022-11-09","cited_by_count":513},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2206.14576","title":"Using cognitive psychology to understand GPT-3","created":"2022-06-21","cited_by_count":398},{"id":"2105.08050","title":"Pay Attention to MLPs","created":"2021-05-17","cited_by_count":368},{"id":"2201.10005","title":"Text and Code Embeddings by Contrastive Pre-Training","created":"2022-01-24","cited_by_count":361},{"id":"2305.07922","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","created":"2023-05-13","cited_by_count":333},{"id":"2306.13213","title":"Visual Adversarial Examples Jailbreak Aligned Large Language Models","created":"2023-06-22","cited_by_count":328},{"id":"1908.06954","title":"Attention on Attention for Image Captioning","created":"2019-08-19","cited_by_count":289},{"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":"2212.04037","title":"Demystifying Prompts in Language Models via Perplexity Estimation","created":"2022-12-08","cited_by_count":216},{"id":"2108.00941","title":"A Survey of Human-in-the-loop for Machine Learning","created":"2021-08-02","cited_by_count":215},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"id":"1907.12461","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","created":"2019-07-29","cited_by_count":182},{"id":"2012.02780","title":"Few-shot Image Generation with Elastic Weight Consolidation","created":"2020-12-04","cited_by_count":122},{"id":"2303.08559","title":"Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!","created":"2023-03-15","cited_by_count":119},{"id":"2211.01335","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","created":"2022-11-02","cited_by_count":109},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84},{"id":"2209.15323","title":"SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation","created":"2022-09-30","cited_by_count":82},{"id":"1509.04767","title":"Zero-Shot Learning via Semantic Similarity Embedding","created":"2015-09-15","cited_by_count":74},{"id":"1806.00926","title":"NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition","created":"2018-06-04","cited_by_count":73},{"id":"2208.11640","title":"Repair Is Nearly Generation: Multilingual Program Repair with LLMs","created":"2022-08-24","cited_by_count":68},{"id":"2303.12071","title":"ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals","created":"2023-03-21","cited_by_count":48},{"id":"2307.05722","title":"Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations","created":"2023-07-10","cited_by_count":45},{"id":"2201.06696","title":"ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues","created":"2022-01-18","cited_by_count":42},{"id":"2203.08372","title":"Multi-View Document Representation Learning for Open-Domain Dense Retrieval","created":"2022-03-16","cited_by_count":41},{"id":"1704.03899","title":"Deep Reinforcement Learning-based Image Captioning with Embedding Reward","created":"2017-04-12","cited_by_count":40},{"id":"2310.17680","title":"CodeFusion: A Pre-trained Diffusion Model for Code Generation","created":"2023-10-26","cited_by_count":31},{"id":"2205.04363","title":"Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning","created":"2022-05-09","cited_by_count":25},{"id":"2010.03276","title":"ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization","created":"2020-10-07","cited_by_count":22},{"id":"2305.10679","title":"Think Outside the Code: Brainstorming Boosts Large Language Models in Code Generation","created":"2023-05-18","cited_by_count":19},{"id":"2204.00185","title":"Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings","created":"2022-04-01","cited_by_count":17},{"id":"2305.15808","title":"Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback","created":"2023-05-25","cited_by_count":17},{"id":"2104.10640","title":"The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures","created":"2021-03-23","cited_by_count":16},{"id":"1908.08206","title":"Denoising based Sequence-to-Sequence Pre-training for Text Generation","created":"2019-08-22","cited_by_count":15},{"id":"2304.01053","title":"ViT-DAE: Transformer-driven Diffusion Autoencoder for Histopathology Image Analysis","created":"2023-04-03","cited_by_count":15},{"id":"2305.03195","title":"Gpt-4: A Review on Advancements and Opportunities in Natural Language Processing","created":"2023-05-04","cited_by_count":15},{"id":"2306.01220","title":"Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?","created":"2023-06-02","cited_by_count":14},{"id":"1908.08788","title":"When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification","created":"2019-08-22","cited_by_count":13},{"id":"2201.12723","title":"A Frustratingly Simple Approach for End-to-End Image Captioning","created":"2022-01-30","cited_by_count":12},{"id":"2307.06521","title":"Artificial Intelligence for Drug Discovery: Are We There Yet?","created":"2023-07-13","cited_by_count":11},{"id":"2205.05862","title":"AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling","created":"2022-05-12","cited_by_count":10},{"id":"2208.04254","title":"Distinctive Image Captioning via CLIP Guided Group Optimization","created":"2022-08-08","cited_by_count":6},{"id":"2201.01614","title":"PARM: A Paragraph Aggregation Retrieval Model for Dense Document-to-Document Retrieval","created":"2022-01-05","cited_by_count":5},{"id":"2208.08493","title":"Text-to-Image Generation via Implicit Visual Guidance and Hypernetwork","created":"2022-08-17","cited_by_count":4},{"id":"2306.14628","title":"An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning","created":"2023-06-26","cited_by_count":3},{"id":"2206.06177","title":"Transductive CLIP with Class-Conditional Contrastive Learning","created":"2022-06-13","cited_by_count":2},{"id":"2205.09246","title":"Transformer-based Program Synthesis for Low-Data Environments","created":"2022-05-18","cited_by_count":1},{"id":"2305.10834","title":"AIwriting: Relations Between Image Generation and Digital Writing","created":"2023-05-18","cited_by_count":1}],"next_cursor":null}