{"list":"other","total":64,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2210.03493","title":"Automatic Chain of Thought Prompting in Large Language Models","created":"2022-10-07","cited_by_count":688},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638},{"id":"2210.10163","title":"MedCLIP: Contrastive Learning from Unpaired Medical Images and Text","created":"2022-10-18","cited_by_count":570},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312},{"id":"2110.07178","title":"Symbolic Knowledge Distillation: from General Language Models to Commonsense Models","created":"2021-10-14","cited_by_count":270},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2210.13312","title":"Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs","created":"2022-10-24","cited_by_count":220},{"id":"2210.12353","title":"Leveraging Large Language Models for Multiple Choice Question Answering","created":"2022-10-22","cited_by_count":203},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187},{"id":"2212.10465","title":"SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization","created":"2022-12-20","cited_by_count":168},{"id":"2303.02151","title":"Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners","created":"2023-03-03","cited_by_count":152},{"id":"1909.10705","title":"Do Massively Pretrained Language Models Make Better Storytellers?","created":"2019-09-24","cited_by_count":90},{"id":"2109.05433","title":"Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image Search","created":"2021-09-12","cited_by_count":90},{"id":"1811.00945","title":"Image Chat: Engaging Grounded Conversations","created":"2018-11-02","cited_by_count":77},{"id":"2012.13391","title":"I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling","created":"2020-12-24","cited_by_count":68},{"id":"2305.11792","title":"Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs","created":"2023-05-19","cited_by_count":62},{"id":"1701.08251","title":"Image-Grounded Conversations: Multimodal Context for Natural Question and Response Generation","created":"2017-01-28","cited_by_count":59},{"id":"2108.11830","title":"Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts","created":"2021-08-26","cited_by_count":56},{"id":"2211.05719","title":"MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation","created":"2022-11-10","cited_by_count":56},{"id":"1903.03166","title":"CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog","created":"2019-03-07","cited_by_count":44},{"id":"2108.01453","title":"PhotoChat: A Human-Human Dialogue Dataset with Photo Sharing Behavior for Joint Image-Text Modeling","created":"2021-07-06","cited_by_count":43},{"id":"2310.09343","title":"Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents","created":"2023-10-13","cited_by_count":41},{"id":"2305.01795","title":"Multimodal Procedural Planning via Dual Text-Image Prompting","created":"2023-05-02","cited_by_count":40},{"id":"2207.07635","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning","created":"2022-07-15","cited_by_count":39},{"id":"2204.03359","title":"ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO","created":"2022-04-07","cited_by_count":37},{"id":"2108.07154","title":"MMChat: Multi-Modal Chat Dataset on Social Media","created":"2021-08-16","cited_by_count":30},{"id":"2012.15015","title":"OpenViDial: A Large-Scale, Open-Domain Dialogue Dataset with Visual Contexts","created":"2020-12-30","cited_by_count":27},{"id":"2107.08685","title":"Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images","created":"2021-07-19","cited_by_count":26},{"id":"2010.01082","title":"Multi-Modal Open-Domain Dialogue","created":"2020-10-02","cited_by_count":19},{"id":"2204.08535","title":"Imagination-Augmented Natural Language Understanding","created":"2022-04-18","cited_by_count":19},{"id":"2305.14839","title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","created":"2023-05-24","cited_by_count":19},{"id":"2109.12761","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","created":"2021-09-27","cited_by_count":16},{"id":"2210.05725","title":"Measuring and Improving Semantic Diversity of Dialogue Generation","created":"2022-10-11","cited_by_count":16},{"id":"2303.09713","title":"CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos","created":"2023-03-17","cited_by_count":14},{"id":"2106.05970","title":"ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation","created":"2021-06-10","cited_by_count":6}],"next_cursor":null}