{"list":"other","total":87,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2302.04761","title":"Toolformer: Language Models Can Teach Themselves to Use Tools","created":"2023-02-09","cited_by_count":4182},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2303.17651","title":"Self-Refine: Iterative Refinement with Self-Feedback","created":"2023-03-30","cited_by_count":3442},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2310.11511","title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","created":"2023-10-17","cited_by_count":1839},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2305.15334","title":"Gorilla: Large Language Model Connected with Massive APIs","created":"2023-05-24","cited_by_count":1332},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"2310.01798","title":"Large Language Models Cannot Self-Correct Reasoning Yet","created":"2023-10-03","cited_by_count":1017},{"id":"2304.05128","title":"Teaching Large Language Models to Self-Debug","created":"2023-04-11","cited_by_count":988},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2112.08654","title":"Learning to Prompt for Continual Learning","created":"2021-12-16","cited_by_count":944},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2204.04799","title":"DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning","created":"2022-04-10","cited_by_count":642},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2305.03726","title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","created":"2023-05-05","cited_by_count":550},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2302.01560","title":"Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents","created":"2023-02-03","cited_by_count":398},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"id":"2303.17491","title":"Language Models can Solve Computer Tasks","created":"2023-03-30","cited_by_count":372},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2305.17126","title":"Large Language Models as Tool Makers","created":"2023-05-26","cited_by_count":303},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302},{"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":"2305.18752","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","created":"2023-05-30","cited_by_count":248},{"id":"2305.11554","title":"ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings","created":"2023-05-19","cited_by_count":240},{"id":"2308.03188","title":"Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies","created":"2023-08-06","cited_by_count":238},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"id":"2303.09014","title":"ART: Automatic multi-step reasoning and tool-use for large language models","created":"2023-03-16","cited_by_count":197},{"id":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"id":"2210.06774","title":"Re3: Generating Longer Stories With Recursive Reprompting and Revision","created":"2022-10-13","cited_by_count":193},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193},{"id":"2303.16434","title":"TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs","created":"2023-03-29","cited_by_count":184},{"id":"2309.07915","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","created":"2023-09-14","cited_by_count":172},{"id":"2311.05997","title":"JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models","created":"2023-11-10","cited_by_count":171},{"id":"2301.13670","title":"What Makes Good Examples for Visual In-Context Learning?","created":"2023-01-31","cited_by_count":150},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"id":"1810.10220","title":"DSFD: Dual Shot Face Detector","created":"2018-10-24","cited_by_count":116},{"id":"2310.08118","title":"Can Large Language Models Really Improve by Self-critiquing Their Own Plans?","created":"2023-10-12","cited_by_count":108},{"id":"2306.08640","title":"AssistGPT: A General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn","created":"2023-06-14","cited_by_count":97},{"id":"2305.05662","title":"InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language","created":"2023-05-09","cited_by_count":96},{"id":"2310.12397","title":"GPT-4 Doesn't Know It's Wrong: An Analysis of Iterative Prompting for Reasoning Problems","created":"2023-10-19","cited_by_count":89},{"id":"2310.03051","title":"How FaR Are Large Language Models From Agents with Theory-of-Mind?","created":"2023-10-04","cited_by_count":76},{"id":"2305.13068","title":"Making Language Models Better Tool Learners with Execution Feedback","created":"2023-05-22","cited_by_count":70},{"id":"2310.17796","title":"ControlLLM: Augment Language Models with Tools by Searching on Graphs","created":"2023-10-26","cited_by_count":59},{"id":"2006.06649","title":"Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning","created":"2020-06-11","cited_by_count":58},{"id":"2303.17071","title":"DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents","created":"2023-03-30","cited_by_count":52},{"id":"1803.07464","title":"VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions","created":"2018-03-20","cited_by_count":50},{"id":"2212.04842","title":"PIVOT: Prompting for Video Continual Learning","created":"2022-12-09","cited_by_count":45},{"id":"2211.12764","title":"VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval","created":"2022-11-23","cited_by_count":36},{"id":"2309.01093","title":"CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection","created":"2023-09-03","cited_by_count":36},{"id":"2012.10582","title":"Learning by Fixing: Solving Math Word Problems with Weak Supervision","created":"2020-12-19","cited_by_count":25},{"id":"2311.05348","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","created":"2023-11-09","cited_by_count":24},{"id":"1801.09041","title":"Tell-and-Answer: Towards Explainable Visual Question Answering using Attributes and Captions","created":"2018-01-27","cited_by_count":22},{"id":"2305.08195","title":"Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing","created":"2023-05-14","cited_by_count":19},{"id":"2308.06531","title":"SegPrompt: Boosting Open-world Segmentation via Category-level Prompt Learning","created":"2023-08-12","cited_by_count":17},{"id":"2308.09658","title":"Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning","created":"2023-08-18","cited_by_count":17},{"id":"2007.01499","title":"A Competence-aware Curriculum for Visual Concepts Learning via Question Answering","created":"2020-07-03","cited_by_count":16},{"id":"2012.14011","title":"SMART: A Situation Model for Algebra Story Problems via Attributed Grammar","created":"2020-12-27","cited_by_count":14},{"id":"2210.01603","title":"Neural-Symbolic Recursive Machine for Systematic Generalization","created":"2022-10-04","cited_by_count":12},{"id":"2312.00401","title":"VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things","created":"2023-12-01","cited_by_count":4}],"next_cursor":null}