{"list":"other","total":53,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2404.16130","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","created":"2024-04-24","cited_by_count":1453},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668},{"id":"2305.06983","title":"Active Retrieval Augmented Generation","created":"2023-05-11","cited_by_count":516},{"id":"2405.14458","title":"YOLOv10: Real-Time End-to-End Object Detection","created":"2024-05-23","cited_by_count":515},{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429},{"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":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"2305.09645","title":"StructGPT: A General Framework for Large Language Model to Reason over Structured Data","created":"2023-05-16","cited_by_count":343},{"id":"2307.07697","title":"Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph","created":"2023-07-15","cited_by_count":238},{"id":"1907.13440","title":"MineRL: A Large-Scale Dataset of Minecraft Demonstrations","created":"2019-07-29","cited_by_count":215},{"id":"2501.00309","title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","created":"2024-12-31","cited_by_count":172},{"id":"2306.04136","title":"Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering","created":"2023-06-07","cited_by_count":119},{"id":"2403.03186","title":"Cradle: Empowering Foundation Agents Towards General Computer Control","created":"2024-03-05","cited_by_count":117},{"id":"2003.08536","title":"Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions","created":"2020-03-19","cited_by_count":106},{"id":"2212.00959","title":"UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph","created":"2022-12-02","cited_by_count":103},{"id":"2306.00937","title":"STEVE-1: A Generative Model for Text-to-Behavior in Minecraft","created":"2023-06-01","cited_by_count":97},{"id":"2202.13296","title":"Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering","created":"2022-02-27","cited_by_count":93},{"id":"2402.11163","title":"KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge Graph","created":"2024-02-17","cited_by_count":93},{"id":"2405.16506","title":"GRAG: Graph Retrieval-Augmented Generation","created":"2024-05-26","cited_by_count":78},{"id":"2312.07472","title":"MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception","created":"2023-12-12","cited_by_count":67},{"id":"2501.02226","title":"Knowledge Graph Retrieval-Augmented Generation for LLM-based Recommendation","created":"2025-01-04","cited_by_count":57},{"id":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42},{"id":"2312.14871","title":"BrainVis: Exploring the Bridge between Brain and Visual Signals via Image Reconstruction","created":"2023-12-22","cited_by_count":30},{"id":"2406.11668","title":"\"Not Aligned\" is Not \"Malicious\": Being Careful about Hallucinations of Large Language Models' Jailbreak","created":"2024-06-17","cited_by_count":25},{"id":"2401.00158","title":"ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph","created":"2023-12-30","cited_by_count":23},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21},{"id":"2310.08922","title":"LLaMA Rider: Spurring Large Language Models to Explore the Open World","created":"2023-10-13","cited_by_count":21},{"id":"2503.22166","title":"Reasoning of Large Language Models over Knowledge Graphs with Super-Relations","created":"2025-03-28","cited_by_count":21},{"id":"2505.13890","title":"Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLM","created":"2025-05-20","cited_by_count":21},{"id":"2401.12585","title":"SLANG: New Concept Comprehension of Large Language Models","created":"2024-01-23","cited_by_count":20},{"id":"2410.02684","title":"HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router","created":"2024-10-03","cited_by_count":16},{"id":"2405.19996","title":"DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild","created":"2024-05-30","cited_by_count":14},{"id":"2412.20392","title":"Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning","created":"2024-12-29","cited_by_count":12},{"id":"2503.23768","title":"Texture or Semantics? Vision-Language Models Get Lost in Font Recognition","created":"2025-03-31","cited_by_count":11},{"id":"2405.17424","title":"LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence","created":"2024-05-27","cited_by_count":10},{"id":"2502.19128","title":"SCA3D: Enhancing Cross-modal 3D Retrieval via 3D Shape and Caption Paired Data Augmentation","created":"2025-02-26","cited_by_count":9},{"id":"2408.09449","title":"From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification","created":"2024-08-18","cited_by_count":7},{"id":"2410.15180","title":"HACSurv: A Hierarchical Copula-Based Approach for Survival Analysis with Dependent Competing Risks","created":"2024-10-19","cited_by_count":7},{"id":"2508.03343","title":"WaMo: Wavelet-Enhanced Multi-Frequency Trajectory Analysis for Fine-Grained Text-Motion Retrieval","created":"2025-08-05","cited_by_count":7},{"id":"2407.07638","title":"Tuning Vision-Language Models with Candidate Labels by Prompt Alignment","created":"2024-07-10","cited_by_count":6},{"id":"2410.20016","title":"Vulnerability of LLMs to Vertically Aligned Text Manipulations","created":"2024-10-26","cited_by_count":6},{"id":"2411.17993","title":"DRS: Deep Question Reformulation With Structured Output","created":"2024-11-27","cited_by_count":6},{"id":"2504.01476","title":"Enhanced Cross-modal 3D Retrieval via Tri-modal Reconstruction","created":"2025-04-02","cited_by_count":5},{"id":"2504.01589","title":"Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models","created":"2025-04-02","cited_by_count":5},{"id":"2508.01678","title":"Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models","created":"2025-08-03","cited_by_count":4},{"id":"2501.06746","title":"Diversified Augmentation with Domain Adaptation for Debiased Video Temporal Grounding","created":"2025-01-12","cited_by_count":2}],"next_cursor":null}