{"list":"other","total":91,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"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":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1806.08804","title":"Hierarchical Graph Representation Learning with Differentiable Pooling","created":"2018-06-22","cited_by_count":787},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"1907.04931","title":"GraphSAINT: Graph Sampling Based Inductive Learning Method","created":"2019-07-10","cited_by_count":618},{"id":"2006.09963","title":"GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training","created":"2020-06-17","cited_by_count":463},{"id":"1911.06136","title":"KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation","created":"2019-11-13","cited_by_count":356},{"id":"2205.09712","title":"Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning","created":"2022-05-19","cited_by_count":334},{"id":"2106.05234","title":"Do Transformers Really Perform Bad for Graph Representation?","created":"2021-06-09","cited_by_count":320},{"id":"2305.10037","title":"Can Language Models Solve Graph Problems in Natural Language?","created":"2023-05-17","cited_by_count":252},{"id":"2310.00149","title":"One for All: Towards Training One Graph Model for All Classification Tasks","created":"2023-09-29","cited_by_count":243},{"id":"1802.00543","title":"Modeling polypharmacy side effects with graph convolutional networks","created":"2018-02-02","cited_by_count":237},{"id":"2310.13023","title":"GraphGPT: Graph Instruction Tuning for Large Language Models","created":"2023-10-19","cited_by_count":226},{"id":"2308.07134","title":"Language is All a Graph Needs","created":"2023-08-14","cited_by_count":220},{"id":"2305.15066","title":"GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking","created":"2023-05-24","cited_by_count":210},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187},{"id":"2402.08170","title":"LLaGA: Large Language and Graph Assistant","created":"2024-02-13","cited_by_count":181},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179},{"id":"2310.04560","title":"Talk like a Graph: Encoding Graphs for Large Language Models","created":"2023-10-06","cited_by_count":176},{"id":"2501.00309","title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","created":"2024-12-31","cited_by_count":172},{"id":"2302.08043","title":"GraphPrompt: Unifying Pre-Training and Downstream Tasks for Graph Neural Networks","created":"2023-02-16","cited_by_count":167},{"id":"2307.01504","title":"All in One: Multi-task Prompting for Graph Neural Networks","created":"2023-07-04","cited_by_count":148},{"id":"2204.08570","title":"A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability","created":"2022-04-18","cited_by_count":118},{"id":"2310.05845","title":"GraphLLM: Boosting Graph Reasoning Ability of Large Language Model","created":"2023-10-09","cited_by_count":107},{"id":"1911.03977","title":"Multimodal Intelligence: Representation Learning, Information Fusion, and Applications","created":"2019-11-10","cited_by_count":89},{"id":"1706.05137","title":"One Model To Learn Them All","created":"2017-06-16","cited_by_count":87},{"id":"2310.04562","title":"Towards Foundation Models for Knowledge Graph Reasoning","created":"2023-10-06","cited_by_count":86},{"id":"2311.16208","title":"InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery","created":"2023-11-27","cited_by_count":86},{"id":"2402.02216","title":"Position: Graph Foundation Models are Already Here","created":"2024-02-03","cited_by_count":86},{"id":"2402.09834","title":"All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining","created":"2024-02-15","cited_by_count":86},{"id":"2308.06911","title":"GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text","created":"2023-08-14","cited_by_count":82},{"id":"2305.08298","title":"Symbol tuning improves in-context learning in language models","created":"2023-05-15","cited_by_count":75},{"id":"2402.03190","title":"Unified Hallucination Detection for Multimodal Large Language Models","created":"2024-02-05","cited_by_count":75},{"id":"2402.12984","title":"Can GNN be Good Adapter for LLMs?","created":"2024-02-20","cited_by_count":71},{"id":"2306.13089","title":"GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning","created":"2023-05-28","cited_by_count":70},{"id":"2311.18775","title":"CoDi-2: In-Context, Interleaved, and Interactive Any-to-Any Generation","created":"2023-11-30","cited_by_count":63},{"id":"2207.06010","title":"Does GNN Pretraining Help Molecular Representation?","created":"2022-07-13","cited_by_count":60},{"id":"2410.10329","title":"GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs","created":"2024-10-14","cited_by_count":58},{"id":"2407.09709","title":"GOFA: A Generative One-For-All Model for Joint Graph Language Modeling","created":"2024-07-12","cited_by_count":57},{"id":"2209.03299","title":"Multimodal learning with graphs","created":"2022-09-07","cited_by_count":54},{"id":"2205.02357","title":"Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion","created":"2022-05-04","cited_by_count":44},{"id":"2406.02030","title":"Multimodal Reasoning with Multimodal Knowledge Graph","created":"2024-06-04","cited_by_count":44},{"id":"2312.03731","title":"MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs","created":"2023-11-28","cited_by_count":40},{"id":"2308.11224","title":"Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis","created":"2023-08-22","cited_by_count":35},{"id":"2406.16321","title":"Mosaic of Modalities: A Comprehensive Benchmark for Multimodal Graph Learning","created":"2024-06-24","cited_by_count":29},{"id":"2310.07478","title":"Multimodal Graph Learning for Generative Tasks","created":"2023-10-11","cited_by_count":27},{"id":"2310.04944","title":"Beyond Text: A Deep Dive into Large Language Models' Ability on Understanding Graph Data","created":"2023-10-07","cited_by_count":25},{"id":"2306.02051","title":"A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers","created":"2023-06-03","cited_by_count":22},{"id":"2402.05322","title":"Learning on Multimodal Graphs: A Survey","created":"2024-02-07","cited_by_count":22},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22},{"id":"2210.00312","title":"Multimodal Analogical Reasoning over Knowledge Graphs","created":"2022-10-01","cited_by_count":21},{"id":"2306.14052","title":"A Survey on Graph Neural Network Acceleration: Algorithms, Systems, and Customized Hardware","created":"2023-06-24","cited_by_count":18},{"id":"2502.11925","title":"GRAPHGPT-O: Synergistic Multimodal Comprehension and Generation on Graphs","created":"2025-02-17","cited_by_count":17},{"id":"2402.12728","title":"Modality-Aware Integration with Large Language Models for Knowledge-based Visual Question Answering","created":"2024-02-20","cited_by_count":16},{"id":"2005.09606","title":"A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks","created":"2020-05-19","cited_by_count":15},{"id":"2204.09220","title":"LingYi: Medical Conversational Question Answering System based on Multi-modal Knowledge Graphs","created":"2022-04-20","cited_by_count":15},{"id":"2404.03080","title":"Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model","created":"2024-04-03","cited_by_count":15},{"id":"2410.07157","title":"InstructG2I: Synthesizing Images from Multimodal Attributed Graphs","created":"2024-10-09","cited_by_count":14},{"id":"2503.03854","title":"Vision-Language Models Struggle to Align Entities across Modalities","created":"2025-03-05","cited_by_count":14},{"id":"2402.13556","title":"Inductive Graph Alignment Prompt: Bridging the Gap between Graph Pre-training and Inductive Fine-tuning From Spectral Perspective","created":"2024-02-21","cited_by_count":13},{"id":"2205.12396","title":"Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks","created":"2022-05-24","cited_by_count":12},{"id":"2501.01124","title":"Graph2text or Graph2token: A Perspective of Large Language Models for Graph Learning","created":"2025-01-02","cited_by_count":12},{"id":"2206.13163","title":"Endowing Language Models with Multimodal Knowledge Graph Representations","created":"2022-06-27","cited_by_count":11},{"id":"2305.00581","title":"Multimodal Graph Transformer for Multimodal Question Answering","created":"2023-04-30","cited_by_count":10},{"id":"2209.05840","title":"Visual Recipe Flow: A Dataset for Learning Visual State Changes of Objects with Recipe Flows","created":"2022-09-13","cited_by_count":8},{"id":"2310.08446","title":"Towards Robust Multi-Modal Reasoning via Model Selection","created":"2023-10-12","cited_by_count":6},{"id":"2503.02435","title":"NLI4DB: A Systematic Review of Natural Language Interfaces for Databases","created":"2025-03-04","cited_by_count":5},{"id":"2503.21435","title":"Graph-to-Vision: Multi-graph Understanding and Reasoning using Vision-Language Models","created":"2025-03-27","cited_by_count":5},{"id":"2502.13277","title":"HyperGCL: Multi-Modal Graph Contrastive Learning via Learnable Hypergraph Views","created":"2025-02-18","cited_by_count":4},{"id":"2312.11282","title":"Evaluating and Enhancing Large Language Models for Conversational Reasoning on Knowledge Graphs","created":"2023-12-18","cited_by_count":3},{"id":"2411.01307","title":"Can Multimodal Large Language Model Think Analogically?","created":"2024-11-02","cited_by_count":2},{"id":"2501.07746","title":"A Heterogeneous Multimodal Graph Learning Framework for Recognizing User Emotions in Social Networks","created":"2025-01-13","cited_by_count":1}],"next_cursor":null}