{"total":13,"rows":[{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66,"area":null},{"id":"2210.08451","title":"Bridging the Domain Gap for Multi-Agent Perception","created":"2022-10-16","cited_by_count":60,"area":null},{"id":"2207.05518","title":"Tracking Objects as Pixel-wise Distributions","created":"2022-07-12","cited_by_count":37,"area":null},{"id":"2206.02928","title":"Neuro-Symbolic Procedural Planning with Commonsense Prompting","created":"2022-06-06","cited_by_count":28,"area":null},{"id":"2404.08589","title":"Enhancing Visual Question Answering through Question-Driven Image Captions as Prompts","created":"2024-04-12","cited_by_count":18,"area":null},{"id":"2308.01236","title":"Grounded Image Text Matching with Mismatched Relation Reasoning","created":"2023-08-02","cited_by_count":8,"area":null},{"id":"2212.02064","title":"E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance","created":"2022-12-05","cited_by_count":6,"area":null},{"id":"2201.08081","title":"LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training","created":"2022-01-20","cited_by_count":5,"area":null},{"id":"2207.14741","title":"End-to-end View Synthesis via NeRF Attention","created":"2022-07-29","cited_by_count":5,"area":null},{"id":"2211.08086","title":"Visually Grounded VQA by Lattice-based Retrieval","created":"2022-11-15","cited_by_count":3,"area":null},{"id":"2211.05190","title":"Towards Reasoning-Aware Explainable VQA","created":"2022-11-09","cited_by_count":2,"area":null},{"id":"2309.01955","title":"A Survey on Interpretable Cross-modal Reasoning","created":"2023-09-05","cited_by_count":2,"area":null}],"next_cursor":null}