{"total":22,"rows":[{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204,"area":null},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2212.02623","title":"Unifying Vision, Text, and Layout for Universal Document Processing","created":"2022-12-05","cited_by_count":140,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117,"area":null},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83,"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":"2406.04321","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","created":"2024-06-06","cited_by_count":40,"area":null},{"id":"2211.11275","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","created":"2022-11-21","cited_by_count":37,"area":null},{"id":"2411.18428","title":"MM-Path: Multi-modal, Multi-granularity Path Representation Learning -- Extended Version","created":"2024-11-27","cited_by_count":14,"area":null},{"id":"2502.12478","title":"MSE-Adapter: A Lightweight Plugin Endowing LLMs with the Capability to Perform Multimodal Sentiment Analysis and Emotion Recognition","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2304.04385","title":"On Robustness in Multimodal Learning","created":"2023-04-10","cited_by_count":3,"area":null},{"id":"2305.12311","title":"i-Code V2: An Autoregressive Generation Framework over Vision, Language, and Speech Data","created":"2023-05-21","cited_by_count":2,"area":null},{"id":"2405.07202","title":"Unified Video-Language Pre-training with Synchronized Audio","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2408.00365","title":"Multimodal Fusion and Coherence Modeling for Video Topic Segmentation","created":"2024-08-01","cited_by_count":1,"area":null},{"id":"2305.13738","title":"i-Code Studio: A Configurable and Composable Framework for Integrative AI","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2306.10056","title":"Generate to Understand for Representation","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2511.11706","title":"Context-Aware Multimodal Representation Learning for Spatio-Temporally Explicit Environmental Modelling","created":"2025-11-12","cited_by_count":0,"area":null}],"next_cursor":null}