{"total":276,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"area":null},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297,"area":null},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225,"area":null},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"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":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142,"area":null},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135,"area":null},{"id":"2301.13823","title":"Grounding Language Models to Images for Multimodal Inputs and Outputs","created":"2023-01-31","cited_by_count":131,"area":null},{"id":"2306.04387","title":"M$^3$IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning","created":"2023-06-07","cited_by_count":126,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2212.10773","title":"MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning","created":"2022-12-21","cited_by_count":109,"area":null},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93,"area":null},{"id":"2108.00316","title":"Chest ImaGenome Dataset for Clinical Reasoning","created":"2021-07-31","cited_by_count":90,"area":null},{"id":"2303.06594","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions","created":"2023-03-12","cited_by_count":86,"area":null},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2401.10208","title":"MM-Interleaved: Interleaved Image-Text Generative Modeling via Multi-modal Feature Synchronizer","created":"2024-01-18","cited_by_count":80,"area":null},{"id":"2104.00783","title":"Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems","created":"2021-04-01","cited_by_count":75,"area":null},{"id":"2101.11796","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","created":"2021-01-28","cited_by_count":70,"area":null},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62,"area":null},{"id":"2108.04927","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","created":"2021-08-10","cited_by_count":58,"area":null},{"id":"2104.08667","title":"SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations","created":"2021-04-18","cited_by_count":56,"area":null},{"id":"2211.05719","title":"MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation","created":"2022-11-10","cited_by_count":56,"area":null},{"id":"2209.09019","title":"LAVIS: A Library for Language-Vision Intelligence","created":"2022-09-15","cited_by_count":55,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2104.08666","title":"Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models","created":"2021-04-18","cited_by_count":52,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46,"area":null},{"id":"2303.09429","title":"Data Roaming and Quality Assessment for Composed Image Retrieval","created":"2023-03-16","cited_by_count":46,"area":null},{"id":"2101.12059","title":"VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs","created":"2021-01-28","cited_by_count":42,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2210.07179","title":"MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2312.09251","title":"VL-GPT: A Generative Pre-trained Transformer for Vision and Language Understanding and Generation","created":"2023-12-14","cited_by_count":41,"area":null},{"id":"2506.20093","title":"ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset","created":"2025-06-25","cited_by_count":37,"area":null},{"id":"2110.14375","title":"Perceptual Score: What Data Modalities Does Your Model Perceive?","created":"2021-10-27","cited_by_count":35,"area":null},{"id":"2110.08515","title":"Multimodal Dialogue Response Generation","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2203.04203","title":"AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant","created":"2022-03-08","cited_by_count":32,"area":null},{"id":"2108.07154","title":"MMChat: Multi-Modal Chat Dataset on Social Media","created":"2021-08-16","cited_by_count":30,"area":null},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2308.16463","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","created":"2023-08-31","cited_by_count":28,"area":null},{"id":"2209.10304","title":"I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification","created":"2022-09-21","cited_by_count":27,"area":null},{"id":"2107.08685","title":"Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images","created":"2021-07-19","cited_by_count":26,"area":null},{"id":"2203.15867","title":"Image Retrieval from Contextual Descriptions","created":"2022-03-29","cited_by_count":26,"area":null},{"id":"2205.03966","title":"Chart Question Answering: State of the Art and Future Directions","created":"2022-05-08","cited_by_count":26,"area":null},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2209.12028","title":"Towards Explainable 3D Grounded Visual Question Answering: A New Benchmark and Strong Baseline","created":"2022-09-24","cited_by_count":25,"area":null},{"id":"2305.20062","title":"Chatting Makes Perfect: Chat-based Image Retrieval","created":"2023-05-31","cited_by_count":25,"area":null},{"id":"2306.05731","title":"Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions","created":"2023-06-09","cited_by_count":25,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2406.03411","title":"Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approach","created":"2024-06-05","cited_by_count":25,"area":null},{"id":"2305.17388","title":"MPCHAT: Towards Multimodal Persona-Grounded Conversation","created":"2023-05-27","cited_by_count":24,"area":null},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","cited_by_count":23,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"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,"area":null},{"id":"2301.11367","title":"Style-Aware Contrastive Learning for Multi-Style Image Captioning","created":"2023-01-26","cited_by_count":21,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2210.13626","title":"VLC-BERT: Visual Question Answering with Contextualized Commonsense Knowledge","created":"2022-10-24","cited_by_count":20,"area":null},{"id":"2105.13073","title":"Maria: A Visual Experience Powered Conversational Agent","created":"2021-05-27","cited_by_count":19,"area":null},{"id":"2112.08812","title":"Ditch the Gold Standard: Re-evaluating Conversational Question Answering","created":"2021-12-16","cited_by_count":19,"area":null},{"id":"2205.00423","title":"UTC: A Unified Transformer with Inter-Task Contrastive Learning for Visual Dialog","created":"2022-05-01","cited_by_count":19,"area":null},{"id":"2305.14839","title":"PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts","created":"2023-05-24","cited_by_count":19,"area":null},{"id":"2108.02359","title":"O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning","created":"2021-08-05","cited_by_count":18,"area":null},{"id":"2205.05739","title":"Learning to Retrieve Videos by Asking Questions","created":"2022-05-11","cited_by_count":18,"area":null},{"id":"2210.08714","title":"Selective Query-guided Debiasing for Video Corpus Moment Retrieval","created":"2022-10-17","cited_by_count":18,"area":null},{"id":"2210.12261","title":"Z-LaVI: Zero-Shot Language Solver Fueled by Visual Imagination","created":"2022-10-21","cited_by_count":18,"area":null},{"id":"2103.13361","title":"Structured Co-reference Graph Attention for Video-grounded Dialogue","created":"2021-03-24","cited_by_count":17,"area":null},{"id":"2212.04119","title":"DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2204.02624","title":"There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory","created":"2022-04-06","cited_by_count":16,"area":null},{"id":"2205.06907","title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","created":"2022-05-13","cited_by_count":16,"area":null},{"id":"2208.00934","title":"Video Question Answering with Iterative Video-Text Co-Tokenization","created":"2022-08-01","cited_by_count":16,"area":null},{"id":"2402.17128","title":"OSCaR: Object State Captioning and State Change Representation","created":"2024-02-27","cited_by_count":16,"area":null},{"id":"2106.04484","title":"Are VQA Systems RAD? Measuring Robustness to Augmented Data with Focused Interventions","created":"2021-06-08","cited_by_count":15,"area":null},{"id":"2107.11252","title":"Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation","created":"2021-07-23","cited_by_count":15,"area":null},{"id":"2109.05042","title":"Reference-Centric Models for Grounded Collaborative Dialogue","created":"2021-09-10","cited_by_count":15,"area":null},{"id":"2110.06894","title":"Audio-Visual Scene-Aware Dialog and Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning","created":"2021-10-13","cited_by_count":15,"area":null},{"id":"2211.12148","title":"Aligning Source Visual and Target Language Domains for Unpaired Video Captioning","created":"2022-11-22","cited_by_count":14,"area":null},{"id":"2303.09713","title":"CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos","created":"2023-03-17","cited_by_count":14,"area":null},{"id":"2101.00151","title":"DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue","created":"2021-01-01","cited_by_count":13,"area":null},{"id":"2109.08475","title":"GoG: Relation-aware Graph-over-Graph Network for Visual Dialog","created":"2021-09-17","cited_by_count":13,"area":null},{"id":"2203.17273","title":"FindIt: Generalized Localization with Natural Language Queries","created":"2022-03-31","cited_by_count":13,"area":null},{"id":"2109.01839","title":"Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark","created":"2021-09-04","cited_by_count":12,"area":null},{"id":"2110.08258","title":"A Framework for Learning to Request Rich and Contextually Useful Information from Humans","created":"2021-10-14","cited_by_count":12,"area":null},{"id":"2211.08371","title":"Pragmatics in Language Grounding: Phenomena, Tasks, and Modeling Approaches","created":"2022-11-15","cited_by_count":12,"area":null},{"id":"2308.10402","title":"Simple Baselines for Interactive Video Retrieval with Questions and Answers","created":"2023-08-21","cited_by_count":12,"area":null},{"id":"2401.02347","title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training","created":"2024-01-04","cited_by_count":12,"area":null},{"id":"2404.12235","title":"Beyond Average: Individualized Visual Scanpath Prediction","created":"2024-04-18","cited_by_count":12,"area":null},{"id":"2407.03386","title":"Visual Robustness Benchmark for Visual Question Answering (VQA)","created":"2024-07-03","cited_by_count":12,"area":null},{"id":"2407.14885","title":"Falcon2-11B Technical Report","created":"2024-07-20","cited_by_count":12,"area":null},{"id":"2103.00820","title":"Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues","created":"2021-03-01","cited_by_count":11,"area":null},{"id":"2109.08478","title":"Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation","created":"2021-09-17","cited_by_count":11,"area":null},{"id":"2111.07993","title":"CoLLIE: Continual Learning of Language Grounding from Language-Image Embeddings","created":"2021-11-15","cited_by_count":11,"area":null},{"id":"2111.14792","title":"Classification-Regression for Chart Comprehension","created":"2021-11-29","cited_by_count":11,"area":null},{"id":"2207.03656","title":"Video Dialog as Conversation about Objects Living in Space-Time","created":"2022-07-08","cited_by_count":11,"area":null},{"id":"2305.18756","title":"VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2404.09632","title":"Bridging Vision and Language Spaces with Assignment Prediction","created":"2024-04-15","cited_by_count":11,"area":null},{"id":"2103.01910","title":"MultiSubs: A Large-scale Multimodal and Multilingual Dataset","created":"2021-03-02","cited_by_count":10,"area":null},{"id":"2109.06013","title":"Learning to Ground Visual Objects for Visual Dialog","created":"2021-09-13","cited_by_count":10,"area":null}],"next_cursor":"100"}