{"total":123,"rows":[{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"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":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"id":"2306.09093","title":"Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration","created":"2023-06-15","cited_by_count":172,"area":"mllm"},{"id":"2203.12221","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)","created":"2022-03-23","cited_by_count":122,"area":null},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86,"area":null},{"id":"2312.06720","title":"Audio-Visual LLM for Video Understanding","created":"2023-12-11","cited_by_count":77,"area":"mllm"},{"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":"2209.09019","title":"LAVIS: A Library for Language-Vision Intelligence","created":"2022-09-15","cited_by_count":55,"area":null},{"id":"2403.04640","title":"CAT: Enhancing Multimodal Large Language Model to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2024-03-07","cited_by_count":53,"area":"mllm"},{"id":"2411.19772","title":"LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos","created":"2024-11-29","cited_by_count":51,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"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":"2412.15838","title":"Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback","created":"2024-12-20","cited_by_count":39,"area":"alignment"},{"id":"2503.19951","title":"Audio-centric Video Understanding Benchmark without Text Shortcut","created":"2025-03-25","cited_by_count":36,"area":"mllm"},{"id":"2110.10101","title":"Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition","created":"2021-10-19","cited_by_count":35,"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":"2204.13031","title":"DialogVED: A Pre-trained Latent Variable Encoder-Decoder Model for Dialog Response Generation","created":"2022-04-27","cited_by_count":35,"area":null},{"id":"2508.01875","title":"StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding","created":"2025-08-03","cited_by_count":33,"area":"inference"},{"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":"2104.08006","title":"ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation","created":"2021-04-16","cited_by_count":31,"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":"2202.09277","title":"(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering","created":"2022-02-18","cited_by_count":30,"area":null},{"id":"2308.05421","title":"Progressive Spatio-temporal Perception for Audio-Visual Question Answering","created":"2023-08-10","cited_by_count":29,"area":null},{"id":"2312.16602","title":"Visual Instruction Tuning towards General-Purpose Multimodal Model: A Survey","created":"2023-12-27","cited_by_count":29,"area":null},{"id":"2109.04275","title":"M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining","created":"2021-09-09","cited_by_count":26,"area":null},{"id":"2502.11775","title":"video-SALMONN-o1: Reasoning-enhanced Audio-visual Large Language Model","created":"2025-02-17","cited_by_count":24,"area":"lr"},{"id":"2311.16789","title":"A Survey of the Evolution of Language Model-Based Dialogue Systems: Data, Task and Models","created":"2023-11-28","cited_by_count":23,"area":null},{"id":"2205.01543","title":"Learning to Transfer Prompts for Text Generation","created":"2022-05-03","cited_by_count":22,"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":"2310.05863","title":"Fine-grained Audio-Visual Joint Representations for Multimodal Large Language Models","created":"2023-10-09","cited_by_count":21,"area":"mllm"},{"id":"2405.17974","title":"Recent Trends in Personalized Dialogue Generation: A Review of Datasets, Methodologies, and Evaluations","created":"2024-05-28","cited_by_count":20,"area":null},{"id":"2205.14912","title":"E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation","created":"2022-05-30","cited_by_count":19,"area":null},{"id":"2205.05739","title":"Learning to Retrieve Videos by Asking Questions","created":"2022-05-11","cited_by_count":18,"area":null},{"id":"2212.05765","title":"Information-Theoretic Text Hallucination Reduction for Video-grounded Dialogue","created":"2022-12-12","cited_by_count":18,"area":null},{"id":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2404.12020","title":"Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering","created":"2024-04-18","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":"2104.08570","title":"Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems","created":"2021-04-17","cited_by_count":17,"area":null},{"id":"2301.04871","title":"Learning to Memorize Entailment and Discourse Relations for Persona-Consistent Dialogues","created":"2023-01-12","cited_by_count":17,"area":null},{"id":"2109.12761","title":"OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts","created":"2021-09-27","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":"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":"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":"2104.03762","title":"Video Question Answering with Phrases via Semantic Roles","created":"2021-04-08","cited_by_count":13,"area":null},{"id":"2312.09736","title":"HEAR: Hearing Enhanced Audio Response for Video-grounded Dialogue","created":"2023-12-15","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":"2308.10402","title":"Simple Baselines for Interactive Video Retrieval with Questions and Answers","created":"2023-08-21","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":"2104.07921","title":"VGNMN: Video-grounded Neural Module Network to Video-Grounded Language Tasks","created":"2021-04-16","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":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2406.06499","title":"NarrativeBridge: Enhancing Video Captioning with Causal-Temporal Narrative","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2504.02061","title":"Aligned Better, Listen Better for Audio-Visual Large Language Models","created":"2025-04-02","cited_by_count":10,"area":null},{"id":"2105.14207","title":"Maintaining Common Ground in Dynamic Environments","created":"2021-05-29","cited_by_count":9,"area":null},{"id":"2504.16030","title":"LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale","created":"2025-04-22","cited_by_count":9,"area":null},{"id":"2408.05926","title":"BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation","created":"2024-08-12","cited_by_count":8,"area":null},{"id":"2205.12502","title":"The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training","created":"2022-05-25","cited_by_count":7,"area":null},{"id":"2209.01621","title":"Interactive Question Answering Systems: Literature Review","created":"2022-09-04","cited_by_count":7,"area":null},{"id":"2211.04534","title":"Going for GOAL: A Resource for Grounded Football Commentaries","created":"2022-11-08","cited_by_count":7,"area":null},{"id":"2301.05880","title":"TikTalk: A Video-Based Dialogue Dataset for Multi-Modal Chitchat in Real World","created":"2023-01-14","cited_by_count":7,"area":null},{"id":"2206.07898","title":"Multimodal Dialogue State Tracking","created":"2022-06-16","cited_by_count":6,"area":null},{"id":"2212.09086","title":"PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism","created":"2022-12-18","cited_by_count":6,"area":null},{"id":"2404.06760","title":"DiffusionDialog: A Diffusion Model for Diverse Dialog Generation with Latent Space","created":"2024-04-10","cited_by_count":6,"area":"diffusion"},{"id":"2106.14069","title":"Saying the Unseen: Video Descriptions via Dialog Agents","created":"2021-06-26","cited_by_count":5,"area":null},{"id":"2210.14512","title":"End-to-End Multimodal Representation Learning for Video Dialog","created":"2022-10-26","cited_by_count":5,"area":null},{"id":"2310.18359","title":"DeSIQ: Towards an Unbiased, Challenging Benchmark for Social Intelligence Understanding","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2403.06679","title":"Answering Diverse Questions via Text Attached with Key Audio-Visual Clues","created":"2024-03-11","cited_by_count":5,"area":null},{"id":"2406.02554","title":"Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition","created":"2024-03-22","cited_by_count":5,"area":null},{"id":"2507.15504","title":"Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2402.04631","title":"The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trends","created":"2024-02-07","cited_by_count":4,"area":"agents"},{"id":"2410.12109","title":"OMCAT: Omni Context Aware Transformer","created":"2024-10-15","cited_by_count":4,"area":"mllm"},{"id":"2503.19794","title":"PAVE: Patching and Adapting Video Large Language Models","created":"2025-03-25","cited_by_count":4,"area":"lr"},{"id":"2505.17114","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2505.20638","title":"Music Audio-Visual Question Answering Requires Specialized Multimodal Designs","created":"2025-05-27","cited_by_count":4,"area":"mllm"},{"id":"2108.02147","title":"Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers","created":"2021-08-04","cited_by_count":3,"area":null},{"id":"2201.01289","title":"Self-directed Machine Learning","created":"2022-01-04","cited_by_count":3,"area":null},{"id":"2202.11847","title":"CAISE: Conversational Agent for Image Search and Editing","created":"2022-02-24","cited_by_count":3,"area":null},{"id":"2402.11875","title":"M2K-VDG: Model-Adaptive Multimodal Knowledge Anchor Enhanced Video-grounded Dialogue Generation","created":"2024-02-19","cited_by_count":3,"area":null},{"id":"2407.02218","title":"Multi-Modal Video Dialog State Tracking in the Wild","created":"2024-07-02","cited_by_count":3,"area":null},{"id":"2606.24286","title":"AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression","created":"2026-06-23","cited_by_count":3,"area":"mllm"},{"id":"2106.08914","title":"$C^3$: Compositional Counterfactual Contrastive Learning for Video-grounded Dialogues","created":"2021-06-16","cited_by_count":2,"area":null},{"id":"2207.00782","title":"Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review","created":"2022-07-02","cited_by_count":2,"area":null},{"id":"2305.14658","title":"Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response","created":"2023-05-24","cited_by_count":2,"area":null},{"id":"2307.04532","title":"Read, Look or Listen? What's Needed for Solving a Multimodal Dataset","created":"2023-07-06","cited_by_count":2,"area":null},{"id":"2411.04933","title":"SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2509.17901","title":"Do Modern Video-LLMs Need to Listen? A Benchmark Audit and Scalable Remedy","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2511.09958","title":"Audio-VLA: Adding Contact Audio Perception to Vision-Language-Action Model for Robotic Manipulation","created":"2025-11-13","cited_by_count":2,"area":"vla"},{"id":"2608.01157","title":"InteracVid: Building a Real Interactive Audio-Visual Response Dataset from Live-Chat Videos","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2608.07014","title":"Stable Curves, Unstable Items: Item-Level Scaling Heterogeneity in Video LLMs","created":"2026-08-07","cited_by_count":2,"area":null},{"id":"2108.05158","title":"Mounting Video Metadata on Transformer-based Language Model for Open-ended Video Question Answering","created":"2021-08-11","cited_by_count":1,"area":null},{"id":"2111.03994","title":"NarrationBot and InfoBot: A Hybrid System for Automated Video Description","created":"2021-11-07","cited_by_count":1,"area":null},{"id":"2203.12692","title":"Affective Feedback Synthesis Towards Multimodal Text and Image Data","created":"2022-03-23","cited_by_count":1,"area":null},{"id":"2204.11143","title":"Supplementing Missing Visions via Dialog for Scene Graph Generations","created":"2022-04-23","cited_by_count":1,"area":null},{"id":"2207.01823","title":"Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation","created":"2022-07-05","cited_by_count":1,"area":null},{"id":"2302.14680","title":"Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue","created":"2023-02-28","cited_by_count":1,"area":null}],"next_cursor":"100"}