{"total":125,"rows":[{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062,"area":null},{"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":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2407.10759","title":"Qwen2-Audio Technical Report","created":"2024-07-15","cited_by_count":560,"area":null},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542,"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":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506,"area":null},{"id":"2403.00476","title":"TempCompass: Do Video LLMs Really Understand Videos?","created":"2024-03-01","cited_by_count":363,"area":null},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333,"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":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2306.07207","title":"Valley: Video Assistant with Large Language model Enhanced abilitY","created":"2023-06-12","cited_by_count":234,"area":null},{"id":"2402.07729","title":"AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension","created":"2024-02-12","cited_by_count":220,"area":null},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142,"area":null},{"id":"2402.01801","title":"Large Language Models for Time Series: A Survey","created":"2024-02-02","cited_by_count":114,"area":null},{"id":"2311.16103","title":"Video-Bench: A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models","created":"2023-11-27","cited_by_count":107,"area":null},{"id":"2406.15704","title":"video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models","created":"2024-06-22","cited_by_count":102,"area":null},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96,"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":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2309.13963","title":"Connecting Speech Encoder and Large Language Model for ASR","created":"2023-09-25","cited_by_count":80,"area":null},{"id":"2404.17176","title":"MovieChat+: Question-aware Sparse Memory for Long Video Question Answering","created":"2024-04-26","cited_by_count":73,"area":null},{"id":"2406.08772","title":"MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs","created":"2024-06-13","cited_by_count":61,"area":null},{"id":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57,"area":null},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2309.02033","title":"Data-Juicer: A One-Stop Data Processing System for Large Language Models","created":"2023-09-05","cited_by_count":52,"area":null},{"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":"2405.16886","title":"Hawk: Learning to Understand Open-World Video Anomalies","created":"2024-05-27","cited_by_count":49,"area":null},{"id":"2412.19806","title":"Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing","created":"2024-10-08","cited_by_count":49,"area":null},{"id":"2311.16926","title":"LLaFS: When Large Language Models Meet Few-Shot Segmentation","created":"2023-11-28","cited_by_count":48,"area":null},{"id":"2401.05702","title":"Video Anomaly Detection and Explanation via Large Language Models","created":"2024-01-11","cited_by_count":47,"area":null},{"id":"2404.12353","title":"V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning","created":"2024-04-18","cited_by_count":46,"area":null},{"id":"2505.21494","title":"Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment","created":"2025-05-27","cited_by_count":43,"area":null},{"id":"2312.04293","title":"GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition","created":"2023-12-07","cited_by_count":38,"area":null},{"id":"2403.01988","title":"FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs","created":"2024-03-04","cited_by_count":38,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2407.11351","title":"Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities","created":"2024-07-16","cited_by_count":31,"area":null},{"id":"2308.11804","title":"Adversarial Illusions in Multi-Modal Embeddings","created":"2023-08-22","cited_by_count":29,"area":null},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","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":"2412.05167","title":"Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models","created":"2024-12-06","cited_by_count":29,"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":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2308.14363","title":"Mobile Foundation Model as Firmware","created":"2023-08-28","cited_by_count":25,"area":null},{"id":"2404.17113","title":"MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition","created":"2024-04-26","cited_by_count":23,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","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":"2310.08884","title":"Extending Multi-modal Contrastive Representations","created":"2023-10-13","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":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2407.15087","title":"Navigation Instruction Generation with BEV Perception and Large Language Models","created":"2024-07-21","cited_by_count":21,"area":null},{"id":"2505.16690","title":"Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator","created":"2025-05-22","cited_by_count":20,"area":null},{"id":"2411.16771","title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","created":"2024-11-25","cited_by_count":19,"area":null},{"id":"2401.06395","title":"ModaVerse: Efficiently Transforming Modalities with LLMs","created":"2024-01-12","cited_by_count":18,"area":null},{"id":"2505.08137","title":"Large Language Models for Computer-Aided Design: A Survey","created":"2025-05-13","cited_by_count":18,"area":null},{"id":"2310.15326","title":"Specialist or Generalist? Instruction Tuning for Specific NLP Tasks","created":"2023-10-23","cited_by_count":17,"area":null},{"id":"2406.18941","title":"CLIP3D-AD: Extending CLIP for 3D Few-Shot Anomaly Detection with Multi-View Images Generation","created":"2024-06-27","cited_by_count":16,"area":null},{"id":"2412.17619","title":"Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detection","created":"2024-12-23","cited_by_count":15,"area":null},{"id":"2403.20236","title":"Long-Tailed Anomaly Detection with Learnable Class Names","created":"2024-03-29","cited_by_count":14,"area":null},{"id":"2412.02158","title":"Agri-LLaVA: Knowledge-Infused Large Multimodal Assistant on Agricultural Pests and Diseases","created":"2024-12-03","cited_by_count":14,"area":null},{"id":"2501.13306","title":"OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia","created":"2025-01-23","cited_by_count":13,"area":null},{"id":"2306.10765","title":"Path to Medical AGI: Unify Domain-specific Medical LLMs with the Lowest Cost","created":"2023-06-19","cited_by_count":12,"area":null},{"id":"2306.12725","title":"Generative Multimodal Entity Linking","created":"2023-06-22","cited_by_count":12,"area":null},{"id":"2309.14183","title":"Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition","created":"2023-09-25","cited_by_count":11,"area":null},{"id":"2401.02746","title":"Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues","created":"2024-01-05","cited_by_count":11,"area":null},{"id":"2502.18863","title":"Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM","created":"2025-02-26","cited_by_count":11,"area":null},{"id":"2309.14327","title":"DeepSpeed-VisualChat: Multi-Round Multi-Image Interleave Chat via Multi-Modal Causal Attention","created":"2023-09-25","cited_by_count":10,"area":null},{"id":"2410.05714","title":"Enhancing Temporal Modeling of Video LLMs via Time Gating","created":"2024-10-08","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":"2401.17664","title":"Image Anything: Towards Reasoning-coherent and Training-free Multi-modal Image Generation","created":"2024-01-31","cited_by_count":9,"area":null},{"id":"2402.02503","title":"GeReA: Question-Aware Prompt Captions for Knowledge-based Visual Question Answering","created":"2024-02-04","cited_by_count":9,"area":null},{"id":"2604.02605","title":"Do Audio-Visual Large Language Models Really See and Hear?","created":"2026-04-03","cited_by_count":9,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2405.00574","title":"EALD-MLLM: Emotion Analysis in Long-sequential and De-identity videos with Multi-modal Large Language Model","created":"2024-05-01","cited_by_count":8,"area":null},{"id":"2505.20873","title":"Fork-Merge Decoding: Enhancing Multimodal Understanding in Audio-Visual Large Language Models","created":"2025-05-27","cited_by_count":8,"area":null},{"id":"2508.08237","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2409.18680","title":"Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models","created":"2024-09-27","cited_by_count":6,"area":null},{"id":"2503.09321","title":"DAVE: Diagnostic benchmark for Audio Visual Evaluation","created":"2025-03-12","cited_by_count":6,"area":null},{"id":"2510.15148","title":"XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models","created":"2025-10-16","cited_by_count":6,"area":null},{"id":"2512.09841","title":"ChronusOmni: Improving Time Awareness of Omni Large Language Models","created":"2025-12-10","cited_by_count":6,"area":null},{"id":"2407.02042","title":"Fake News Detection and Manipulation Reasoning via Large Vision-Language Models","created":"2024-07-02","cited_by_count":5,"area":null},{"id":"2509.19994","title":"Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models","created":"2025-09-24","cited_by_count":5,"area":null},{"id":"2601.16449","title":"Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding","created":"2026-01-23","cited_by_count":5,"area":null},{"id":"2309.07623","title":"SwitchGPT: Adapting Large Language Models for Non-Text Outputs","created":"2023-09-14","cited_by_count":4,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","cited_by_count":4,"area":null},{"id":"2408.07694","title":"End-to-end Semantic-centric Video-based Multimodal Affective Computing","created":"2024-08-14","cited_by_count":4,"area":null},{"id":"2503.01261","title":"Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text","created":"2025-03-03","cited_by_count":4,"area":null},{"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":"2509.25991","title":"Towards Unified Multimodal Misinformation Detection in Social Media: A Benchmark Dataset and Baseline","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2511.07299","title":"VADER: Towards Causal Video Anomaly Understanding with Relation-Aware Large Language Models","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2405.16136","title":"C3LLM: Conditional Multimodal Content Generation Using Large Language Models","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2605.17360","title":"Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction","created":"2026-05-17","cited_by_count":3,"area":null},{"id":"2411.03287","title":"The Future of Intelligent Healthcare: A Systematic Analysis and Discussion on the Integration and Impact of Robots Using Large Language Models for Healthcare","created":"2024-11-05","cited_by_count":2,"area":null},{"id":"2411.17690","title":"Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2501.01164","title":"Towards Interactive Deepfake Analysis","created":"2025-01-02","cited_by_count":2,"area":null},{"id":"2503.20990","title":"FinAudio: A Benchmark for Audio Large Language Models in Financial Applications","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2505.10257","title":"Sage Deer: A Super-Aligned Driving Generalist Is Your Copilot","created":"2025-05-15","cited_by_count":2,"area":null},{"id":"2505.11216","title":"GeoMM: On Geodesic Perspective for Multi-modal Learning","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.00358","title":"$\\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time","created":"2025-05-31","cited_by_count":2,"area":null}],"next_cursor":"100"}