{"total":34,"rows":[{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26,"area":null},{"id":"2411.02465","title":"See it, Think it, Sorted: Large Multimodal Models are Few-shot Time Series Anomaly Analyzers","created":"2024-11-04","cited_by_count":20,"area":null},{"id":"2509.23883","title":"DocPruner: A Storage-Efficient Framework for Multi-Vector Visual Document Retrieval via Adaptive Patch-Level Embedding Pruning","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2505.12589","title":"SurveillanceVQA-589K: A Benchmark for Comprehensive Surveillance Video-Language Understanding with Large Models","created":"2025-05-19","cited_by_count":18,"area":null},{"id":"2410.13757","title":"MobA: Multifaceted Memory-Enhanced Adaptive Planning for Efficient Mobile Task Automation","created":"2024-10-17","cited_by_count":14,"area":null},{"id":"2407.11784","title":"Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development","created":"2024-07-16","cited_by_count":10,"area":null},{"id":"2505.19139","title":"The Eye of Sherlock Holmes: Uncovering User Private Attribute Profiling via Vision-Language Model Agentic Framework","created":"2025-05-25","cited_by_count":9,"area":null},{"id":"2407.21553","title":"CXSimulator: A User Behavior Simulation using LLM Embeddings for Web-Marketing Campaign Assessment","created":"2024-07-31","cited_by_count":8,"area":null},{"id":"2505.16630","title":"SoccerChat: Integrating Multimodal Data for Enhanced Soccer Game Understanding","created":"2025-05-22","cited_by_count":8,"area":null},{"id":"2407.04065","title":"On the Workflows and Smells of Leaderboard Operations (LBOps): An Exploratory Study of Foundation Model Leaderboards","created":"2024-07-04","cited_by_count":6,"area":null},{"id":"2403.11456","title":"HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models","created":"2024-03-18","cited_by_count":5,"area":null},{"id":"2407.13717","title":"CoDefeater: Using LLMs To Find Defeaters in Assurance Cases","created":"2024-07-18","cited_by_count":5,"area":null},{"id":"2508.03209","title":"GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2602.03226","title":"ATACompressor: Adaptive Task-Aware Compression for Efficient Long-Context Processing in LLMs","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2508.02320","title":"Zero-shot Compositional Action Recognition with Neural Logic Constraints","created":"2025-08-04","cited_by_count":4,"area":null},{"id":"2503.08857","title":"Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs","created":"2025-03-11","cited_by_count":3,"area":null},{"id":"2506.17912","title":"PlanMoGPT: Flow-Enhanced Progressive Planning for Text to Motion Synthesis","created":"2025-06-22","cited_by_count":2,"area":null},{"id":"2506.18862","title":"TAMMs: Change Understanding and Forecasting in Satellite Image Time Series with Temporal-Aware Multimodal Models","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2604.10784","title":"TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2502.13034","title":"Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2504.13873","title":"Translating Multimodal AI into Real-World Inspection: TEMAI Evaluation Framework and Pathways for Implementation","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2506.06282","title":"Understanding Financial Reasoning in AI: A Multimodal Benchmark and Error Learning Approach","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2506.18272","title":"ReFrame: Rectification Framework for Image Explaining Architectures","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2509.07473","title":"SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2404.05406","title":"PerkwE_COQA: Enhanced Persian Conversational Question Answering by combining contextual keyword extraction with Large Language Models","created":"2024-04-08","cited_by_count":0,"area":null},{"id":"2506.14212","title":"What's in the Box? Reasoning about Unseen Objects from Multimodal Cues","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2508.17442","title":"Multi-Level LVLM Guidance for Untrimmed Video Action Recognition","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2508.21738","title":"From Drone Imagery to Livability Mapping: AI-powered Environment Perception in Rural China","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2509.05695","title":"Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2511.11777","title":"Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2603.15623","title":"Finder: A Multimodal AI-Powered Search Framework for Pharmaceutical Data Retrieval","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2606.16639","title":"SPICE: Synergy and Partial Information Based Curriculum Evolution","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2609.33833","title":"One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}