{"total":61,"rows":[{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2406.06040","title":"Vript: A Video Is Worth Thousands of Words","created":"2024-06-10","cited_by_count":71,"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":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2412.04280","title":"HumanEdit: A High-Quality Human-Rewarded Dataset for Instruction-based Image Editing","created":"2024-12-05","cited_by_count":29,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2411.16771","title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","created":"2024-11-25","cited_by_count":19,"area":null},{"id":"2405.13684","title":"CrossCheckGPT: Universal Hallucination Ranking for Multimodal Foundation Models","created":"2024-05-22","cited_by_count":18,"area":null},{"id":"2504.19254","title":"Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers","created":"2025-04-27","cited_by_count":18,"area":null},{"id":"2506.07371","title":"ARGUS: Hallucination and Omission Evaluation in Video-LLMs","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2506.19848","title":"ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing","created":"2025-06-24","cited_by_count":15,"area":null},{"id":"2505.14518","title":"Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples","created":"2025-05-20","cited_by_count":11,"area":null},{"id":"2411.00394","title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?","created":"2024-11-01","cited_by_count":10,"area":null},{"id":"2411.01414","title":"A Deep Dive Into Large Language Model Code Generation Mistakes: What and Why?","created":"2024-11-03","cited_by_count":10,"area":null},{"id":"2410.05217","title":"Organizing Unstructured Image Collections using Natural Language","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2603.03437","title":"Beyond Accuracy: Evaluating Visual Grounding In Multimodal Medical Reasoning","created":"2026-03-03","cited_by_count":7,"area":null},{"id":"2506.07209","title":"HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance","created":"2025-06-08","cited_by_count":6,"area":null},{"id":"2404.09690","title":"Harnessing GPT-4V(ision) for Insurance: A Preliminary Exploration","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2409.03025","title":"No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2409.20353","title":"CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset","created":"2024-09-30","cited_by_count":5,"area":null},{"id":"2509.18816","title":"Pay More Attention To Audio: Mitigating Imbalance of Cross-Modal Attention in Large Audio Language Models","created":"2025-09-23","cited_by_count":5,"area":null},{"id":"2602.17431","title":"Fine-Grained Uncertainty Quantification for Long-Form Language Model Outputs: A Comparative Study","created":"2026-02-19","cited_by_count":4,"area":null},{"id":"2405.13580","title":"AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2412.18224","title":"Expand VSR Benchmark for VLLM to Expertize in Spatial Rules","created":"2024-12-24","cited_by_count":3,"area":null},{"id":"2502.16841","title":"Fair Foundation Models for Medical Image Analysis: Challenges and Perspectives","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2507.21773","title":"AgriEval: A Comprehensive Chinese Agricultural Benchmark for Large Language Models","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2508.12422","title":"Illusions in Humans and AI: How Visual Perception Aligns and Diverges","created":"2025-08-17","cited_by_count":3,"area":null},{"id":"2508.20765","title":"Looking Beyond the Obvious: A Survey on Abstract Concept Recognition for Video Understanding","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2511.01458","title":"When to Trust the Answer: Question-Aligned Semantic Nearest Neighbor Entropy for Safer Surgical VQA","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2604.28078","title":"AesRM: Improving Video Aesthetics with Expert-Level Feedback","created":"2026-04-30","cited_by_count":3,"area":null},{"id":"2506.01015","title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2506.02696","title":"Shaking to Reveal: Perturbation-Based Detection of LLM Hallucinations","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2511.04042","title":"An LLM-based Framework for Human-Swarm Teaming Cognition in Disaster Search and Rescue","created":"2025-11-06","cited_by_count":2,"area":null},{"id":"2602.00117","title":"IC-EO: Interpretable Code-based assistant for Earth Observation","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2603.10360","title":"One Token, Two Fates: A Unified Framework via Vision Token Manipulation Against MLLMs Hallucination","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2606.19868","title":"A Systematic Evaluation of Black-Box Uncertainty Estimation Methods for Large Language Models","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2606.31933","title":"No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2402.14002","title":"Hallucinations or Attention Misdirection? The Path to Strategic Value Extraction in Business Using Large Language Models","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2410.11444","title":"A Theoretical Survey on Foundation Models","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2506.09916","title":"Only-Style: Stylistic Consistency in Image Generation without Content Leakage","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2512.03479","title":"ProcObject-10K: Benchmarking Object-Centric Procedural Understanding in Instructional Videos","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2512.09806","title":"CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2603.26127","title":"Finding Distributed Object-Centric Properties in Self-Supervised Transformers","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2603.27112","title":"RailVQA: A Benchmark and Framework for Efficient Interpretable Visual Cognition in Automatic Train Operation","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2605.10676","title":"Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.31077","title":"AnyMatch: Supercharging Universal Multi-Modal Image Matching with Large-Scale Single-View Images","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2503.00436","title":"HalCECE: A Framework for Explainable Hallucination Detection through Conceptual Counterfactuals in Image Captioning","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2509.21473","title":"Are Hallucinations Bad Estimations?","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2512.19455","title":"SiamGPT: Quality-First Fine-Tuning for Stable Thai Text Generation","created":"2025-12-22","cited_by_count":0,"area":null},{"id":"2512.21684","title":"SlideChain: Semantic Provenance for Lecture Understanding via Blockchain Registration","created":"2025-12-25","cited_by_count":0,"area":null},{"id":"2601.10010","title":"VERHallu: Evaluating and Mitigating Event Relation Hallucination in Video Large Language Models","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.13122","title":"Responsible AI for General-Purpose Systems: Overview, Challenges, and A Path Forward","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2602.00114","title":"Can One-Shot Test-Time Data Augmentation Help with Generalization?","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.04617","title":"LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2604.24972","title":"Dynamic Decision Learning: Test-Time Evolution for Abnormality Grounding in Rare Diseases","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.31304","title":"Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.00087","title":"Structured Visual Evidence Decomposition for Evidence-Grounded Multimodal Screening of Obstructive Sleep Apnea-Hypopnea Syndrome","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2607.01115","title":"Towards Developing a Multimodal Chat Assistant for University Stakeholders: RAG-based Approach","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.18736","title":"FedLNS: Leverage LayerNorm Signature Modeling to Mitigate Adversarial Manipulation in Federated LLMs","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.29999","title":"GHOST-Q: Towards Studying Grounding Hallucinations Overlooked Under Same-score TradeOffs in Quantized VLMS","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.34967","title":"Semantic Uncertainty Quantification Needs Factual Equivalence","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}