{"total":56,"rows":[{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388,"area":null},{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100,"area":null},{"id":"2502.05173","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","created":"2025-02-07","cited_by_count":65,"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":"2406.05132","title":"3D-GRAND: A Million-Scale Dataset for 3D-LLMs with Better Grounding and Less Hallucination","created":"2024-06-07","cited_by_count":36,"area":null},{"id":"2410.20774","title":"Are LLM-Judges Robust to Expressions of Uncertainty? Investigating the effect of Epistemic Markers on LLM-based Evaluation","created":"2024-10-28","cited_by_count":29,"area":null},{"id":"2411.16771","title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","created":"2024-11-25","cited_by_count":19,"area":null},{"id":"2403.16527","title":"Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Art","created":"2024-03-25","cited_by_count":17,"area":null},{"id":"2405.04180","title":"Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models","created":"2024-05-07","cited_by_count":17,"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":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14,"area":null},{"id":"2410.05258","title":"Differential Transformer","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2410.16638","title":"LLMScan: Causal Scan for LLM Misbehavior Detection","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2505.18816","title":"Reasoning Segmentation for Images and Videos: A Survey","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2510.09012","title":"Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy","created":"2025-10-10","cited_by_count":12,"area":null},{"id":"2510.21356","title":"Gaze-VLM:Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding","created":"2025-10-24","cited_by_count":11,"area":null},{"id":"2512.04643","title":"SEASON: Mitigating Temporal Hallucination in Video Large Language Models via Self-Diagnostic Contrastive Decoding","created":"2025-12-04","cited_by_count":10,"area":null},{"id":"2412.07183","title":"Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly","created":"2024-12-10","cited_by_count":9,"area":null},{"id":"2511.20032","title":"Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention","created":"2025-11-25","cited_by_count":9,"area":null},{"id":"2405.14161","title":"Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models","created":"2024-05-23","cited_by_count":8,"area":null},{"id":"2410.15359","title":"Hallucination in Multimodal Foundation Models: A Survey on Causes, Corrections, and Evaluations","created":"2024-10-20","cited_by_count":8,"area":null},{"id":"2503.22215","title":"Learning to Instruct for Visual Instruction Tuning","created":"2025-03-28","cited_by_count":8,"area":null},{"id":"2510.13796","title":"The Mechanistic Emergence of Symbol Grounding in Language Models","created":"2025-10-15","cited_by_count":6,"area":null},{"id":"2412.11404","title":"Attention with Dependency Parsing Augmentation for Fine-Grained Attribution","created":"2024-12-16","cited_by_count":5,"area":null},{"id":"2504.07433","title":"From Token to Line: Enhancing Code Generation with a Long-Term Perspective","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2509.09700","title":"Cross-Layer Attention Probing for Fine-Grained Hallucination Detection","created":"2025-09-04","cited_by_count":4,"area":null},{"id":"2512.05119","title":"RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering","created":"2025-10-11","cited_by_count":4,"area":null},{"id":"2602.11700","title":"TabSieve: Explicit In-Table Evidence Selection for Tabular Prediction","created":"2026-02-12","cited_by_count":4,"area":null},{"id":"2606.09859","title":"Mitigating Manifold Departure: Uncertainty-Aware Subspace Rectification for Trustworthy MLLM Decoding","created":"2026-05-31","cited_by_count":4,"area":null},{"id":"2509.00842","title":"Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings","created":"2025-08-31","cited_by_count":3,"area":null},{"id":"2510.12251","title":"DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2510.24767","title":"Towards Fine-Grained Human Motion Video Captioning","created":"2025-10-24","cited_by_count":3,"area":null},{"id":"2603.07990","title":"MJ1: Multimodal Judgment via Grounded Verification","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2604.10410","title":"CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2503.09994","title":"TIME: Temporal-Sensitive Multi-Dimensional Instruction Tuning and Robust Benchmarking for Video-LLMs","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2507.08021","title":"Unveiling Effective In-Context Configurations for Image Captioning: An External & Internal Analysis","created":"2025-07-08","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":"2605.13737","title":"Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2606.05161","title":"Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2504.03302","title":"Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2506.12483","title":"MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination","created":"2025-06-14","cited_by_count":1,"area":null},{"id":"2604.03045","title":"STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.05072","title":"Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2604.06393","title":"ART: Attention Replacement Technique to Improve Factuality in LLMs","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2604.12357","title":"ReflectCAP: Detailed Image Captioning with Reflective Memory","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2505.18168","title":"Emotion Knowledge Enhancement for Vision Large Language Models: A Self-Verification Approach for High-Quality Emotion Instruction Data Generation","created":"2025-05-14","cited_by_count":0,"area":null},{"id":"2510.00517","title":"Understanding Sensitivity of Differential Attention through the Lens of Adversarial Robustness","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2512.15423","title":"The 3D Mirage: Probing and Taming 3D Hallucinations","created":"2025-12-17","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":"2607.29240","title":"When Model Priors Conflict with Visual Evidence: Mitigating Commonsense-Driven Hallucinations by Selective Prior Calibration","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2609.20195","title":"Music Hallucination in Audio-Language Models: A Hierarchical Formulation and Empirical Study","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2610.00024","title":"Encoded but Disconnected: Decomposing Vision-Language Model Failures under a Patching Null","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.02999","title":"OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.18141","title":"Mitigating Cross-Modal Hallucinations by Correcting Modality Misrouting in Omnimodal LLMs","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19728","title":"Mitigating Video Hallucinations via Attention-Guided Representation Perturbation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}