{"total":84,"rows":[{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752,"area":null},{"id":"2603.21687","title":"MIRAGE: The Illusion of Visual Understanding","created":"2026-03-23","cited_by_count":65,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2410.06126","title":"X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection","created":"2024-10-08","cited_by_count":35,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2408.11424","title":"EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning","created":"2024-08-21","cited_by_count":28,"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":"2408.12880","title":"Has Multimodal Learning Delivered Universal Intelligence in Healthcare? A Comprehensive Survey","created":"2024-08-23","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":"2411.16771","title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","created":"2024-11-25","cited_by_count":19,"area":null},{"id":"2502.12414","title":"Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Models","created":"2025-02-18","cited_by_count":18,"area":null},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","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":"2407.01942","title":"Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2503.14749","title":"Uncertainty Distillation: Teaching Language Models to Express Semantic Confidence","created":"2025-03-18","cited_by_count":13,"area":null},{"id":"2509.11866","title":"Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding","created":"2025-09-15","cited_by_count":13,"area":null},{"id":"2411.18672","title":"FactCheXcker: Mitigating Measurement Hallucinations in Chest X-ray Report Generation Models","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2504.06666","title":"Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception","created":"2025-04-09","cited_by_count":12,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2506.13045","title":"Continual Learning for Generative AI: From LLMs to MLLMs and Beyond","created":"2025-06-16","cited_by_count":12,"area":null},{"id":"2409.08435","title":"When Context Leads but Parametric Memory Follows in Large Language Models","created":"2024-09-13","cited_by_count":11,"area":null},{"id":"2502.08279","title":"What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations","created":"2025-02-12","cited_by_count":11,"area":null},{"id":"2406.02524","title":"CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks","created":"2024-06-04","cited_by_count":10,"area":null},{"id":"2410.01660","title":"Conformal Generative Modeling with Improved Sample Efficiency through Sequential Greedy Filtering","created":"2024-10-02","cited_by_count":10,"area":null},{"id":"2510.02423","title":"RefineShot: Rethinking Cinematography Understanding with Foundational Skill Evaluation","created":"2025-10-02","cited_by_count":10,"area":null},{"id":"2406.17880","title":"MLLM as Video Narrator: Mitigating Modality Imbalance in Video Moment Retrieval","created":"2024-06-25","cited_by_count":9,"area":null},{"id":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2505.13636","title":"Incentivizing Truthful Language Models via Peer Elicitation Games","created":"2025-05-19","cited_by_count":9,"area":null},{"id":"2509.21972","title":"From Superficial Outputs to Superficial Learning: Risks of Large Language Models in Education","created":"2025-09-26","cited_by_count":9,"area":null},{"id":"2510.16567","title":"Hallucination Benchmark for Speech Foundation Models","created":"2025-10-18","cited_by_count":8,"area":null},{"id":"2505.24347","title":"Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2507.02870","title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","created":"2025-06-06","cited_by_count":7,"area":null},{"id":"2408.07249","title":"Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach","created":"2024-08-14","cited_by_count":5,"area":null},{"id":"2503.00811","title":"Evaluating and Predicting Distorted Human Body Parts for Generated Images","created":"2025-03-02","cited_by_count":5,"area":null},{"id":"2504.05324","title":"Hybrid Retrieval for Hallucination Mitigation in Large Language Models: A Comparative Analysis","created":"2025-02-28","cited_by_count":5,"area":null},{"id":"2505.17099","title":"Learning Interpretable Representations Leads to Semantically Faithful EEG-to-Text Generation","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2506.03028","title":"Protein Inverse Folding From Structure Feedback","created":"2025-06-03","cited_by_count":5,"area":null},{"id":"2511.18271","title":"Beyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models","created":"2025-11-23","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":"2410.01064","title":"Truth or Deceit? A Bayesian Decoding Game Enhances Consistency and Reliability","created":"2024-10-01","cited_by_count":3,"area":null},{"id":"2509.17784","title":"Revealing Multimodal Causality with Large Language Models","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2606.08277","title":"Remember with Confidence: Uncertainty Quantification for Spatio-temporal Memory with Probabilistic Guarantees","created":"2026-06-06","cited_by_count":3,"area":null},{"id":"2409.13606","title":"Towards Child-Inclusive Clinical Video Understanding for Autism Spectrum Disorder","created":"2024-09-20","cited_by_count":2,"area":null},{"id":"2603.15011","title":"Molecular Identifier Visual Prompt and Verifiable Reinforcement Learning for Chemical Reaction Diagram Parsing","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2604.05623","title":"DetailVerifyBench: A Benchmark for Dense Hallucination Localization in Long Image Captions","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2606.03951","title":"Demo2Tutorial: From Human Experience to Multimodal Software Tutorials","created":"2026-06-02","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":"2409.06601","title":"LaMsS: When Large Language Models Meet Self-Skepticism","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2505.18880","title":"REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing","created":"2025-05-24","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":"2507.19870","title":"OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaboration","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2508.03935","title":"CAP-LLM: Context-Augmented Personalized Large Language Models for News Headline Generation","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2508.16974","title":"Hierarchical Contextual Grounding LVLM: Enhancing Fine-Grained Visual-Language Understanding with Robust Grounding","created":"2025-08-23","cited_by_count":1,"area":null},{"id":"2508.21451","title":"MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2511.13351","title":"Dual-LoRA and Quality-Enhanced Pseudo Replay for Multimodal Continual Food Learning","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2511.20965","title":"TrafficLens: Multi-Camera Traffic Video Analysis Using LLMs","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2601.13707","title":"Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2604.18105","title":"NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2604.23860","title":"Exploring Audio Hallucination in Egocentric Video Understanding","created":"2026-04-26","cited_by_count":1,"area":null},{"id":"2605.07593","title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","created":"2026-05-08","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":"2605.18233","title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2607.21061","title":"MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2502.11113","title":"Valuable Hallucinations: Realizable Non-realistic Propositions","created":"2025-02-16","cited_by_count":0,"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":"2504.05254","title":"Explaining Low Perception Model Competency with High-Competency Counterfactuals","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2504.09528","title":"AeroLite: Tag-Guided Lightweight Generation of Aerial Image Captions","created":"2025-04-13","cited_by_count":0,"area":null},{"id":"2507.19885","title":"Zero-shot Performance of Generative AI in Brazilian Portuguese Medical Exam","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2509.13279","title":"HARMONIC: A Content-Centric Cognitive Robotic Architecture","created":"2025-09-16","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":"2603.14609","title":"GroundSet: A Cadastral-Grounded Dataset for Spatial Understanding with Vector Data","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2604.26957","title":"Simulating Validity: Modal Decoupling in MLLM Generated Feedback on Science Drawings","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2605.00873","title":"BRITE: A Benchmark for Reliable and Interpretable T2V Evaluation on Implausible Scenarios","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.20193","title":"Improving Quantized Model Performance in Qualitative Analysis with Multi-Pass Prompt Verification","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2606.08158","title":"Constrained Paraphrase Consistency for LLM Hallucination Detection","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2606.09249","title":"DECIS: Dual-Evidence Corrective Verification for Interpretable Strabismus Diagnostic Decision-Making","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.13211","title":"Hallucination in Medical Imaging AI: A Cross-Modality Analytical Framework for Taxonomy, Detection, and Mitigation under Regulatory Constraints","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.10678","title":"Personalized Emotional Intelligence in Generative AI through Symbolic Affective Reasoning","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.28649","title":"COSI-Lab: Conference Living Lab for Modeling Multi-Perspective Multimodal Social Intention","created":"2026-06-02","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":"2608.26168","title":"Hallucinations in LLMs: A Lifecycle-Based Survey of Causes, Detection, Mitigation, and Prevention","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2609.22647","title":"Math2Visual-X: A Modular Framework for Pedagogically Aligned Lower-Primary Math Visuals Generation","created":"2026-09-18","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}],"next_cursor":null}