{"total":23,"rows":[{"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":"2406.04175","title":"Confabulation: The Surprising Value of Large Language Model Hallucinations","created":"2024-06-06","cited_by_count":43,"area":null},{"id":"2407.20664","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","created":"2024-07-30","cited_by_count":18,"area":null},{"id":"2404.07461","title":"An Audit on the Perspectives and Challenges of Hallucinations in NLP","created":"2024-04-11","cited_by_count":17,"area":null},{"id":"2308.05081","title":"Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling","created":"2023-08-09","cited_by_count":15,"area":null},{"id":"2308.04502","title":"Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition","created":"2023-08-08","cited_by_count":13,"area":null},{"id":"2408.09481","title":"PanoSent: A Panoptic Sextuple Extraction Benchmark for Multimodal Conversational Aspect-based Sentiment Analysis","created":"2024-08-18","cited_by_count":13,"area":null},{"id":"2312.11816","title":"A Dual-way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linking","created":"2023-12-19","cited_by_count":12,"area":null},{"id":"2405.12669","title":"A Survey on Multi-modal Machine Translation: Tasks, Methods and Challenges","created":"2024-05-21","cited_by_count":6,"area":null},{"id":"2503.15019","title":"Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scene","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2406.05620","title":"Beat: Bi-directional One-to-Many Embedding Alignment for Text-based Person Retrieval","created":"2024-06-09","cited_by_count":5,"area":null},{"id":"2501.17261","title":"NUS-Emo at SemEval-2024 Task 3: Instruction-Tuning LLM for Multimodal Emotion-Cause Analysis in Conversations","created":"2024-08-22","cited_by_count":5,"area":null},{"id":"2310.18142","title":"Semi-Supervised Panoptic Narrative Grounding","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2407.13579","title":"Towards Zero-Shot Multimodal Machine Translation","created":"2024-07-18","cited_by_count":3,"area":null},{"id":"2308.04424","title":"A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition","created":"2023-08-08","cited_by_count":2,"area":null},{"id":"2507.17588","title":"Dual-branch Prompting for Multimodal Machine Translation","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2308.04498","title":"DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs","created":"2023-08-08","cited_by_count":1,"area":null},{"id":"2310.09503","title":"JM3D & JM3D-LLM: Elevating 3D Understanding with Joint Multi-modal Cues","created":"2023-10-14","cited_by_count":1,"area":null},{"id":"2407.04801","title":"Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing","created":"2024-07-05","cited_by_count":1,"area":null},{"id":"2410.15312","title":"Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image","created":"2024-10-20","cited_by_count":1,"area":null},{"id":"2505.19507","title":"Multimodal Machine Translation with Visual Scene Graph Pruning","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2312.14966","title":"Dynamic Syntax Mapping: A New Approach to Unsupervised Syntax Parsing","created":"2023-12-18","cited_by_count":0,"area":null}],"next_cursor":null}