{"total":69,"rows":[{"id":"2402.00253","title":"A Survey on Hallucination in Large Vision-Language Models","created":"2024-02-01","cited_by_count":357,"area":"mllm"},{"id":"2312.11557","title":"SAI3D: Segment Any Instance in 3D Scenes","created":"2023-12-17","cited_by_count":90,"area":null},{"id":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79,"area":null},{"id":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","cited_by_count":77,"area":"mllm"},{"id":"2503.06661","title":"AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP","created":"2025-03-09","cited_by_count":73,"area":null},{"id":"2303.10431","title":"DeAR: Debiasing Vision-Language Models with Additive Residuals","created":"2023-03-18","cited_by_count":70,"area":"mllm"},{"id":"2505.16652","title":"Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding","created":"2025-05-22","cited_by_count":43,"area":"mllm"},{"id":"2411.14517","title":"The Double-Ellipsoid Geometry of CLIP","created":"2024-11-21","cited_by_count":42,"area":null},{"id":"2306.08832","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","created":"2023-06-15","cited_by_count":41,"area":"mllm"},{"id":"2305.18010","title":"Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models","created":"2023-05-29","cited_by_count":38,"area":"mllm"},{"id":"2305.14014","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2411.15268","title":"ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models","created":"2024-11-22","cited_by_count":30,"area":"mllm"},{"id":"2305.12476","title":"Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models","created":"2023-05-21","cited_by_count":27,"area":"mllm"},{"id":"2305.17388","title":"MPCHAT: Towards Multimodal Persona-Grounded Conversation","created":"2023-05-27","cited_by_count":24,"area":null},{"id":"2210.01946","title":"Affection: Learning Affective Explanations for Real-World Visual Data","created":"2022-10-04","cited_by_count":19,"area":null},{"id":"2307.15904","title":"Sat2Cap: Mapping Fine-Grained Textual Descriptions from Satellite Images","created":"2023-07-29","cited_by_count":19,"area":null},{"id":"2212.04119","title":"DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2307.16686","title":"Guiding Image Captioning Models Toward More Specific Captions","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2410.07336","title":"Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training","created":"2024-10-09","cited_by_count":16,"area":null},{"id":"2302.06891","title":"UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training","created":"2023-02-14","cited_by_count":14,"area":"mllm"},{"id":"2304.01662","title":"Cross-Domain Image Captioning with Discriminative Finetuning","created":"2023-04-04","cited_by_count":14,"area":null},{"id":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"id":"2308.01126","title":"Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model","created":"2023-08-02","cited_by_count":10,"area":"mllm"},{"id":"2308.12045","title":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","created":"2023-08-23","cited_by_count":10,"area":null},{"id":"2309.10790","title":"Guide Your Agent with Adaptive Multimodal Rewards","created":"2023-09-19","cited_by_count":10,"area":"offlinerl"},{"id":"2501.12011","title":"Reference-free Evaluation Metrics for Text Generation: A Survey","created":"2025-01-21","cited_by_count":9,"area":null},{"id":"2502.20750","title":"Mitigating Hallucinations in Large Vision-Language Models by Adaptively Constraining Information Flow","created":"2025-02-28","cited_by_count":9,"area":"mllm"},{"id":"2312.04539","title":"Auto-Vocabulary Semantic Segmentation","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2508.02419","title":"Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens","created":"2025-08-04","cited_by_count":8,"area":"lr"},{"id":"2208.04254","title":"Distinctive Image Captioning via CLIP Guided Group Optimization","created":"2022-08-08","cited_by_count":6,"area":null},{"id":"2404.17498","title":"Learning text-to-video retrieval from image captioning","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2407.11683","title":"Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2508.07877","title":"Selective Contrastive Learning for Weakly Supervised Affordance Grounding","created":"2025-08-11","cited_by_count":6,"area":null},{"id":"2303.08389","title":"PR-MCS: Perturbation Robust Metric for MultiLingual Image Captioning","created":"2023-03-15","cited_by_count":5,"area":null},{"id":"2406.09126","title":"3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2408.14547","title":"Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization","created":"2024-08-26","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":"2212.03230","title":"Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learning","created":"2022-12-06","cited_by_count":4,"area":null},{"id":"2306.08818","title":"Pragmatic Inference with a CLIP Listener for Contrastive Captioning","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2402.11572","title":"Cobra Effect in Reference-Free Image Captioning Metrics","created":"2024-02-18","cited_by_count":4,"area":null},{"id":"2504.09895","title":"Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data","created":"2025-04-14","cited_by_count":4,"area":"alignment"},{"id":"2508.01678","title":"Cure or Poison? Embedding Instructions Visually Alters Hallucination in Vision-Language Models","created":"2025-08-03","cited_by_count":4,"area":"mllm"},{"id":"2512.16145","title":"MRG-R1: Reinforcement Learning for Clinically Aligned Medical Report Generation","created":"2025-12-18","cited_by_count":4,"area":null},{"id":"2306.15111","title":"Self-Supervised Image Captioning with CLIP","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2308.02862","title":"Improving Generalization of Image Captioning with Unsupervised Prompt Learning","created":"2023-08-05","cited_by_count":2,"area":null},{"id":"2402.13936","title":"Distinctive Image Captioning: Leveraging Ground Truth Captions in CLIP Guided Reinforcement Learning","created":"2024-02-21","cited_by_count":2,"area":null},{"id":"2509.03897","title":"SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation","created":"2025-09-04","cited_by_count":2,"area":null},{"id":"2605.24702","title":"Do Image-Text Metrics Respect Semantic Invariances?","created":"2026-05-23","cited_by_count":2,"area":null},{"id":"2310.19130","title":"Women Wearing Lipstick: Measuring the Bias Between an Object and Its Related Gender","created":"2023-10-29","cited_by_count":1,"area":null},{"id":"2312.01575","title":"A Challenging Multimodal Video Summary: Simultaneously Extracting and Generating Keyframe-Caption Pairs from Video","created":"2023-12-04","cited_by_count":1,"area":null},{"id":"2404.17534","title":"Exploring the Distinctiveness and Fidelity of the Descriptions Generated by Large Vision-Language Models","created":"2024-04-26","cited_by_count":1,"area":"mllm"},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2408.15714","title":"Pixels to Prose: Understanding the art of Image Captioning","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2409.17109","title":"Unveiling Ontological Commitment in Multi-Modal Foundation Models","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2410.23603","title":"Using Multimodal Deep Neural Networks to Disentangle Language from Visual Aesthetics","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2506.12411","title":"InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning","created":"2025-06-14","cited_by_count":1,"area":"safety"},{"id":"2507.20077","title":"The Devil is in the EOS: Sequence Training for Detailed Image Captioning","created":"2025-07-26","cited_by_count":1,"area":"mllm"},{"id":"2509.14571","title":"VisMoDAl: Visual Analytics for Evaluating and Improving Corruption Robustness of Vision-Language Models","created":"2025-09-18","cited_by_count":1,"area":"mllm"},{"id":"2307.14750","title":"Exploring Annotation-free Image Captioning with Retrieval-augmented Pseudo Sentence Generation","created":"2023-07-27","cited_by_count":0,"area":"rag"},{"id":"2408.16827","title":"Fluent and Accurate Image Captioning with a Self-Trained Reward Model","created":"2024-08-29","cited_by_count":0,"area":"alignment"},{"id":"2509.19207","title":"Long Story Short: Disentangling Compositionality and Long-Caption Understanding in Contrastive VLMs","created":"2025-09-23","cited_by_count":0,"area":"mllm"},{"id":"2601.08026","title":"FigEx2: Visual-Conditioned Panel Detection and Captioning for Scientific Compound Figures","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2603.01696","title":"Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning","created":"2026-03-02","cited_by_count":0,"area":"mllm"},{"id":"2606.19103","title":"ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.21305","title":"Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning","created":"2026-08-21","cited_by_count":0,"area":"lr"},{"id":"2609.00591","title":"A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss","created":"2026-09-01","cited_by_count":0,"area":"mllm"},{"id":"2609.07229","title":"Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly Detection","created":"2026-09-07","cited_by_count":0,"area":"mllm"},{"id":"2610.01800","title":"LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}