{"list":"other","total":53,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2309.14525","title":"Aligning Large Multimodal Models with Factually Augmented RLHF","created":"2023-09-25","cited_by_count":712},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2310.14566","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","created":"2023-10-23","cited_by_count":583},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"2311.17911","title":"OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation","created":"2023-11-29","cited_by_count":478},{"id":"2311.03356","title":"GLaMM: Pixel Grounding Large Multimodal Model","created":"2023-11-06","cited_by_count":455},{"id":"2407.11691","title":"VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models","created":"2024-07-16","cited_by_count":455},{"id":"2312.00849","title":"RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback","created":"2023-12-01","cited_by_count":412},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"2406.04325","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","created":"2024-06-06","cited_by_count":388},{"id":"2402.00253","title":"A Survey on Hallucination in Large Vision-Language Models","created":"2024-02-01","cited_by_count":357},{"id":"2306.03514","title":"Recognize Anything: A Strong Image Tagging Model","created":"2023-06-06","cited_by_count":309},{"id":"2410.17247","title":"PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction","created":"2024-10-22","cited_by_count":294},{"id":"2310.16045","title":"Woodpecker: Hallucination Correction for Multimodal Large Language Models","created":"2023-10-24","cited_by_count":226},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"2403.18715","title":"Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding","created":"2024-03-27","cited_by_count":203},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195},{"id":"2407.21771","title":"Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs","created":"2024-07-31","cited_by_count":179},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132},{"id":"2311.03287","title":"Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challenges","created":"2023-11-06","cited_by_count":131},{"id":"2311.13614","title":"HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data","created":"2023-11-22","cited_by_count":126},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108},{"id":"2408.02032","title":"Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models","created":"2024-08-04","cited_by_count":94},{"id":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90},{"id":"2406.11833","title":"MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs","created":"2024-06-17","cited_by_count":90},{"id":"2405.19092","title":"Benchmarking and Improving Detail Image Caption","created":"2024-05-29","cited_by_count":81},{"id":"2407.08303","title":"DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception","created":"2024-07-11","cited_by_count":73},{"id":"2310.07699","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","created":"2023-10-11","cited_by_count":70},{"id":"2502.05173","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","created":"2025-02-07","cited_by_count":65},{"id":"2403.02325","title":"Contrastive Region Guidance: Improving Grounding in Vision-Language Models without Training","created":"2024-03-04","cited_by_count":64},{"id":"2504.07957","title":"MM-IFEngine: Towards Multimodal Instruction Following","created":"2025-04-10","cited_by_count":42},{"id":"2407.06191","title":"Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images","created":"2024-07-08","cited_by_count":35},{"id":"2410.17637","title":"MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models","created":"2024-10-23","cited_by_count":34},{"id":"2406.14544","title":"Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs","created":"2024-06-20","cited_by_count":32},{"id":"2404.10501","title":"Self-Supervised Visual Preference Alignment","created":"2024-04-16","cited_by_count":31},{"id":"2502.18411","title":"OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference","created":"2025-02-25","cited_by_count":28},{"id":"2410.07167","title":"Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate","created":"2024-10-09","cited_by_count":20},{"id":"2410.17251","title":"Altogether: Image Captioning via Re-aligning Alt-text","created":"2024-10-22","cited_by_count":17},{"id":"2412.01824","title":"X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models","created":"2024-12-02","cited_by_count":15},{"id":"2411.12713","title":"CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs","created":"2024-11-19","cited_by_count":12},{"id":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","cited_by_count":11},{"id":"2412.14233","title":"Enhancing Descriptive Captions with Visual Attributes for Multimodal Perception","created":"2024-12-18","cited_by_count":10}],"next_cursor":null}