{"total":122,"rows":[{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239,"area":"mllm"},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089,"area":"mllm"},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906,"area":"mllm"},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509,"area":"mllm"},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501,"area":null},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421,"area":null},{"id":"2311.06242","title":"Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks","created":"2023-11-10","cited_by_count":410,"area":null},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2211.15518","title":"ReCo: Region-Controlled Text-to-Image Generation","created":"2022-11-23","cited_by_count":179,"area":null},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148,"area":null},{"id":"2406.04449","title":"MAIRA-2: Grounded Radiology Report Generation","created":"2024-06-06","cited_by_count":145,"area":null},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140,"area":null},{"id":"2311.07562","title":"GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation","created":"2023-11-13","cited_by_count":137,"area":"mllm"},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2312.02949","title":"LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models","created":"2023-12-05","cited_by_count":113,"area":"mllm"},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"area":null},{"id":"2311.10081","title":"DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback","created":"2023-11-16","cited_by_count":103,"area":"mllm"},{"id":"2401.06071","title":"GroundingGPT:Language Enhanced Multi-modal Grounding Model","created":"2024-01-11","cited_by_count":101,"area":"mllm"},{"id":"2402.04615","title":"ScreenAI: A Vision-Language Model for UI and Infographics Understanding","created":"2024-02-07","cited_by_count":98,"area":"mllm"},{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97,"area":null},{"id":"2311.04498","title":"NExT-Chat: An LMM for Chat, Detection and Segmentation","created":"2023-11-08","cited_by_count":80,"area":"mllm"},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73,"area":null},{"id":"2312.09158","title":"General Object Foundation Model for Images and Videos at Scale","created":"2023-12-14","cited_by_count":71,"area":null},{"id":"2402.16846","title":"GROUNDHOG: Grounding Large Language Models to Holistic Segmentation","created":"2024-02-26","cited_by_count":70,"area":"mllm"},{"id":"2310.04655","title":"VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models","created":"2023-10-07","cited_by_count":68,"area":null},{"id":"2307.09474","title":"ChatSpot: Bootstrapping Multimodal LLMs via Precise Referring Instruction Tuning","created":"2023-07-18","cited_by_count":65,"area":"mllm"},{"id":"2308.14103","title":"Towards Unified Token Learning for Vision-Language Tracking","created":"2023-08-27","cited_by_count":62,"area":null},{"id":"2211.09808","title":"Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2305.15328","title":"Visual Programming for Text-to-Image Generation and Evaluation","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2312.12423","title":"Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model","created":"2023-12-19","cited_by_count":53,"area":"mllm"},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2305.14302","title":"VIP5: Towards Multimodal Foundation Models for Recommendation","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45,"area":"lr"},{"id":"2401.12503","title":"Small Language Model Meets with Reinforced Vision Vocabulary","created":"2024-01-23","cited_by_count":43,"area":"mllm"},{"id":"2404.00906","title":"From Pixels to Graphs: Open-Vocabulary Scene Graph Generation with Vision-Language Models","created":"2024-04-01","cited_by_count":43,"area":"mllm"},{"id":"2406.01920","title":"CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models","created":"2024-06-04","cited_by_count":38,"area":"mllm"},{"id":"2409.17531","title":"SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion","created":"2024-09-26","cited_by_count":36,"area":null},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2311.14552","title":"Griffon: Spelling out All Object Locations at Any Granularity with Large Language Models","created":"2023-11-24","cited_by_count":31,"area":"mllm"},{"id":"2404.13400","title":"HiVG: Hierarchical Multimodal Fine-grained Modulation for Visual Grounding","created":"2024-04-20","cited_by_count":31,"area":null},{"id":"2405.03685","title":"Language-Image Models with 3D Understanding","created":"2024-05-06","cited_by_count":31,"area":"mllm"},{"id":"2205.11169","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","created":"2022-05-23","cited_by_count":30,"area":"mllm"},{"id":"2209.13959","title":"Dynamic MDETR: A Dynamic Multimodal Transformer Decoder for Visual Grounding","created":"2022-09-28","cited_by_count":29,"area":null},{"id":"2312.02433","title":"Lenna: Language Enhanced Reasoning Detection Assistant","created":"2023-12-05","cited_by_count":29,"area":"lr"},{"id":"2403.09333","title":"Griffon v2: Advancing Multimodal Perception with High-Resolution Scaling and Visual-Language Co-Referring","created":"2024-03-14","cited_by_count":29,"area":"mllm"},{"id":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28,"area":"synth"},{"id":"2410.08021","title":"OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling","created":"2024-10-10","cited_by_count":28,"area":null},{"id":"2304.03435","title":"Towards Unified Scene Text Spotting based on Sequence Generation","created":"2023-04-07","cited_by_count":27,"area":null},{"id":"2407.01851","title":"Meerkat: Audio-Visual Large Language Model for Grounding in Space and Time","created":"2024-07-01","cited_by_count":26,"area":"mllm"},{"id":"2507.23779","title":"Phi-Ground Tech Report: Advancing Perception in GUI Grounding","created":"2025-07-31","cited_by_count":25,"area":"lr"},{"id":"2403.07304","title":"Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models","created":"2024-03-12","cited_by_count":24,"area":"mllm"},{"id":"2403.09394","title":"GiT: Towards Generalist Vision Transformer through Universal Language Interface","created":"2024-03-14","cited_by_count":24,"area":null},{"id":"2312.11967","title":"Context Disentangling and Prototype Inheriting for Robust Visual Grounding","created":"2023-12-19","cited_by_count":23,"area":null},{"id":"2210.04135","title":"VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment","created":"2022-10-09","cited_by_count":20,"area":"mllm"},{"id":"2503.13026","title":"HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model","created":"2025-03-17","cited_by_count":20,"area":"mllm"},{"id":"2312.01564","title":"APoLLo: Unified Adapter and Prompt Learning for Vision Language Models","created":"2023-12-04","cited_by_count":19,"area":"mllm"},{"id":"2404.15770","title":"ChEX: Interactive Localization and Region Description in Chest X-rays","created":"2024-04-24","cited_by_count":19,"area":null},{"id":"2503.12652","title":"UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing","created":"2025-03-16","cited_by_count":19,"area":"diffusion"},{"id":"2310.04716","title":"Reinforced UI Instruction Grounding: Towards a Generic UI Task Automation API","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2503.13068","title":"Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation","created":"2025-03-17","cited_by_count":18,"area":"lr"},{"id":"2504.04974","title":"Towards Visual Text Grounding of Multimodal Large Language Model","created":"2025-04-07","cited_by_count":18,"area":"mllm"},{"id":"2307.11558","title":"Advancing Visual Grounding with Scene Knowledge: Benchmark and Method","created":"2023-07-21","cited_by_count":17,"area":null},{"id":"2312.09237","title":"Pixel Aligned Language Models","created":"2023-12-14","cited_by_count":17,"area":"mllm"},{"id":"2202.06574","title":"I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning","created":"2022-02-14","cited_by_count":16,"area":null},{"id":"2310.03291","title":"Expedited Training of Visual Conditioned Language Generation via Redundancy Reduction","created":"2023-10-05","cited_by_count":15,"area":"mllm"},{"id":"2407.16696","title":"PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2306.01242","title":"Responsible Task Automation: Empowering Large Language Models as Responsible Task Automators","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2402.08657","title":"PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs","created":"2024-02-13","cited_by_count":14,"area":"mllm"},{"id":"2311.13258","title":"ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation","created":"2023-11-22","cited_by_count":13,"area":"mllm"},{"id":"2312.02694","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2205.09256","title":"Training Vision-Language Transformers from Captions","created":"2022-05-19","cited_by_count":11,"area":null},{"id":"2305.17903","title":"Deeply Coupled Cross-Modal Prompt Learning","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2312.06731","title":"Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator","created":"2023-12-11","cited_by_count":11,"area":"mllm"},{"id":"2404.13594","title":"Lost in Space: Probing Fine-grained Spatial Understanding in Vision and Language Resamplers","created":"2024-04-21","cited_by_count":11,"area":null},{"id":"2411.09691","title":"Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models","created":"2024-11-14","cited_by_count":11,"area":"mllm"},{"id":"2303.16990","title":"What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions","created":"2023-03-29","cited_by_count":10,"area":null},{"id":"2509.10345","title":"Towards Understanding Visual Grounding in Visual Language Models","created":"2025-09-12","cited_by_count":10,"area":"mllm"},{"id":"2311.04067","title":"Multitask Multimodal Prompted Training for Interactive Embodied Task Completion","created":"2023-11-07","cited_by_count":9,"area":null},{"id":"2312.03026","title":"Uni3DL: Unified Model for 3D and Language Understanding","created":"2023-12-05","cited_by_count":9,"area":null},{"id":"2311.12327","title":"Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models","created":"2023-11-21","cited_by_count":8,"area":"mllm"},{"id":"2509.13747","title":"Improving Generalized Visual Grounding with Instance-aware Joint Learning","created":"2025-09-17","cited_by_count":8,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2407.02389","title":"SafaRi:Adaptive Sequence Transformer for Weakly Supervised Referring Expression Segmentation","created":"2024-07-02","cited_by_count":6,"area":null},{"id":"2409.05395","title":"Shaking Up VLMs: Comparing Transformers and Structured State Space Models for Vision & Language Modeling","created":"2024-09-09","cited_by_count":6,"area":"mllm"},{"id":"2204.07913","title":"A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression Comprehension","created":"2022-04-17","cited_by_count":5,"area":null},{"id":"2307.03254","title":"Vision Language Transformers: A Survey","created":"2023-07-06","cited_by_count":5,"area":"mllm"},{"id":"2402.17172","title":"Lane2Seq: Towards Unified Lane Detection via Sequence Generation","created":"2024-02-27","cited_by_count":5,"area":null},{"id":"2403.07692","title":"Masked AutoDecoder is Effective Multi-Task Vision Generalist","created":"2024-03-12","cited_by_count":4,"area":null},{"id":"2403.13513","title":"What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models","created":"2024-03-20","cited_by_count":4,"area":"mllm"},{"id":"2305.03204","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","created":"2023-05-04","cited_by_count":3,"area":"lr"},{"id":"2305.07019","title":"Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts","created":"2023-05-11","cited_by_count":3,"area":"mllm"},{"id":"2309.12382","title":"SCOB: Universal Text Understanding via Character-wise Supervised Contrastive Learning with Online Text Rendering for Bridging Domain Gap","created":"2023-09-21","cited_by_count":3,"area":null},{"id":"2405.00260","title":"CREPE: Coordinate-Aware End-to-End Document Parser","created":"2024-05-01","cited_by_count":3,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2510.14374","title":"Spatial Preference Rewarding for MLLMs Spatial Understanding","created":"2025-10-16","cited_by_count":3,"area":"mllm"},{"id":"2512.24561","title":"RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarios","created":"2025-12-31","cited_by_count":3,"area":null}],"next_cursor":"100"}