{"total":131,"rows":[{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776,"area":"lr"},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"area":null},{"id":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526,"area":"lr"},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297,"area":null},{"id":"2305.17216","title":"Generating Images with Multimodal Language Models","created":"2023-05-26","cited_by_count":260,"area":"mllm"},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2307.05222","title":"Emu: Generative Pretraining in Multimodality","created":"2023-07-11","cited_by_count":157,"area":null},{"id":"2308.10741","title":"On the Adversarial Robustness of Multi-Modal Foundation Models","created":"2023-08-21","cited_by_count":145,"area":"safety"},{"id":"2406.08394","title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","created":"2024-06-12","cited_by_count":137,"area":"mllm"},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136,"area":"lr"},{"id":"2402.12336","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","created":"2024-02-19","cited_by_count":120,"area":"mllm"},{"id":"2306.05179","title":"M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models","created":"2023-06-08","cited_by_count":110,"area":null},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2411.16044","title":"ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration","created":"2024-11-25","cited_by_count":103,"area":"mllm"},{"id":"2310.08825","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models","created":"2023-10-13","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":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90,"area":"lr"},{"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":"2404.15406","title":"Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs","created":"2024-04-23","cited_by_count":80,"area":"mllm"},{"id":"2312.17240","title":"LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model","created":"2023-12-28","cited_by_count":71,"area":"lr"},{"id":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","cited_by_count":69,"area":null},{"id":"2412.03735","title":"VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding","created":"2024-12-04","cited_by_count":68,"area":"mllm"},{"id":"2512.10942","title":"VL-JEPA: Joint Embedding Predictive Architecture for Vision-language","created":"2025-12-11","cited_by_count":68,"area":"mllm"},{"id":"2305.14800","title":"Exploring Diverse In-Context Configurations for Image Captioning","created":"2023-05-24","cited_by_count":63,"area":null},{"id":"2405.08295","title":"SpeechVerse: A Large-scale Generalizable Audio Language Model","created":"2024-05-14","cited_by_count":63,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2305.11490","title":"LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation","created":"2023-05-19","cited_by_count":57,"area":"lr"},{"id":"2407.13766","title":"Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark","created":"2024-07-18","cited_by_count":55,"area":"mllm"},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2306.16410","title":"Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language","created":"2023-06-28","cited_by_count":53,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2408.10433","title":"CLIP-DPO: Vision-Language Models as a Source of Preference for Fixing Hallucinations in LVLMs","created":"2024-08-19","cited_by_count":49,"area":"mllm"},{"id":"2310.12973","title":"Frozen Transformers in Language Models Are Effective Visual Encoder Layers","created":"2023-10-19","cited_by_count":39,"area":null},{"id":"2402.01763","title":"When Large Language Models Meet Vector Databases: A Survey","created":"2024-01-30","cited_by_count":39,"area":null},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35,"area":"mllm"},{"id":"2501.15140","title":"Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models","created":"2025-01-25","cited_by_count":31,"area":"mllm"},{"id":"2402.06475","title":"Large Language Models for Captioning and Retrieving Remote Sensing Images","created":"2024-02-09","cited_by_count":30,"area":null},{"id":"2403.08857","title":"DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation","created":"2024-03-13","cited_by_count":26,"area":null},{"id":"2403.17343","title":"Residual-based Language Models are Free Boosters for Biomedical Imaging","created":"2024-03-26","cited_by_count":24,"area":null},{"id":"2404.18624","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2309.08637","title":"TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild","created":"2023-09-14","cited_by_count":22,"area":null},{"id":"2311.09580","title":"MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts","created":"2023-11-16","cited_by_count":21,"area":null},{"id":"2312.03584","title":"Context Diffusion: In-Context Aware Image Generation","created":"2023-12-06","cited_by_count":21,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2505.05528","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","created":"2025-05-08","cited_by_count":21,"area":"mllm"},{"id":"2408.11813","title":"SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs","created":"2024-08-21","cited_by_count":19,"area":"mllm"},{"id":"2310.09036","title":"MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks","created":"2023-10-13","cited_by_count":18,"area":"mllm"},{"id":"2403.04735","title":"SnapNTell: Enhancing Entity-Centric Visual Question Answering with Retrieval Augmented Multimodal LLM","created":"2024-03-07","cited_by_count":18,"area":"mllm"},{"id":"2403.13499","title":"Improved Baselines for Data-efficient Perceptual Augmentation of LLMs","created":"2024-03-20","cited_by_count":18,"area":null},{"id":"2510.14605","title":"Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and Filtering","created":"2025-10-16","cited_by_count":17,"area":"mllm"},{"id":"2311.07622","title":"Pretrain like Your Inference: Masked Tuning Improves Zero-Shot Composed Image Retrieval","created":"2023-11-13","cited_by_count":14,"area":"mllm"},{"id":"2402.08657","title":"PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs","created":"2024-02-13","cited_by_count":14,"area":"mllm"},{"id":"2407.13851","title":"X-Former: Unifying Contrastive and Reconstruction Learning for MLLMs","created":"2024-07-18","cited_by_count":14,"area":"mllm"},{"id":"2404.15516","title":"Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval","created":"2024-04-23","cited_by_count":13,"area":"mllm"},{"id":"2506.18158","title":"Chain-of-Memory: Enhancing GUI Agents for Cross-Application Navigation","created":"2025-06-22","cited_by_count":13,"area":"mllm"},{"id":"2507.19599","title":"Object-centric Video Question Answering with Visual Grounding and Referring","created":"2025-07-25","cited_by_count":13,"area":null},{"id":"2310.17050","title":"Exploring Question Decomposition for Zero-Shot VQA","created":"2023-10-25","cited_by_count":12,"area":null},{"id":"2402.18695","title":"Grounding Language Models for Visual Entity Recognition","created":"2024-02-28","cited_by_count":12,"area":null},{"id":"2409.16667","title":"A Character-Centric Creative Story Generation via Imagination","created":"2024-09-25","cited_by_count":12,"area":null},{"id":"2411.05254","title":"Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding","created":"2024-11-08","cited_by_count":12,"area":"mllm"},{"id":"2404.09632","title":"Bridging Vision and Language Spaces with Assignment Prediction","created":"2024-04-15","cited_by_count":11,"area":null},{"id":"2404.15790","title":"Leveraging Large Language Models for Multimodal Search","created":"2024-04-24","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":"2510.05184","title":"Representation Potentials of Foundation Models for Multimodal Alignment: A Survey","created":"2025-10-05","cited_by_count":11,"area":null},{"id":"2503.10183","title":"Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding","created":"2025-03-13","cited_by_count":10,"area":"mllm"},{"id":"2509.10345","title":"Towards Understanding Visual Grounding in Visual Language Models","created":"2025-09-12","cited_by_count":10,"area":"mllm"},{"id":"2310.08577","title":"Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models","created":"2023-10-12","cited_by_count":9,"area":"mllm"},{"id":"2402.10977","title":"Generative AI and Process Systems Engineering: The Next Frontier","created":"2024-02-15","cited_by_count":9,"area":null},{"id":"2505.18561","title":"CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2408.05926","title":"BI-MDRG: Bridging Image History in Multimodal Dialogue Response Generation","created":"2024-08-12","cited_by_count":8,"area":null},{"id":"2503.21851","title":"On Large Multimodal Models as Open-World Image Classifiers","created":"2025-03-27","cited_by_count":8,"area":"mllm"},{"id":"2505.19952","title":"Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2312.04552","title":"Generating Illustrated Instructions","created":"2023-12-07","cited_by_count":7,"area":null},{"id":"2403.10492","title":"Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning","created":"2024-03-15","cited_by_count":7,"area":"mllm"},{"id":"2405.19333","title":"Multi-Modal Generative Embedding Model","created":"2024-05-29","cited_by_count":7,"area":null},{"id":"2503.07503","title":"Think Before You Segment: High-Quality Reasoning Segmentation with GPT Chain of Thoughts","created":"2025-03-10","cited_by_count":7,"area":"lr"},{"id":"2503.09402","title":"VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary","created":"2025-03-12","cited_by_count":7,"area":null},{"id":"2405.15341","title":"V-Zen: Efficient GUI Understanding and Precise Grounding With A Novel Multimodal LLM","created":"2024-05-24","cited_by_count":6,"area":"mllm"},{"id":"2410.18715","title":"ChatSearch: a Dataset and a Generative Retrieval Model for General Conversational Image Retrieval","created":"2024-10-24","cited_by_count":6,"area":null},{"id":"2408.05334","title":"Revisiting Multi-Modal LLM Evaluation","created":"2024-08-09","cited_by_count":5,"area":"mllm"},{"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":"2410.19925","title":"Improving Multimodal Large Language Models Using Continual Learning","created":"2024-10-25","cited_by_count":5,"area":"mllm"},{"id":"2505.19707","title":"MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2312.07532","title":"Interfacing Foundation Models' Embeddings","created":"2023-12-12","cited_by_count":4,"area":null},{"id":"2510.24331","title":"What do vision-language models see in the context? Investigating multimodal in-context learning","created":"2025-10-28","cited_by_count":4,"area":"mllm"},{"id":"2604.04496","title":"The Indra Representation Hypothesis for Multimodal Alignment","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2403.06935","title":"Naming, Describing, and Quantifying Visual Objects in Humans and LLMs","created":"2024-03-11","cited_by_count":3,"area":null},{"id":"2403.15209","title":"MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2406.15768","title":"MR-MLLM: Mutual Reinforcement of Multimodal Comprehension and Vision Perception","created":"2024-06-22","cited_by_count":3,"area":"mllm"},{"id":"2407.11449","title":"Controllable Contextualized Image Captioning: Directing the Visual Narrative through User-Defined Highlights","created":"2024-07-16","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":"2412.20750","title":"Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking","created":"2024-12-30","cited_by_count":3,"area":"mllm"},{"id":"2307.16395","title":"Bridging the Gap: Exploring the Capabilities of Bridge-Architectures for Complex Visual Reasoning Tasks","created":"2023-07-31","cited_by_count":2,"area":"lr"},{"id":"2404.13530","title":"Listen Then See: Video Alignment with Speaker Attention","created":"2024-04-21","cited_by_count":2,"area":null}],"next_cursor":"100"}