{"total":100,"rows":[{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109,"area":null},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255,"area":null},{"id":"2407.01449","title":"ColPali: Efficient Document Retrieval with Vision Language Models","created":"2024-06-27","cited_by_count":195,"area":"mllm"},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132,"area":null},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126,"area":"mllm"},{"id":"2407.10920","title":"Benchmarking Vision Language Models for Cultural Understanding","created":"2024-07-15","cited_by_count":101,"area":"mllm"},{"id":"2410.14669","title":"NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples","created":"2024-10-18","cited_by_count":97,"area":"mllm"},{"id":"2506.18902","title":"jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval","created":"2025-06-23","cited_by_count":76,"area":null},{"id":"2507.22062","title":"Meta CLIP 2: A Worldwide Scaling Recipe","created":"2025-07-29","cited_by_count":64,"area":"mllm"},{"id":"2311.07463","title":"MEGAVERSE: Benchmarking Large Language Models Across Languages, Modalities, Models and Tasks","created":"2023-11-13","cited_by_count":57,"area":null},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2410.07112","title":"VHELM: A Holistic Evaluation of Vision Language Models","created":"2024-10-09","cited_by_count":53,"area":"mllm"},{"id":"2404.04925","title":"Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers","created":"2024-04-07","cited_by_count":51,"area":"lr"},{"id":"2406.10118","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","created":"2024-06-14","cited_by_count":43,"area":null},{"id":"2307.06930","title":"mBLIP: Efficient Bootstrapping of Multilingual Vision-LLMs","created":"2023-07-13","cited_by_count":41,"area":"mllm"},{"id":"2412.08802","title":"jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images","created":"2024-12-11","cited_by_count":37,"area":null},{"id":"2308.09991","title":"AltDiffusion: A Multilingual Text-to-Image Diffusion Model","created":"2023-08-19","cited_by_count":30,"area":"diffusion"},{"id":"2212.10408","title":"Geographic and Geopolitical Biases of Language Models","created":"2022-12-20","cited_by_count":29,"area":null},{"id":"2302.08268","title":"Retrieval-augmented Image Captioning","created":"2023-02-16","cited_by_count":29,"area":"rag"},{"id":"2407.03791","title":"M5 -- A Diverse Benchmark to Assess the Performance of Large Multimodal Models Across Multilingual and Multicultural Vision-Language Tasks","created":"2024-07-04","cited_by_count":27,"area":"mllm"},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2303.10056","title":"GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation","created":"2023-03-17","cited_by_count":25,"area":"diffusion"},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"area":null},{"id":"2302.11217","title":"Connecting Vision and Language with Video Localized Narratives","created":"2023-02-22","cited_by_count":24,"area":null},{"id":"2309.01859","title":"NLLB-CLIP -- train performant multilingual image retrieval model on a budget","created":"2023-09-04","cited_by_count":24,"area":null},{"id":"2510.11693","title":"Scaling Language-Centric Omnimodal Representation Learning","created":"2025-10-13","cited_by_count":22,"area":"mllm"},{"id":"2406.19097","title":"Fairness and Bias in Multimodal AI: A Survey","created":"2024-06-27","cited_by_count":20,"area":"mllm"},{"id":"2502.07617","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","created":"2025-02-11","cited_by_count":19,"area":"mllm"},{"id":"2508.04227","title":"Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting","created":"2025-08-06","cited_by_count":18,"area":"mllm"},{"id":"2305.19821","title":"LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting","created":"2023-05-31","cited_by_count":17,"area":"rag"},{"id":"2405.13777","title":"No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models","created":"2024-05-22","cited_by_count":16,"area":"mllm"},{"id":"2508.07414","title":"Grounding Multilingual Multimodal LLMs With Cultural Knowledge","created":"2025-08-10","cited_by_count":16,"area":"mllm"},{"id":"2412.06745","title":"ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities","created":"2024-12-09","cited_by_count":15,"area":null},{"id":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"area":null},{"id":"2411.05001","title":"Analyzing The Language of Visual Tokens","created":"2024-11-07","cited_by_count":12,"area":null},{"id":"2411.11927","title":"FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training","created":"2024-11-18","cited_by_count":12,"area":null},{"id":"2306.08658","title":"Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations","created":"2023-06-14","cited_by_count":11,"area":null},{"id":"2407.02333","title":"Why do LLaVA Vision-Language Models Reply to Images in English?","created":"2024-07-02","cited_by_count":11,"area":"mllm"},{"id":"2410.15453","title":"CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts","created":"2024-10-20","cited_by_count":11,"area":null},{"id":"2503.22610","title":"Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users","created":"2025-03-28","cited_by_count":11,"area":"mllm"},{"id":"2303.17376","title":"A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision","created":"2023-03-30","cited_by_count":10,"area":null},{"id":"2502.07503","title":"Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems","created":"2025-02-11","cited_by_count":10,"area":null},{"id":"2209.05401","title":"MaXM: Towards Multilingual Visual Question Answering","created":"2022-09-12","cited_by_count":9,"area":null},{"id":"2406.08707","title":"mOSCAR: A Large-scale Multilingual and Multimodal Document-level Corpus","created":"2024-06-13","cited_by_count":9,"area":"mllm"},{"id":"2505.20728","title":"Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Models","created":"2025-05-27","cited_by_count":9,"area":"lr"},{"id":"2310.14356","title":"Semantic and Expressive Variation in Image Captions Across Languages","created":"2023-10-22","cited_by_count":8,"area":null},{"id":"2307.10188","title":"Several categories of Large Language Models (LLMs): A Short Survey","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2505.19108","title":"CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models","created":"2025-05-25","cited_by_count":7,"area":"lr"},{"id":"2508.03164","title":"ChartCap: Mitigating Hallucination of Dense Chart Captioning","created":"2025-08-05","cited_by_count":7,"area":"mllm"},{"id":"2409.16646","title":"Cross-Lingual and Cross-Cultural Variation in Image Descriptions","created":"2024-09-25","cited_by_count":5,"area":null},{"id":"2410.02027","title":"Quantifying the Gaps Between Translation and Native Perception in Training for Multimodal, Multilingual Retrieval","created":"2024-10-02","cited_by_count":5,"area":"mllm"},{"id":"2502.06600","title":"Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2502.12852","title":"MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching","created":"2025-02-18","cited_by_count":5,"area":null},{"id":"2503.22577","title":"Breaking Language Barriers in Visual Language Models via Multilingual Textual Regularization","created":"2025-03-28","cited_by_count":4,"area":"mllm"},{"id":"2309.03921","title":"C-CLIP: Contrastive Image-Text Encoders to Close the Descriptive-Commentative Gap","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2412.01271","title":"MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost","created":"2024-12-02","cited_by_count":3,"area":"diffusion"},{"id":"2503.09313","title":"xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge Distillation","created":"2025-03-12","cited_by_count":3,"area":"distill"},{"id":"2505.08910","title":"Behind Maya: Building a Multilingual Vision Language Model","created":"2025-05-13","cited_by_count":3,"area":"mllm"},{"id":"2510.23896","title":"AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages","created":"2025-10-27","cited_by_count":3,"area":"rag"},{"id":"2602.14073","title":"Annotation-Efficient Vision-Language Model Adaptation to the Polish Language Using the LLaVA Framework","created":"2026-02-15","cited_by_count":3,"area":"mllm"},{"id":"2602.14653","title":"Is Information Density Uniform when Utterances are Grounded on Perception and Discourse?","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2604.05900","title":"AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis","created":"2026-04-07","cited_by_count":3,"area":"mllm"},{"id":"2406.02331","title":"Translation Deserves Better: Analyzing Translation Artifacts in Cross-lingual Visual Question Answering","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2407.02623","title":"Uplifting Lower-Income Data: Strategies for Socioeconomic Perspective Shifts in Large Multi-modal Models","created":"2024-07-02","cited_by_count":2,"area":null},{"id":"2505.14160","title":"Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models","created":"2025-05-20","cited_by_count":2,"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":"2501.04513","title":"Improving Image Captioning by Mimicking Human Reformulation Feedback at Inference-time","created":"2025-01-08","cited_by_count":1,"area":"alignment"},{"id":"2504.14359","title":"A Multimodal Recaptioning Framework to Account for Perceptual Diversity Across Languages in Vision-Language Modeling","created":"2025-04-19","cited_by_count":1,"area":"mllm"},{"id":"2505.23008","title":"Synthetic Document Question Answering in Hungarian","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2509.17523","title":"Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2509.22123","title":"Multilingual Vision-Language Models, A Survey","created":"2025-09-26","cited_by_count":1,"area":"mllm"},{"id":"2509.23370","title":"GRAPE: Let GRPO Supervise Query Rewriting by Ranking for Retrieval","created":"2025-09-27","cited_by_count":1,"area":"lr"},{"id":"2510.06820","title":"Efficient Discriminative Joint Encoders for Large Scale Vision-Language Reranking","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2510.18795","title":"ProCLIP: Progressive Vision-Language Alignment via LLM-based Embedder","created":"2025-10-21","cited_by_count":1,"area":null},{"id":"2512.05959","title":"M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG","created":"2025-12-05","cited_by_count":1,"area":"mllm"},{"id":"2601.06891","title":"CLIMP: Contrastive Language-Image Mamba Pretraining","created":"2026-01-11","cited_by_count":1,"area":"ssm"},{"id":"2601.10649","title":"MINERVA-Cultural: A Benchmark for Cultural and Multilingual Long Video Reasoning","created":"2026-01-15","cited_by_count":1,"area":"lr"},{"id":"2605.30126","title":"PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding","created":"2026-05-28","cited_by_count":1,"area":"mllm"},{"id":"2404.08666","title":"Revealing Trends in Datasets from the 2022 ACL and EMNLP Conferences","created":"2024-03-31","cited_by_count":0,"area":null},{"id":"2407.09495","title":"Image captioning in different languages","created":"2024-05-31","cited_by_count":0,"area":null},{"id":"2409.03911","title":"The Role of Generative Systems in Historical Photography Management: A Case Study on Catalan Archives","created":"2024-09-05","cited_by_count":0,"area":null},{"id":"2505.02746","title":"Using Knowledge Graphs to harvest datasets for efficient CLIP model training","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2505.13273","title":"EMoE: Training-Free Expert Disagreement for Uncertainty-Aware Text-to-Image Diffusion","created":"2025-05-19","cited_by_count":0,"area":"diffusion"},{"id":"2507.20411","title":"CONCAP: Seeing Beyond English with Concepts Retrieval-Augmented Captioning","created":"2025-07-27","cited_by_count":0,"area":"mllm"},{"id":"2510.09815","title":"Towards Understanding Ambiguity Resolution in Multimodal Inference of Meaning","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.17405","title":"AFRICAPTION: Establishing a New Paradigm for Image Captioning in African Languages","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.22276","title":"WAON: A Large-Scale Japanese Image-Text Dataset for Cultural Adaptation in Contrastive Vision-Language Models","created":"2025-10-25","cited_by_count":0,"area":"mllm"},{"id":"2510.26861","title":"Evaluating Perspectival Biases in Cross-Modal Retrieval","created":"2025-10-30","cited_by_count":0,"area":null},{"id":"2601.10096","title":"Multilingual-To-Multimodal (M2M): Unlocking New Languages with Monolingual Text","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.22678","title":"ViCLIP-OT: The First Foundation Vision-Language Model for Vietnamese Image-Text Retrieval with Optimal Transport","created":"2026-02-26","cited_by_count":0,"area":"mllm"},{"id":"2604.02557","title":"Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and Evaluation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.31401","title":"\"\\^{I}n\\c{t}elegi Rom\\^ane\\c{s}te?'' A Recipe for Romanian Vision-Language Models","created":"2026-05-29","cited_by_count":0,"area":"mllm"},{"id":"2606.17188","title":"Not Truly Multilingual: Script Consistency as a Missing Dimension in VLM Evaluation","created":"2026-06-15","cited_by_count":0,"area":"mllm"},{"id":"2606.20770","title":"Beyond 'One Language, One Script': Quantifying Orthographic Bias in Multilingual VLMs with PuMVR","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2608.23920","title":"Wontopos Tablet 2: Measuring Multilingual and Multimodal Memory Retrieval Without Lexical Matching","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.30725","title":"Where Do Multilingual Vision-Language Encoders Fail on Low-Resource Languages?","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.25298","title":"FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.30739","title":"SEA-CLIP-Tiny: Efficient Multilingual Text-Vision Embedding for Southeast Asian Languages","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}