{"total":30,"rows":[{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512,"area":null},{"id":"2505.05071","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","created":"2025-05-08","cited_by_count":81,"area":null},{"id":"2408.15045","title":"DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding","created":"2024-08-27","cited_by_count":23,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2410.10783","title":"LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","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":"2502.15392","title":"Chitrarth: Bridging Vision and Language for a Billion People","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2503.18434","title":"A Simple yet Effective Layout Token in Large Language Models for Document Understanding","created":"2025-03-24","cited_by_count":9,"area":null},{"id":"2511.20648","title":"LocateAnything3D: Vision-Language 3D Detection with Chain-of-Sight","created":"2025-11-25","cited_by_count":8,"area":null},{"id":"2509.22228","title":"UrbanFeel: A Comprehensive Benchmark for Temporal and Perceptual Understanding of City Scenes through Human Perspective","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2602.14276","title":"ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2506.21355","title":"SMMILE: An Expert-Driven Benchmark for Multimodal Medical In-Context Learning","created":"2025-06-26","cited_by_count":5,"area":null},{"id":"2507.08603","title":"Unlocking Speech Instruction Data Potential with Query Rewriting","created":"2025-07-11","cited_by_count":4,"area":null},{"id":"2503.04065","title":"PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2509.08940","title":"Discovering Divergent Representations between Text-to-Image Models","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2505.23008","title":"Synthetic Document Question Answering in Hungarian","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2509.07127","title":"SVGauge: Towards Human-Aligned Evaluation for SVG Generation","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2602.09843","title":"Kelix Technical Report","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2602.17322","title":"Leveraging Contrastive Learning for a Similarity-Guided Tampered Document Data Generation Pipeline","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2607.21061","title":"MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2512.15531","title":"An Efficient and Effective Encoder Model for Vision and Language Tasks in the Remote Sensing Domain","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2602.21877","title":"How to Take a Memorable Picture? Empowering Users with Actionable Feedback","created":"2026-02-25","cited_by_count":0,"area":null},{"id":"2604.16099","title":"DenTab: A Dataset for Table Recognition and Visual QA on Real-World Dental Estimates","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.17570","title":"PBSBench: A Multi-Level Vision-Language Framework and Benchmark for Hematopathology Whole Slide Image Interpretation","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2607.23870","title":"MulRobBench: A Decision-Level Benchmark for Safe and Security-Policy-Compliant Multimodal UAV Agents","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2609.03429","title":"When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.29999","title":"GHOST-Q: Towards Studying Grounding Hallucinations Overlooked Under Same-score TradeOffs in Quantized VLMS","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.08560","title":"Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}