{"total":29,"rows":[{"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":"2402.07865","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","created":"2024-02-12","cited_by_count":339,"area":null},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132,"area":null},{"id":"2409.10695","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","created":"2024-09-16","cited_by_count":116,"area":null},{"id":"2407.04172","title":"ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild","created":"2024-07-04","cited_by_count":79,"area":null},{"id":"2311.04219","title":"OtterHD: A High-Resolution Multi-modality Model","created":"2023-11-07","cited_by_count":72,"area":null},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46,"area":null},{"id":"2311.16241","title":"SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance","created":"2023-11-27","cited_by_count":41,"area":null},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2406.17711","title":"Data curation via joint example selection further accelerates multimodal learning","created":"2024-06-25","cited_by_count":33,"area":null},{"id":"2412.15212","title":"Scaling 4D Representations","created":"2024-12-19","cited_by_count":30,"area":null},{"id":"2406.04542","title":"M&M VTO: Multi-Garment Virtual Try-On and Editing","created":"2024-06-06","cited_by_count":29,"area":null},{"id":"2407.14563","title":"Learning Visual Grounding from Generative Vision and Language Model","created":"2024-07-18","cited_by_count":27,"area":null},{"id":"2412.09582","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","created":"2024-12-12","cited_by_count":25,"area":null},{"id":"2311.13596","title":"T-Rex: Counting by Visual Prompting","created":"2023-11-22","cited_by_count":20,"area":null},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2412.06779","title":"AnyBimanual: Transferring Unimanual Policy for General Bimanual Manipulation","created":"2024-12-09","cited_by_count":16,"area":null},{"id":"2503.14021","title":"MP-GUI: Modality Perception with MLLMs for GUI Understanding","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2403.02626","title":"Modeling Collaborator: Enabling Subjective Vision Classification With Minimal Human Effort via LLM Tool-Use","created":"2024-03-05","cited_by_count":9,"area":null},{"id":"2512.22208","title":"Open-Source Multimodal Moxin Models with Moxin-VLM and Moxin-VLA","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2402.05804","title":"InkSight: Offline-to-Online Handwriting Conversion by Teaching Vision-Language Models to Read and Write","created":"2024-02-08","cited_by_count":2,"area":null},{"id":"2504.05644","title":"iEBAKER: Improved Remote Sensing Image-Text Retrieval Framework via Eliminate Before Align and Keyword Explicit Reasoning","created":"2025-04-08","cited_by_count":1,"area":null},{"id":"2508.21451","title":"MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2603.07474","title":"Cross-Modal Taxonomic Generalization in (Vision-) Language Models","created":"2026-03-08","cited_by_count":1,"area":null},{"id":"2412.18327","title":"HAUR: Human Annotation Understanding and Recognition Through Text-Heavy Images","created":"2024-12-24","cited_by_count":0,"area":null},{"id":"2509.16892","title":"Learning from Gene Names, Expression Values and Images: Contrastive Masked Text-Image Pretraining for Spatial Transcriptomics Representation Learning","created":"2025-09-21","cited_by_count":0,"area":null},{"id":"2512.01636","title":"Generative Editing in the Joint Vision-Language Space for Zero-Shot Composed Image Retrieval","created":"2025-12-01","cited_by_count":0,"area":null}],"next_cursor":null}