{"total":14,"rows":[{"id":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64,"area":null},{"id":"2502.06604","title":"Do we really have to filter out random noise in pre-training data for language models?","created":"2025-02-10","cited_by_count":11,"area":null},{"id":"2309.01961","title":"NICE: CVPR 2023 Challenge on Zero-shot Image Captioning","created":"2023-09-05","cited_by_count":9,"area":null},{"id":"2407.11211","title":"Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2507.01409","title":"CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2410.11963","title":"CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2404.12739","title":"The Solution for the CVPR2024 NICE Image Captioning Challenge","created":"2024-04-19","cited_by_count":1,"area":null},{"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":"2403.15691","title":"Temporal-Spatial Object Relations Modeling for Vision-and-Language Navigation","created":"2024-03-23","cited_by_count":0,"area":null},{"id":"2410.12561","title":"Development of Image Collection Method Using YOLO and Siamese Network","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2412.06172","title":"Robust Noisy Correspondence Learning via Self-Drop and Dual-Weight","created":"2024-12-09","cited_by_count":0,"area":null},{"id":"2509.09717","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2601.03011","title":"ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarios","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2603.05446","title":"NaiLIA: Multimodal Nail Design Retrieval Based on Dense Intent Descriptions and Palette Queries","created":"2026-03-05","cited_by_count":0,"area":null}],"next_cursor":null}