{"total":14,"rows":[{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137,"area":"synth"},{"id":"2305.04160","title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","created":"2023-05-07","cited_by_count":128,"area":"synth"},{"id":"2307.07063","title":"Bootstrapping Vision-Language Learning with Decoupled Language Pre-training","created":"2023-07-13","cited_by_count":28,"area":"synth"},{"id":"2308.06412","title":"Taming Self-Training for Open-Vocabulary Object Detection","created":"2023-08-11","cited_by_count":25,"area":"synth"},{"id":"2510.12784","title":"SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models","created":"2025-10-14","cited_by_count":22,"area":"synth"},{"id":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"id":"2503.15141","title":"Object-Centric Pretraining via Target Encoder Bootstrapping","created":"2025-03-19","cited_by_count":6,"area":"synth"},{"id":"2403.13804","title":"Learning from Synthetic Data for Visual Grounding","created":"2024-03-20","cited_by_count":4,"area":"synth"},{"id":"2406.11977","title":"Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models","created":"2024-06-17","cited_by_count":2,"area":"synth"},{"id":"2608.11292","title":"Self-Evolving Code-with-Image Reasoning","created":"2026-08-11","cited_by_count":2,"area":"synth"},{"id":"2310.01393","title":"DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection","created":"2023-10-02","cited_by_count":1,"area":"synth"},{"id":"2605.28239","title":"Learning to Label: A Reinforced Self-Evolving Framework for Semi-supervised Referring Expression Segmentation","created":"2026-05-27","cited_by_count":0,"area":"synth"},{"id":"2608.05249","title":"PRISM: Priority-aware Rubric Internalization via Structured Multimodal Data Synthesis","created":"2026-08-05","cited_by_count":0,"area":"synth"},{"id":"2610.19330","title":"NavAble: A Large-Scale Dataset and Synthetic Data Generation Pipeline for Blind Navigation","created":"2026-10-14","cited_by_count":0,"area":"synth"}],"next_cursor":null}