{"total":46,"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":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2412.14475","title":"MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval","created":"2024-12-19","cited_by_count":84,"area":"synth"},{"id":"2309.00916","title":"BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing","created":"2023-09-02","cited_by_count":79,"area":"synth"},{"id":"2502.08468","title":"mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data","created":"2025-02-12","cited_by_count":49,"area":"synth"},{"id":"2310.00158","title":"Feedback-guided Data Synthesis for Imbalanced Classification","created":"2023-09-29","cited_by_count":33,"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":"2112.00054","title":"Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data","created":"2021-11-30","cited_by_count":26,"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":"2502.03997","title":"CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing","created":"2025-02-06","cited_by_count":19,"area":"synth"},{"id":"2305.12799","title":"Interactive Data Synthesis for Systematic Vision Adaptation via LLMs-AIGCs Collaboration","created":"2023-05-22","cited_by_count":12,"area":"synth"},{"id":"2407.17493","title":"Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling","created":"2024-07-04","cited_by_count":12,"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":"2409.00121","title":"BELT-2: Bootstrapping EEG-to-Language representation alignment for multi-task brain decoding","created":"2024-08-28","cited_by_count":10,"area":"synth"},{"id":"2507.16663","title":"Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs","created":"2025-07-22","cited_by_count":10,"area":"synth"},{"id":"2411.02188","title":"Digi2Real: Bridging the Realism Gap in Synthetic Data Face Recognition via Foundation Models","created":"2024-11-04","cited_by_count":9,"area":"synth"},{"id":"2603.02623","title":"Uni-Skill: Building Self-Evolving Skill Repository for Generalizable Robotic Manipulation","created":"2026-03-03","cited_by_count":9,"area":"synth"},{"id":"2503.12303","title":"Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition","created":"2025-03-16","cited_by_count":7,"area":"synth"},{"id":"2403.11487","title":"Can LLMs Generate Human-Like Wayfinding Instructions? Towards Platform-Agnostic Embodied Instruction Synthesis","created":"2024-03-18","cited_by_count":6,"area":"synth"},{"id":"2403.19880","title":"Vision-Language Synthetic Data Enhances Echocardiography Downstream Tasks","created":"2024-03-28","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":"2404.16637","title":"Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data","created":"2024-04-25","cited_by_count":4,"area":"synth"},{"id":"2406.18790","title":"MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data","created":"2024-06-26","cited_by_count":4,"area":"synth"},{"id":"2408.16310","title":"Bootstrap Segmentation Foundation Model under Distribution Shift via Object-Centric Learning","created":"2024-08-29","cited_by_count":4,"area":"synth"},{"id":"2502.03323","title":"Out-of-Distribution Detection using Synthetic Data Generation","created":"2025-02-05","cited_by_count":4,"area":"synth"},{"id":"2601.06086","title":"AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free Tuning","created":"2025-12-31","cited_by_count":3,"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":"2504.00185","title":"Self-Evolving Visual Concept Library using Vision-Language Critics","created":"2025-03-31","cited_by_count":2,"area":"synth"},{"id":"2209.15000","title":"REST: REtrieve & Self-Train for generative action recognition","created":"2022-09-29","cited_by_count":1,"area":"synth"},{"id":"2306.16658","title":"Prompt Ensemble Self-training for Open-Vocabulary Domain Adaptation","created":"2023-06-29","cited_by_count":1,"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":"2509.00527","title":"Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement","created":"2025-08-30","cited_by_count":1,"area":"synth"},{"id":"2603.07515","title":"EvolveReason: Self-Evolving Reasoning Paradigm for Explainable Deepfake Facial Image Identification","created":"2026-03-08","cited_by_count":1,"area":"synth"},{"id":"2605.04127","title":"Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities","created":"2026-05-05","cited_by_count":1,"area":"synth"},{"id":"2606.03509","title":"EvoMemNav: Efficient Self-Evolving Fine-Grained Memory for Zero-Shot Embodied Navigation","created":"2026-06-02","cited_by_count":1,"area":"synth"},{"id":"2504.04510","title":"Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification","created":"2025-04-06","cited_by_count":0,"area":"synth"},{"id":"2509.15859","title":"Efficient Long-Tail Learning in Latent Space by sampling Synthetic Data","created":"2025-09-19","cited_by_count":0,"area":"synth"},{"id":"2511.05057","title":"Role-SynthCLIP: A Role Play Driven Diverse Synthetic Data Approach","created":"2025-11-07","cited_by_count":0,"area":"synth"},{"id":"2603.16044","title":"Enhancing Linguistic Generalization of VLA: Fine-Tuning OpenVLA via Synthetic Instruction Augmentation","created":"2026-03-17","cited_by_count":0,"area":"synth"},{"id":"2605.01135","title":"ScribbleEdit: Synthetic Data for Image Editing with Scribbles and Text","created":"2026-05-01","cited_by_count":0,"area":"synth"},{"id":"2606.18235","title":"EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation","created":"2026-06-16","cited_by_count":0,"area":"synth"},{"id":"2608.24263","title":"Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing","created":"2026-08-25","cited_by_count":0,"area":"synth"},{"id":"2609.29988","title":"Let Training Guide Selection: Online Synthetic Data Filtering via Real-Anchored Utility","created":"2026-09-24","cited_by_count":0,"area":"synth"},{"id":"2610.19424","title":"VideoHarness-SRSI: Structured Recursive Self-Improvement for Video Understanding Harness","created":"2026-10-14","cited_by_count":0,"area":"synth"}],"next_cursor":null}