Tong Sun

Latest

• ADOPD: A Large-Scale Document Page Decomposition Dataset (The Twelfth International Conference on Learning Representations 2024)
• ARTIST: Improving the Generation of Text-rich Images by Disentanglement (arXiv 2024)
• Customization assistant for text-to-image generation (Proceedings of the IEEE onference on Computer Vision and Pattern Recognition 2024)
• DocSynthv2: A Practical Autoregressive Modeling for Document Generation (arXiv 2024)
• LLaVA-Read: Enhancing Reading Ability of Multimodal Language Models (arXiv 2024)
• SOHES: Self-supervised Open-world Hierarchical Entity Segmentation (The Twelfth International Conference on Learning Representations 2024)
• TRINS: Towards Multimodal Language Models that Can Read (Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2024)
• Toffee: Efficient Million-Scale Dataset Construction for Subject-Driven Text-to-Image Generation (arXiv 2024)
• Llavar: Enhanced visual instruction tuning for text-rich image understanding (arXiv 2023)
• Bit-aware randomized response for local differential privacy in federated learning ( 2022)
• Learning adaptive axis attentions in fine-tuning: Beyond fixed sparse attention patterns (Findings of the Association for Computational Linguistics (ACL) 2022)
• MGDoc: Pre-training with multi-granular hierarchy for document image understanding (Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2022)
• Tigan: Text-based interactive image generation and manipulation (Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2022)
• Towards language-free training for text-to-image generation (Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2022)
• User-Entity Differential Privacy in Learning Natural Language Models (IEEE International Conference on Big Data (Big Data) 2022)
• Towards interpreting and mitigating shortcut learning behavior of NLU models (proceedings of the north american chapter of the association for computational linguistics 2021)
• Unidoc: Unified pretraining framework for document understanding (Advances in Neural Information Processing Systems (NeurIPS) 2021)
• Self-supervised relationship probing (Advances in Neural Information Processing Systems (NeurIPS) 2020)