Research map / Vision-language and multimodal / Human and embodied modeling
Reject Decoding via Language-Vision Models for Text-to-Image Synthesis
Fuxiang Wu, Liu Liu, Fusheng Hao, Fengxiang He, Lei Wang, Jun Cheng
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use reject decoding with tiny multimodal vision models instead of generating all reference paths before reranking | RQ-Transformer pre · MS-COCO | FID: 16.4212 -> 14.3066 | Improved |
| Use reject decoding with tiny multimodal vision models instead of generating all reference paths before reranking | RQ-Transformer coco · MS-COCO | IS: 27.27 -> 27.98 | Improved |
| Use reject decoding with tiny multimodal vision models instead of generating all reference paths before reranking | RQ-Transformer coco · MS-COCO | Consuming Time (s): 10.74 -> 10.32 | Improved |
| Increase the end predicted path count Ne (ablation) | Reject decoding · MS-COCO | FID | Mixed |
| Use more visual tokens in the language-vision similarity model (ablation) | Reject decoding · MS-COCO | RPtrans | Improved |
| Train the multimodal vision model for more epochs (ablation) | Reject decoding · MS-COCO | FID | Improved |
| Use the original transformer similarity instead of trained language-vision models (ablation) | Reject decoding · MS-COCO | FID: 8.63 | Hurt |
Closest papers by meaning
- Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis (CVPR 2025 · similarity 0.87)
- Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis (ICLR 2025 · similarity 0.86)
- A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation (CVPR 2025 · similarity 0.85)
- CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning (ICML 2025 · similarity 0.85)
- Elucidating the design space of language models for image generation (ICML 2025 · similarity 0.85)
- SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
