Research map / Vision-language and multimodal / CLIP and zero-shot
Alignment-Enriched Tuning for Patch-Level Pre-trained Document Image Models
Lei Wang, Jiabang He, Xing Xu, Ning Liu, Hui Liu
This paper tried a common change: Add a contrastive loss
add intra-modal contrastive loss · FUNSD · F1: 89.77 -> 90.45 Improved
What 1,317 accepted papers report for this change
- 1,253 improved
- 22 no clear effect
- 16 mixed
- 26 hurt
- Beyond Looking Up, Try Looking Around: Harmonizing Global Structure and Local Consistency in Optimal Transport for Short Text Clustering ICML 2026 · add contrastive learning · SearchSnippets · ACC: 56.65 -> 80.12Improved
- SleepLM: Natural-Language Intelligence for Human Sleep ICML 2026 · add contrastive objective to captioning (CoCa vs Cap) · sleep event IoU · IoU: 29.2 -> 27.4Hurt
- LIMSSR: LLM-Driven Sequence-to-Score Reasoning under Training-Time Incomplete Multimodal Observations ICML 2026 · add contrastive loss L_con · FS1000 average · Spearman correlation: 0.759 -> 0.789Improved
See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.
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 alignment-enriched tuning instead of LayoutLMv3 fine-tuning | LayoutLMv3_base · FUNSD | F1: 89.82 -> 91.55 | Improved |
| use alignment-enriched tuning instead of LayoutLMv3 fine-tuning | LayoutLMv3_base · CORD | F1: 95.97 -> 97.04 | Improved |
| use alignment-enriched tuning instead of LayoutLMv3 fine-tuning | LayoutLMv3_base · DocVQA | ANLS: 78.76 -> 79.73 | Improved |
| add document-level image-text contrastive loss (ablation) | AETNet_base with supervised objective · FUNSD | F1: 89.77 -> 90.44 | Improved |
| add document-level image-text contrastive loss (ablation) | AETNet_base with supervised objective · CORD | F1: 96.30 -> 96.48 | Improved |
| add intra-modal contrastive loss (ablation) | AETNet_base with supervised objective · FUNSD | F1: 89.77 -> 90.45 | Improved |
| add intra-modal contrastive loss (ablation) | AETNet_base with supervised objective · CORD | F1: 96.30 -> 96.61 | Improved |
| add global-local image-text contrastive loss (ablation) | AETNet_base with supervised objective · FUNSD | F1: 89.77 -> 90.18 | Improved |
| add global-local image-text contrastive loss (ablation) | AETNet_base with supervised objective · CORD | F1: 96.30 -> 96.37 | Improved |
| add patch-level image-text alignment loss (ablation) | AETNet_base with supervised objective · FUNSD | F1: 89.77 -> 90.69 | Improved |
| add patch-level image-text alignment loss (ablation) | AETNet_base with supervised objective · CORD | F1: 96.30 -> 96.78 | Improved |
| add alignment losses and alignment-aware encoders rather than using only supervised tuning (ablation) | LayoutLMv3_base on FUNSD · FUNSD | F1: 89.82 -> 91.55 | Improved |
Closest papers by meaning
- Aligning Text to Image in Diffusion Models is Easier Than You Think (NeurIPS 2025 · similarity 0.89)
- Discriminative Probing and Tuning for Text-to-Image Generation (CVPR 2024 · similarity 0.88)
- Improving Long-Text Alignment for Text-to-Image Diffusion Models (ICLR 2025 · similarity 0.87)
- AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding (NeurIPS 2025 · similarity 0.87)
- Information Theoretic Text-to-Image Alignment (ICLR 2025 · similarity 0.87)
- CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching (NeurIPS 2024 · similarity 0.86)
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.
