Research map / Vision-language and multimodal / CLIP and zero-shot
Reversible Primitive–Composition Alignment for Continual Vision–Language Learning
Canran Xiao, Tianxiang Xu, siyuanma, Yiyang Jiang, Haoyu Gao, Yuhan Wu
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 |
|---|---|---|---|
| add composed positive to InfoNCE (ablation) | COMPO-REALIGN · Retrieval/ITM, compositional DIL + MTIL | Avg R@1 Image→Text: 56.9 -> 58.8 (−1.9 when removed) | Improved |
| add composed positive to InfoNCE (ablation) | COMPO-REALIGN · Retrieval/ITM, compositional DIL + MTIL | AF: 4.0 -> 3.2 (+0.8 when removed) | Improved |
| add composed positive to InfoNCE (ablation) | COMPO-REALIGN · VQACL | Avg accuracy: 55.0 -> 56.8 (−1.8 when removed) | Improved |
| add spectral trust region (ablation) | COMPO-REALIGN · Retrieval/ITM, compositional DIL + MTIL | AF: 4.3 -> 3.2 (+1.1 when removed) | Improved |
| add spectral trust region (ablation) | COMPO-REALIGN · Retrieval/ITM, compositional DIL + MTIL | Avg R@1 Image→Text: 57.9 -> 58.8 (−0.9 when removed) | Improved |
| use Cayley orthogonal core instead of linear mix (ablation) | COMPO-REALIGN · Retrieval/ITM, compositional DIL + MTIL | CRR: 0.88 -> 0.91 (−0.03 when removed) | Improved |
| add tiny text buffer (ablation) | COMPO-REALIGN · Retrieval/ITM, compositional DIL + MTIL | Avg R@1 Image→Text: 56.3 -> 58.8 (−2.5 when removed) | Improved |
| add tiny text buffer (ablation) | COMPO-REALIGN · CLOVE-scene | Avg accuracy: 62.8 -> 65.1 (−2.3 when removed) | Improved |
| use mean pooling instead of attention pooling (ablation) | COMPO-REALIGN · Retrieval/ITM, compositional DIL + MTIL | Avg R@1 Image→Text: 58.5 vs 58.8 (−0.3) | No clear effect |
| add primitive shaper (phi and A) (ablation) | COMPO-REALIGN · Retrieval/ITM, compositional DIL + MTIL | Avg R@1 Image→Text: 57.6 -> 58.8 (−1.2 when removed) | Improved |
| use temperature 0.07 instead of 0.10 (ablation) | COMPO-REALIGN · Retrieval/ITM, compositional DIL + MTIL | Avg R@1 Image→Text: 57.4 -> 58.8 (−1.4 when drifted) | Improved |
| use Cayley orthogonal core instead of linear mix (ablation) | COMPO-REALIGN · VQACL | Avg accuracy: 55.6 -> 56.8 (−1.2 when removed) | Improved |
Closest papers by meaning
- CoMem: Compositional Concept-Graph Memory for Vision–Language Adaptation (ICLR 2026 · similarity 0.90)
- SineProject: Machine Unlearning for Stable Vision-Language Alignment (CVPR 2026 · similarity 0.88)
- Synthetic Data is an Elegant GIFT for Continual Vision-Language Models (CVPR 2025 · similarity 0.88)
- Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data (CVPR 2025 · similarity 0.87)
- Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning (AAAI 2024 · similarity 0.87)
- Unlocking Compositional Generalization in Continual Few-Shot Learning (NeurIPS 2026 · similarity 0.87)
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.
