AI Paper Atlas

Research map / Benchmarks / C-GQA closed-world

C-GQA closed-world leaderboard

14 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on C-GQA closed-world. Best AUC: 18.8 (EVA (Ours), ICLR 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

C-GQA closed-world · AUC

14 papers, each with its best reported number for its own method; higher is better.

#AUC ↑MethodPaperTopic
118.8EVA (Ours)
CLIP ViT-L/14
Decoupling Primitive with Experts: Dynamic Feature Alignment for Compositional Zero-Shot Learning
ICLR 2026 · Table 1
Zero-/few-shot and meta-learning
217.6PCI (Ours)
CLIP ViT-L/14
Prototype-Conditioned Imagination for Compositional Zero-Shot Learning
ECCV 2026 · Table 1
CLIP and zero-shot
316.3I2CD
CLIP ViT-L/14
I2CD: An Invertible Causal Framework for Compositional Zero-Shot Learning via Disentangle-Compose-Disentangle
AAAI 2026 · Table 1
Zero-/few-shot and meta-learning
416.3VP-CMJL
CLIP ViT-L/14
Learning Visual Proxy for Compositional Zero-Shot Learning
ICCV 2025 · Table 1
CLIP and zero-shot
516.2SAM-CZSL
CLIP ViT-L/14 (LoRA)
Bridging the Modality Gap in Compositional Zero-Shot Learning via Sparse Alignment and Unimodal Memory Bank
CVPR 2026 · Table 2
CLIP and zero-shot
616TOMCAT
CLIP ViT-L/14
TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning
NeurIPS 2025 · Table 1
CLIP and zero-shot
715.9Troika+FlowComposer
CLIP ViT-L/14
FlowComposer: Composable Flows for Compositional Zero-Shot Learning
CVPR 2026 · Table 1
CLIP and zero-shot
814.4Ours
CLIP ViT-L/14
Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning
AAAI 2024 · Table 1
Zero-/few-shot and meta-learning
912.4Troika
CLIP ViT-L/14
Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
CVPR 2024 · Table 3
CLIP and zero-shot
1011PLID
CLIP ViT-L/14
Prompting Language-Informed Distribution for Compositional Zero-Shot Learning
ECCV 2024 · Table 1
CLIP and zero-shot
4 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.