AI Paper Atlas

Research map / Benchmarks / UT-Zappos open-world

UT-Zappos open-world leaderboard

13 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on UT-Zappos open-world. Best AUC: 43.7 (TOMCAT, NeurIPS 2025).

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.

UT-Zappos open-world · AUC

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

#AUC ↑MethodPaperTopic
143.7TOMCAT
CLIP ViT-L/14
TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning
NeurIPS 2025 · Table 1
CLIP and zero-shot
242.3SAM-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 3
CLIP and zero-shot
342.1PCI (Ours)
CLIP ViT-L/14
Prototype-Conditioned Imagination for Compositional Zero-Shot Learning
ECCV 2026 · Table 1
CLIP and zero-shot
441.4VP-CMJL
CLIP ViT-L/14
Learning Visual Proxy for Compositional Zero-Shot Learning
ICCV 2025 · Table 1
CLIP and zero-shot
540.2EVA (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
638.8MRSP
CLIP ViT-L/14
MRSP: Learn Multi-Representations of Single Primitive for Compositional Zero-Shot Learning
ECCV 2024 · Table 3
Zero-/few-shot and meta-learning
735.6I2CD
CLIP ViT-L/14
I2CD: An Invertible Causal Framework for Compositional Zero-Shot Learning via Disentangle-Compose-Disentangle
AAAI 2026 · Table 2
Zero-/few-shot and meta-learning
835.5Troika+FlowComposer
CLIP ViT-L/14
FlowComposer: Composable Flows for Compositional Zero-Shot Learning
CVPR 2026 · Table 1
CLIP and zero-shot
933.3Ours
CLIP ViT-L/14
Retrieval-Augmented Primitive Representations for Compositional Zero-Shot Learning
AAAI 2024 · Table 3
Zero-/few-shot and meta-learning
1033Troika
CLIP ViT-L/14
Troika: Multi-Path Cross-Modal Traction for Compositional Zero-Shot Learning
CVPR 2024 · Table 3
CLIP and zero-shot
3 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.