AI Paper Atlas

Research map / Benchmarks / Photo

Photo leaderboard

67 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Photo. Best accuracy: 97.05 (GeoMancer, 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.

Photo · accuracy

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

#accuracy ↑MethodPaperTopic
197.05GeoMancerToward a Unified Geometry Understanding : Riemannian Diffusion Framework for Graph Generation and Prediction
NeurIPS 2025 · Table 3
Graph self-supervised learning
296.94LGDUnifying Generation and Prediction on Graphs with Latent Graph Diffusion
NeurIPS 2024 · Node-level classification task
Graph self-supervised learning
396.78GraphSAGE*
GraphSAGE
Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
NeurIPS 2024 · Homophilous results table
GNN architectures
496.27BDFormerRethinking Graph Transformers as Graph Signal Denoisers: The Role of Block-Diagonal Priors
ICML 2026 · Table 1
GNN architectures
596.14TokenphormerTokenphormer: Structure-aware Multi-token Graph Transformer for Node Classification
AAAI 2025 · Table: Comparison of Tokenphor
GNN architectures
696.11PolynormerPolynormer: Polynomial-Expressive Graph Transformer in Linear Time
ICLR 2024 · Table 1
GNN architectures
796.1SGN-BFLocal Vertex Colouring Graph Neural Networks
ICML 2023 · Vertex classification results
GNN architectures
895.91c-IGNN
GCN
Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective
NeurIPS 2025 · Overall Performance of Node Cl
GNN architectures
995.91M$^3$DphormerUnifying and Enhancing Graph Transformers via a Hierarchical Mask Framework
NeurIPS 2025 · Node classification results ta
Graph self-supervised learning
1095.9ERMSS
ERM
Symmetric Self-Paced Learning for Domain Generalization
AAAI 2024 · Table 2
Domain adaptation and generalization
57 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.