AI Paper Atlas

Research map / Benchmarks / Lipo

Lipo leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Lipo. Best RMSE: 0.454 (ConAN-FGW, ICML 2024).

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.

Lipo · RMSE

10 papers, each with its best reported number for its own method; lower is better.

#RMSE ↓MethodPaperTopic
10.454ConAN-FGWStructure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks
ICML 2024 · Table: Models evaluation on re
Graph self-supervised learning
20.53MOL-MambaMOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights
AAAI 2025 · Table: regression benchmarks
Graph self-supervised learning
30.582GEM + InstructMol
GEM
Instructor-inspired Machine Learning for Robust Molecular Property Prediction
NeurIPS 2024 · Table 3
Recognition and long-tail
40.59Ours (Gamma)
Uni-Mol
A probability contrastive learning framework for 3D molecular representation learning
NeurIPS 2024 · Table 2
Recognition and long-tail
50.638MoleBlend
12-layer Transformer
Multimodal Molecular Pretraining via Modality Blending
ICLR 2024 · Appendix, MolNet Regression Ta
Cross-modal learning
60.695SGMPRepresentation Learning on Spatial Networks
NeurIPS 2021 · Table 2
Graph self-supervised learning
70.698SSTAGSSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
NeurIPS 2025 · Table: self-supervised represe
Graph self-supervised learning
80.75EGNN(C)Exploiting Edge Features for Graph Neural Networks
CVPR 2019 · Table 3
GNN architectures
90.7996MolGroup
GIN
Learning to Group Auxiliary Datasets for Molecule
NeurIPS 2023 · Appendix, Table: GIN results
Recognition and long-tail
101.277OT-PCA + ICLCan LLMs Reason Over Non-Text Modalities in a Training-Free Manner? A Case Study with In-Context Representation Learning
NeurIPS 2025 · Performance–cost comparison ta
Language, safety and interpretability

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