AI Paper Atlas

Research map / Benchmarks / CIFAR-10 conditional

CIFAR-10 conditional leaderboard

17 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on CIFAR-10 conditional. Best FID: 1.37 (EDMγ + adversarial θ, φ, ICML 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.

CIFAR-10 conditional · FID

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

#FID ↓MethodPaperTopic
11.37EDMγ + adversarial θ, φ
EDM
Multidimensional Adaptive Coefficient for Inference Trajectory Optimization in Flow and Diffusion
ICML 2025 · Table: Performance comparisons
Fast diffusion sampling
21.38EDM + Neon
EDM-VP
Neon: Negative Extrapolation From Self-Training Improves Image Generation
ICLR 2026 · Table 7a
Fast diffusion sampling
31.38Uni-Instruct FKL (longer training)
EDM
Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction
NeurIPS 2025 · Table: Label-conditioned image
Fast diffusion sampling
41.44D2O-F
EDM NCSN++
Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
ICML 2025 · CIFAR-10 comprehensive compari
Fast diffusion sampling
51.47SADM
EDM
Structure-Guided Adversarial Training of Diffusion Models
CVPR 2024 · Table 2
GANs
61.52EDM+DiffRS
EDM
Diffusion Rejection Sampling
ICML 2024 · Table: Performance comparison
Fast diffusion sampling
71.63CTM, 2 NFE
EDM
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
ICLR 2024 · Table 1
Fast diffusion sampling
81.64EDM-G++
EDM
Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models
ICML 2023 · Table: Performance on CIFAR-10
Fast diffusion sampling
91.75EDM + our scheduleDiagnosing and Improving Diffusion Models by Estimating Optimal Loss Value
ICLR 2026 · Table 4
Fast diffusion sampling
101.77CDM-VP (Ours) best checkpointConsistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent
NeurIPS 2023 · Table 1
Fast diffusion sampling
7 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.