AI Paper Atlas

Research map / Benchmarks / ImageNet 64x64

ImageNet 64x64 leaderboard

16 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImageNet 64x64. Best FID: 1.07 (AYF + adversarial loss, 8 steps, 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.

ImageNet 64x64 · FID

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

#FID ↓MethodPaperTopic
11.07AYF + adversarial loss, 8 stepsAlign Your Flow: Scaling Continuous-Time Flow Map Distillation
NeurIPS 2025 · Table 1
Fast diffusion sampling
21.12Dual-Rate Diffusion K=16, NFE 256Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network
NeurIPS 2026 · Table 1
Fast diffusion sampling
31.23RINScalable Adaptive Computation for Iterative Generation
ICML 2023 · Table 2
Autoregressive and latent generation
41.48SMD
ADM
Score-of-Mixture Training: One-Step Generative Model Training Made Simple via Score Estimation of Mixture Distributions
ICML 2025 · Table 2
Fast diffusion sampling
51.524SiD (α=1.2)
VP-EDM
Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
ICML 2024 · text
Fast diffusion sampling
61.62TDPM+ (T_trunc=99, NFE=100)
ADM
Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders
ICLR 2023 · ImageNet results table
Fast diffusion sampling
71.73CTM, 2 NFE
CM
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
ICLR 2024 · Table 1
Fast diffusion sampling
81.77CADM-G + EDS + ProG
CADM
Rethinking Conditional Diffusion Sampling with Progressive Guidance
NeurIPS 2023 · Table 3
Fast diffusion sampling
91.99Self-consistency, conditioned guidanceLearn to Guide Your Diffusion Model
ICLR 2026 · Table 1
Fast diffusion sampling
102.07ADM (dropout)Diffusion Models Beat GANs on Image Synthesis
NeurIPS 2021 · Table 4
Fast diffusion sampling
6 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.