AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers

Anh Nguyen, Ngan Nguyen, Hong Duc Vu, Trung Dao, Viet Nguyen, Minh Quan Dao, Kien Nguyen, Tran Bao Chi Tran, Phong Nguyen, Khoi Nguyen, Cuong Pham, Dimitris N. Metaxas and 2 more

ECCV 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
distill from SD 3.5 Medium teacher through Bridge into one-step SD 1.5 studentSD 1.5 DMD2 student · HPSv3HPSv3: 5.37 -> 9.42Improved
distill into SD 1.5 via BridgeSD 1.5 DMD2 student · ImageRewardImageReward: -0.29 -> 0.62Improved
average parameters of five teacher-specific distilled students (ablation)SD 1.5 Bridge students · HPSv3HPSv3: 5.37 -> 10.53Improved
average parameters of five distilled students (ablation)SD 2.1 Bridge students · HPSv3HPSv3: 6.42 -> 9.75Improved
replace pruned SD 3.5 initialization (30% sparsity) with Bridge distillation to SD 1.5 (ablation)one-step student · HPSv3HPSv3: 2.76 -> 9.42Improved
initialize student from multi-step SD 1.5 instead of DMD2 one-step checkpoint (ablation)SD 1.5 student · HPSv3 / HPSv2HPSv3: HPSv3 9.42 -> 9.22; HPSv2 28.30 -> 28.44No clear effect
add Attention Fidelity loss to latent reconstruction for Bridge training (ablation)Bridge · decoded-image fidelity (L1/PSNR/SSIM)reconstruction fidelityImproved
add E-LatentLPIPS to L1 loss (ablation)Bridge · decoded-image fidelityreconstruction fidelityNo clear effect
add frozen Student-decoder spatial prior to SwinIR projector (ablation)Bridge · decoded-image fidelityreconstruction fidelityImproved
use SwinIR/UNet backbone instead of MLP for the projector (ablation)Bridge · decoded-image fidelityreconstruction fidelityImproved
jointly train Bridge with the student during distillation instead of freezing (ablation)Bridge distillation · training stabilitystabilityHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy