AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories

Merve Kocabas, Gege Gao, Bernhard Schölkopf, Andreas Geiger

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Generative latent space tooling · 1 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
add FD-loss post-trainingTF-B/16 · ImageNet 256x256FID: 7.93 -> 2.52Improved
add FD-loss post-trainingTF-H/16 · ImageNet 256x256FID: 5.97 -> 1.98Improved
scale model from B/16 to H/16TF · ImageNet 256x256FID: 7.93 -> 5.97Improved
structural loss weight lambda=1 instead of 5 or 10 (ablation)TF-B/16 · ImageNet 256x256FIDImproved
use Muon instead of AdamW (ablation)TF-B/16 · ImageNet 256x256L-NFE FID during trainingImproved
edit at coarser hierarchy level (ablation)TF · Masked SSIM on unedited pixels (feature edits)masked SSIM: 0.92 (subparts) -> 0.77 (object/background)Hurt
use 4-step hierarchical one-step flow instead of many-step baselinesTF · ImageNet 256x256FID at 80 epochs: TF-B/16 7.93 vs iMF-L/2 1.86Mixed
use shared RAE decoder across levels without per-level finetuningTF · intermediate state decodingdecodabilityImproved

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