AI Paper Atlas

Research map / Video / Video generation

ChronoEdit: Towards Temporal Reasoning for In-Context Image Editing and World Simulation

Jay Zhangjie Wu, Xuanchi Ren, Tianchang Shen, Tianshi Cao, Kai He, Yifan Lu, Ruiyuan Gao, Enze Xie, Shiyi Lan, Jose M. Alvarez, Jun Gao, Sanja Fidler and 2 more

ICLR 2026 · Video › Video generation · approach: Trajectory-guided motion control

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 temporal reasoning tokens at inference (Nr=10) (ablation)ChronoEdit-14B · PBench-EditOverall (GPT-4.1): 4.43 -> 4.53Improved
add temporal reasoning tokens at inference (Nr=10) (ablation)ChronoEdit-14B · PBench-EditAction Fidelity: 4.01 -> 4.31Improved
extend reasoning from 10 to 20 or 50 steps (ablation)ChronoEdit-14B-Think · PBench-EditOverall (GPT-4.1): 4.53 -> 4.51 (Nr=20), 4.52 (Nr=50)No clear effect
distill to 8-step Turbo student (ablation)ChronoEdit-14B · ImgEdit Basic-EditOverall (GPT-4.1): 4.42 -> 4.13Mixed
scale from 2B to 14BChronoEdit · ImgEdit Basic-EditOverall (GPT-4.1): 4.13 -> 4.42Improved
scale from 2B to 14B with temporal reasoningChronoEdit-Think (Nr=10) · PBench-EditOverall (GPT-4.1): 4.44 -> 4.53Improved
initialize from pretrained video model instead of scratch (ablation)ChronoEdit · image-pair trainingtraining loss convergenceImproved
encode input with 4x repeated target jointly instead of individually (ablation)ChronoEdit VAE encoding · 1000 video frame pairsPSNR (dB): 40.21 -> 39.82No clear effect
video-prior editing model vs FLUX.1 Kontext [Dev] baselineChronoEdit-14B · ImgEdit Basic-EditOverall (GPT-4.1): 3.52 -> 4.42Improved

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