AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Talk2Move: Reinforcement Learning for Text-Instructed Object-Level Geometric Transformation in Scenes

Jing Tan, Zhaoyang Zhang, Yantao Shen, Jiarui Cai, Shuo Yang, Jiajun Wu, Wei Xia, Zhuowen Tu, Stefano Soatto

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 3 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 RL (GRPO) on top of SFT (ablation)Flux-Kontext+SFT · translationaccuracy: 38.81% -> 47.14%Improved
add RL (GRPO) on top of SFT (ablation)QwenImageEdit+SFT · translationaccuracy: 67.14% -> 73.13%Improved
add RL on top of SFT trained with 1/10 data (ablation)QwenImageEdit+SFT · translationaccuracy: 26.67% -> 73.33%Improved
add SFT to the base editor (ablation)QwenImageEdit · translationaccuracy: 32.86% -> 67.14%Improved
use active step sampling instead of full sampling (ablation)Talk2Move · translationaccuracy: 69.12% -> 76.67%Improved
use active step sampling instead of sliding window (ablation)Talk2Move · translationaccuracy: 67.14% -> 76.67%Improved
use active step sampling instead of full sampling (ablation)Talk2Move · translationiteration time: 172.32 -> 87.27Improved
use active step sampling instead of sliding window (ablation)Talk2Move · translationiteration time: 101.61 -> 87.27Improved
use spatial reward instead of VLM reward (ablation)Talk2Move · rotationaccuracy: 11.63% -> 29.55%Improved
use spatial reward instead of VLM reward (ablation)Talk2Move · rotationrotation error: 0.3294 -> 0.2861Improved
train Talk2Move vs QwenImageEdit baseQwenImageEdit · resize syntheticscale error: 0.4203 -> 0.3894Mixed

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