AI Paper Atlas

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

EchoGen: Cycle-Consistent Learning for Unified Layout-Image Generation and Understanding

Kai Zou, Hongbo Liu, Dian Zheng, Jianxiong Gao, Zhiwei Zhao, Bin Liu

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 0 citations (OpenAlex)

Read the paper

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 Stage 2 Dual Joint Optimization after Stage 1 (ablation)EchoGen · MS COCOAP: 47.26 -> 52.38Improved
add Stage 3 Cycled RL after Stages 1+2 (ablation)EchoGen · MS COCOAP: 52.38 -> 54.61Improved
add Stage 3 RL directly to Stage 1 without Stage 2 (ablation)EchoGen · MS COCOAP: 47.26 -> 48.01No clear effect
add Stage 2 to Stage 1 (ablation)EchoGen · MS COCOFID: 21.98 -> 22.23No clear effect
add Stage 3 RL to Stages 1+2 (ablation)EchoGen · MS COCOFID: 22.23 -> 20.12Improved
add Stage 3 RL to Stage 1 only (ablation)EchoGen · MS COCOFID: 21.98 -> 20.32Improved
use random layouts instead of real-dataset layouts for RL (ablation)EchoGen · MS COCOAP: 54.61 -> 53.96No clear effect
use GPT-4o generated layouts instead of real-dataset layouts for RL (ablation)EchoGen · MS COCOAP: 54.61 -> 54.51No clear effect
enter Stage 2 with low base AP (below 20) (ablation)EchoGen · MS COCOAPHurt
enter Stage 3 RL with weak base accuracy (AP below 40) (ablation)EchoGen · MS COCOAPHurt
unified generation and grounding model (EchoGen) versus unified PlanGenEchoGen · MS COCOAP: 51.39 -> 54.61Improved
unified EchoGen versus best grounding-only CogVLM-groundingEchoGen · Ref-L4Acc0.75: 70.77 -> 75.42Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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