AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models

Xuanlang Dai, Yujie Zhou, Long Xing, Jiazi Bu, Xilin Wei, Yuhong Liu, Beichen Zhang, Kai Chen, Yuhang Zang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 7 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 auxiliary semantic loss (ablation)EndoCoT · Maze-32accuracy: 14 -> 90Improved
add auxiliary semantic loss (ablation)EndoCoT · Maze-32path repetition: 67.24 -> 98.13Improved
use implicit latent tokens instead of explicit text tokens (ablation)EndoCoT · Maze-32accuracy: 0 -> 90Improved
use implicit latent tokens instead of explicit text tokens (ablation)EndoCoT · Maze-8accuracy: 34 -> 100Improved
jointly train MLLM and DiT instead of DiT only (ablation)EndoCoT · Maze-32accuracy: 18 -> 90Improved
jointly train MLLM and DiT instead of MLLM only (ablation)EndoCoT · Maze-32accuracy: 0 -> 90Improved
add second-stage terminal consolidation to single-stage training (ablation)EndoCoT · Maze-32accuracy: 14 -> 90Improved
increase reasoning steps tau from 2 to 50 (ablation)EndoCoT · Maze-32accuracy: 11 -> 90Improved
increase reasoning steps tau from 2 to 20 (ablation)EndoCoT · Maze-16accuracy: 72 -> 100Improved
use EndoCoT instead of DiffThinker (task-specific)Qwen-Image-Edit-2511 · Sudoku-35accuracy: 55 -> 95Improved
use EndoCoT instead of DiffThinker (unified training)Qwen-Image-Edit-2511 · Visual reasoning averageaccuracy: 77.1 -> 84.2Improved
use EndoCoT instead of DiffThinker (unified training)Qwen-Image-Edit-2511 · Maze-32 unifiedaccuracy: 66 -> 52Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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