AI Paper Atlas

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

Exploring Conditions for Diffusion Models in Robotic Control

Heeseong Shin, Byeongho Heo, Dongyoon Han, Seungryong Kim, Taekyung Kim

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Compositional text-to-image guidance · 0 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
replace null condition with generated text captionSCR / SD 1.5 · Cheetah-runscore: 43.4 -> 37.5Hurt
replace null condition with generated text captionSCR / SD 1.5 · DeepMind Control meannormalized score: 68.3 -> 68.9No clear effect
add task prompts (ablation)SD 1.5 null condition · DeepMind Control meannormalized score: 68.3 -> 69.8Improved
add visual prompts (ablation)SD 1.5 null condition · DeepMind Control meannormalized score: 68.3 -> 70.5Improved
combine task and visual prompts (ablation)single-prompt variants · DeepMind Control meannormalized score: 70.5 -> 74.3Improved
task prompt only on Cheetah-run (ablation)SD 1.5 · Cheetah-runscore: 43.4 -> 38.9Hurt
use upsampling-block features instead of down+mid features (ablation)ORCA · DeepMind Control meannormalized score: 74.3 -> 49.7 (up 2)Hurt
concatenate down1-3 and mid layers (ablation)single-layer features · DeepMind Control meannormalized score: 68.4 -> 74.3Improved
fine-tune diffusion model downstream (ablation)SCR · Adroit meansuccess rate (%): 58.0 -> 9.3Hurt
fine-tune encoder downstream (ablation)VC-1 · Adroit meansuccess rate (%): 47.3 -> 31.3Hurt
learn task+visual prompts (ORCA) vs TADPSD 1.5 · Adroit meansuccess rate (%): 57.3 -> 65.3Improved

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