AI Paper Atlas

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

Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?

Jialu Gao, Kaizhe Hu, Guowei Xu, Huazhe Xu

NeurIPS 2023 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 1 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
use LfVoid-generated goals instead of InstructPix2Pix edited goalsexample-based RL · Wipecleaned stain patches: 1.7±1.9 -> 21.3±5.8Improved
use LfVoid-generated goals instead of InstructPix2Pix edited goalsexample-based RL · LEDsuccess rate (%): 0.0±0.0 -> 75.0±50.0Improved
use LfVoid-generated goals instead of InstructPix2Pix edited goalsexample-based RL · Pushsuccess rate (%): 3.3±3.5 -> 27.9±12.7Improved
use generated goal images instead of CLIP language rewardexample-based RL · Wipecleaned stain patches: 0.0±0.0 -> 21.3±5.8Improved
use generated goal images instead of CLIP language rewardexample-based RL · LEDsuccess rate (%): 10.0±20.0 -> 75.0±50.0Improved
use generated goal images instead of CLIP language rewardexample-based RL · Pushsuccess rate (%): 12.5±19.1 -> 27.9±12.7Improved
generated goals versus manually created real goal imagesexample-based RL · LEDsuccess rate (%): 93.3±11.5 -> 75.0±50.0Hurt
generated goals versus manually created real goal imagesexample-based RL · Wipecleaned stain patches: 22.0±5.8 -> 21.3±5.8No clear effect
remove feature extracting module (Null-text P2P-DD) (ablation)LfVoid · Structure-based goal generationuser study Elo: 91.6 -> 63.8Hurt
remove feature extracting module and P2P editing (Null-text DD) (ablation)LfVoid · Structure-based goal generationuser study Elo: 91.6 -> 58Hurt
add P2P attention injection to Null-text DD (ablation)Null-text DD · Structure-based goal generationuser study Elo: 58 -> 63.8Improved
LfVoid versus Imagicgoal editing · Appearance-based goal generationuser study Elo: 47.7 -> 87Improved

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