AI Paper Atlas

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

Reinforcement Learning With LLMs Interaction for Distributed Diffusion Model Services

Hongyang Du, Ruichen Zhang, Dusit Tao Niyato, Jiawen Kang, Zehui Xiong, Shuguang Robert Cui, Xuemin Shen, Dong In Kim

TPAMI 2025 · Image generation › Text-to-image diffusion · approach: Preference optimization for diffusion · 57 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 standard DDPG actor with GDM-based actor (G-DDPG)DDPG under RLLI · distributed GDM AIGC resource allocationtotal QoE: up to 15%Improved
raise bit error probability above thresholddistributed GDM framework · two-device tiger/dog promptsimage quality: BEP below 6% -> above 10%Hurt
increase server denoising steps t0 on a different-prompt devicedistributed GDM framework · Device 2 dog imagetiger features leak: t0 = 2 -> t0 = 4Hurt
increase device denoising steps t2 after shared stepsdistributed GDM framework · Device 2 dog imagetiger features removed: t2 > 6 when t0 = 3Improved
share denoising steps among users, saving three stepsdistributed GDM framework · smartphone energy exampleenergy consumption: 20% to 40%Improved
increase total energy budget from 8 to 12 denoising stepsallocation schemes · QoE requirementachievable QoE: 8 steps no scheme above 0.8; 12 steps several above 0.8Improved
tune server steps for user personality (high agreeableness vs high openness)distributed GDM framework · t2 = 8 with different t0QoE: t0 = 2 best vs t0 = 4 bestMixed
increase server denoising steps when device runs a different promptG-DDPG · Device 2 QoEQoE: moderate t0 bestMixed
increase t0 and t1 when device and server share the same promptG-DDPG · Device 1 QoEQoEImproved

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