AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising

Tianci Liu, Zihan Dong, Linjun Zhang, Haoyu Wang, Jing Gao, Emre Kıcıman, Ranveer Chandra, Wei-Ting Chen

ECCV 2026 · Reinforcement learning › Visual and representation RL · approach: Curriculum and environment design · 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
add RL preference-aligned fine-tuning (ablation)Spire (Qwen2.5-VL-7B) · Slide personalization test pagesVLM-judge AVG: 0.3230 -> 0.5415Improved
add RL preference-aligned fine-tuning (ablation)Spire (Qwen2.5-VL-7B) · Slide personalization test pagesVisual similarity AVG: 0.3448 -> 0.7576Improved
add iterative revision with critic feedback (ablation)Spire · Slide personalization test pagesVLM-judge AVG: 0.4038 -> 0.5415Improved
add iterative revision with critic feedback (ablation)Spire · Slide personalization test pagesVisual similarity AVG: 0.6698 -> 0.7576Improved
replace o4-mini critic with Spire-trained 7B critic (ablation)PSP (o4-mini) · Slide personalization test pagesVLM-judge AVG: 0.4784 -> 0.5035Improved
replace o4-mini critic with Spire-trained 7B critic (ablation)PSP (o4-mini) · Slide personalization test pagesVisual similarity AVG: 0.8062 -> 0.9000Improved
add iterative revision with critic feedback (ablation)Spire · Slide personalization test pagesVLM-judge faithfulness: 0.4865 -> 0.7072Improved
add RL fine-tuning (ablation)Spire · Slide personalization test pagesVLM-judge faithfulness: 0.2995 -> 0.7072Improved
replace o4-mini critic with Spire-trained 7B critic (ablation)PSP (o4-mini) · Slide personalization test pagesVLM-judge faithfulness: 0.5504 -> 0.5777Improved

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