AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Deep Generative Models with Learnable Knowledge Constraints

Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov, LIANHUI Qin, Xiaodan Liang, Haoye Dong, Eric P Xing

NeurIPS 2018 · Reinforcement learning › Visual and representation RL · approach: RL with tree search for discovery · 40 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 a jointly learned human-part consistency constraintPose-conditioned image generation · DeepFashion pose-conditioned image generationSSIM: 0.676 -> 0.727Improved
Add a jointly learned human-part consistency constraintPose-conditioned image generation · DeepFashion pose-conditioned image generationHuman preference: 0.03 -> 0.77Improved
Use a fixed pretrained constraint instead of jointly learning it (ablation)Pose-conditioned image generation · DeepFashion pose-conditioned image generationSSIM: 0.676 -> 0.679No clear effect
Use a fixed pretrained constraint instead of jointly learning it (ablation)Pose-conditioned image generation · DeepFashion pose-conditioned image generationHuman preference: 0.03 -> 0.12Improved
Replace q samples with pθ samples when learning the constraint (ablation)Pose-conditioned image generation · DeepFashion pose-conditioned image generationSSIM: 0.727 -> 0.716Hurt
Add a learned infilling-content matching constraintTemplate-guided sentence generation · IMDB template-guided sentence generationPerplexity: 30.30 -> 28.69Improved
Add a learned infilling-content matching constraintTemplate-guided sentence generation · IMDB template-guided sentence generationHuman preference: 0.19 -> 0.24Improved
Add a binary discriminator instead of a structured matching constraint (ablation)Template-guided sentence generation · IMDB template-guided sentence generationPerplexity: 30.30 -> 30.01No clear effect
Add a binary discriminator instead of a structured matching constraint (ablation)Template-guided sentence generation · IMDB template-guided sentence generationHuman preference: 0.19 -> 0.20No clear effect
Learn the constraint directly by fitting it to current model samples (ablation)Template-guided sentence generation · IMDB template-guided sentence generationPerplexity: 30.30 -> 31.27Hurt
Learn the constraint directly by fitting it to current model samples (ablation)Template-guided sentence generation · IMDB template-guided sentence generationHuman preference: 0.19 -> 0.15Hurt

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