AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Generating Correct Answers for Progressive Matrices Intelligence Tests

Niv Pekar, Yaniv Benny, Lior Wolf

NeurIPS 2020 · Probabilistic and scientific modeling › Molecules and proteins · approach: Sparse concepts and hypothesis testing · 4 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 latent reparameterization with concatenated random noise (ablation)Full answer generator · PGM neutralaccuracy (MRNet evaluator): 65.4 -> 60.1Hurt
Replace Dynamic Selective KLD with standard KLD (ablation)Full answer generator · PGM neutralaccuracy (MRNet evaluator): 65.4 -> 53.3Hurt
Apply KLD to a fixed half of the latent dimensions (ablation)Full answer generator · PGM neutralaccuracy (MRNet evaluator): 65.4 -> 55.8Hurt
Remove the VAE and train the generator with a discriminator (ablation)Full answer generator · PGM neutralaccuracy (MRNet evaluator): 65.4 -> 55.6Hurt
Remove auxiliary rule-type prediction (ablation)Full answer generator · PGM neutralaccuracy (MRNet evaluator): 65.4 -> 57.2Hurt
Replace contrastive relation loss with target-only MSE (ablation)Full answer generator · PGM neutralaccuracy (MRNet evaluator): 65.4 -> 52.7Hurt
Compare generated and choice image features instead of relation-wise encodings (ablation)Full answer generator · PGM neutralaccuracy (MRNet evaluator): 65.4 -> 48.4Hurt
Compare generated and choice images pixel-wise (ablation)Full answer generator · PGM neutralaccuracy (MRNet evaluator): 65.4 -> 48.1Hurt
Remove selective freezing during perceptual-loss backpropagation (ablation)Full answer generator · PGM neutralaccuracy (MRNet evaluator): 65.4 -> 44.6Hurt
Remove randomness during test-time generation (ablation)Full answer generator · PGM neutralaccuracy (MRNet evaluator): 65.4 -> 65.5No clear effect

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