Research map / Probabilistic and scientific modeling / Variational and generative sampling
Mental Sampling in Multimodal Representations
Jianqiao Zhu, Adam Sanborn, Nick Chater
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use MC³ instead of Direct Sampling | Mental sampling algorithms · 2D patchy environment (15 Gaussian mixtures) | flight-distance power-law exponent: -0.59 -> 1.27 | Improved |
| Use MC³ instead of RwM | Mental sampling algorithms · 2D patchy environment (15 Gaussian mixtures) | flight-distance power-law exponent: 0.91 -> 1.27 | Improved |
| Use MC³ instead of Direct Sampling | Mental sampling algorithms · Unimodal Gaussian N(0,3) | power-spectrum slope: -0.01 -> 1.01 | Improved |
| Use MC³ instead of RwM | Mental sampling algorithms · Unimodal Gaussian N(0,3) | power-spectrum slope: 1.64 -> 1.01 | Improved |
| Replace the Gaussian proposal with a Lévy-flight proposal (ablation) | RwM · 2D patchy environment | flight-distance power-law exponent | Hurt |
| Increase spatial sparsity (ablation) | DS and MC³ · 2D patchy environment | flight-distance power-law exponent | Mixed |
| Increase spatial sparsity beyond the explored range (ablation) | DS, RwM, and MC³ · 2D patchy environment | exploration of modes | Hurt |
Closest papers by meaning
- Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging (CVPR 2025 · similarity 0.82)
- Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal Sampling (NeurIPS 2026 · similarity 0.82)
- Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics (ICLR 2025 · similarity 0.82)
- Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models (NeurIPS 2026 · similarity 0.82)
- Theoretical insights for diffusion guidance: A case study for Gaussian mixture models (ICML 2024 · similarity 0.81)
- Chain of Log-Concave Markov Chains (ICLR 2024 · similarity 0.81)
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.
