Research map / Label-efficient and robust learning / Recognition and long-tail
GUST: Combinatorial Generalization by Unsupervised Grouping with Neuronal Coherence
Hao Zheng, Hui Lin, Rong Zhao
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 |
|---|---|---|---|
| remove biological constraints (noise, refractoriness, feedback delay, coincidence detectors, spiking non-linearity) one at a time (ablation) | GUST · Shapes grouping | AMI | Hurt |
| use GUST instead of Slot Attention for generalizing to unseen object counts | scene grouping · Shapes, 2/3/4 objects train/test | AMI: around 0.3 -> more than 0.5 | Improved |
| simulate 3 times longer at test time than in training | GUST · Shapes denoising | denoising loss | Improved |
Closest papers by meaning
- Neurons as Detectors of Coherent Sets in Sensory Dynamics (NeurIPS 2025 · similarity 0.86)
- NeurFlow: Interpreting Neural Networks through Neuron Groups and Functional Interactions (ICLR 2025 · similarity 0.86)
- Bayesian Bi-clustering of Neural Spiking Activity with Latent Structures (ICLR 2024 · similarity 0.85)
- CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observations (ICLR 2025 · similarity 0.85)
- Learning dynamic representations of the functional connectome in neurobiological networks (ICLR 2024 · similarity 0.85)
- BRAID: Input-driven Nonlinear Dynamical Modeling of Neural-Behavioral Data (ICLR 2025 · similarity 0.85)
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.
