Research map / Architectures and efficiency / RNNs and normalization
Sparling: End-to-End Spatial Concept Learning via Extremely Sparse Activations
Kavi Gupta, Osbert Bastani, Armando Solar-Lezama
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 |
|---|---|---|---|
| lower target density delta (more extreme sparsity) during annealing (ablation) | Sparling · DigitCircle, LaTeX-OCR, AudioMNISTSequence | false positive error / false negative error | Mixed |
| lower target density delta (more extreme sparsity) (ablation) | Sparling · DigitCircle, LaTeX-OCR, AudioMNISTSequence | confusion error | Improved |
| lower target density delta (more extreme sparsity) (ablation) | Sparling · DigitCircle, LaTeX-OCR, AudioMNISTSequence | end-to-end error | Hurt |
| add sparse bottleneck (Sparling vs Non-Sparse baseline) | end-to-end model · DigitCircle, LaTeX-OCR, AudioMNISTSequence | end-to-end error | Hurt |
| remove bottleneck, freeze motif model and retrain h-hat (Retrained) (ablation) | Sparling · DigitCircle, LaTeX-OCR, AudioMNISTSequence | end-to-end error | Improved |
| increase density 2-3x above the extreme-sparsity level (ablation) | Sparling · motif domains | confusion error | Hurt |
Closest papers by meaning
- Mechanistic Interpretability with Sparse Autoencoder Neural Operators (NeurIPS 2026 · similarity 0.84)
- From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit (NeurIPS 2025 · similarity 0.83)
- Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry (NeurIPS 2025 · similarity 0.83)
- Causal Temporal Representation Learning with Nonstationary Sparse Transition (NeurIPS 2024 · similarity 0.83)
- Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence (ICLR 2025 · similarity 0.83)
- Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity (NeurIPS 2024 · similarity 0.83)
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.
