Research map / Architectures and efficiency / Attention and transformers
From Markov to Laplace: How Mamba In-Context Learns Markov Chains
Marco Bondaschi, Nived Rajaraman, Xiuying Wei, Razvan Pascanu, Caglar Gulcehre, Michael Gastpar, Ashok Vardhan Makkuva
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 |
|---|---|---|---|
| add convolution to Mamba-2 (ablation) | Mamba-2 · WikiText-103 | perplexity: 30.68 -> 27.55 | Improved |
| add convolution to Transformer (ablation) | Transformer · WikiText-103 | perplexity: 29.28 -> 28.67 | Improved |
| add gating alongside convolution in Mamba (ablation) | Mamba-2 · WikiText-103 | perplexity: 17% change | Improved |
| add more layers (deeper Mamba) (ablation) | Mamba-2 · WikiText-103 | perplexity | Hurt |
Closest papers by meaning
- Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks (ICML 2024 · similarity 0.91)
- Block-Biased Mamba for Long-Range Sequence Processing (NeurIPS 2025 · similarity 0.90)
- Mamba Modulation: On the Length Generalization of Mamba Models (NeurIPS 2025 · similarity 0.89)
- Mamba Can Learn Low-Dimensional Targets In-Context via Test-Time Feature Learning (NeurIPS 2026 · similarity 0.89)
- Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression (NeurIPS 2025 · similarity 0.89)
- LongMamba: Enhancing Mamba's Long-Context Capabilities via Training-Free Receptive Field Enlargement (ICLR 2025 · similarity 0.89)
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.
