Research map / Image generation / Fast diffusion sampling
Denoising Diffusion Error Correction Codes
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Apply diffusion decoding with syndrome-based line search | ECCT-style decoder · Polar(64,32), EbN0 6 | negative natural logarithm of BER: 7.93 -> 12.79 | Helped |
| Use one reverse step with line search instead of regular reverse diffusion (ablation) | DDECC N=2, d=32 · Polar(64,32), EbN0 6 | negative natural logarithm of BER: 3.92 -> 8.23 | Helped |
| Use one reverse step with line search instead of the ECCT baseline (ablation) | DDECC N=2, d=32 · Polar(64,32), EbN0 6 | negative natural logarithm of BER: 7.93 -> 8.23 | Helped |
| Use syndrome-based line search rather than regular reverse diffusion (ablation) | DDECC · Polar(64,48), EbN0 5–6 | negative natural logarithm of BER: 0.11; 0.14; 0.16 | Helped |
| Use syndrome-based line search rather than regular reverse diffusion (ablation) | DDECC · Polar(128,86), EbN0 4–6 | negative natural logarithm of BER: -0.10; -0.11; -0.20 | Hurt |
| Use syndrome-based line search rather than regular reverse diffusion (ablation) | DDECC · LDPC(49,24), EbN0 4–6 | negative natural logarithm of BER: 0.06; 0.05; 0.07 | Mixed |
Closest papers by meaning
- Learning Linear Block Error Correction Codes (ICML 2024 · similarity 0.87)
- Encoder-Decoder Diffusion Language Models for Efficient Training and Inference (NeurIPS 2025 · similarity 0.84)
- CrossMPT: Cross-attention Message-passing Transformer for Error Correcting Codes (ICLR 2025 · similarity 0.84)
- Confidence-Based Decoding is Provably Efficient for Diffusion Language Models (NeurIPS 2026 · similarity 0.84)
- Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference (NeurIPS 2024 · similarity 0.84)
- Structured Masked Diffusion for Joint Multiuser Decoding (NeurIPS 2026 · 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.