ADaPT: Adaptive-window Decoding for Practical fault-Tolerance

• URL: http://arxiv.org/abs/2605.01149v1
• Date: Fri, 01 May 2026 22:49:42 GMT
• Title: ADaPT: Adaptive-window Decoding for Practical fault-Tolerance
• Abstract summary: We propose an adaptive window decoding technique based on decoder confidence.<n>This technique reduces the overhead in decoding time thus reducing reaction time without compromising on logical error rates.
• Score: 2.3480266888270003
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Window decoding, first proposed to reduce decoding complexity for real-time decoding, is an essential component to realize scalable, universal-fault tolerant computation. Prior work has focused on improving throughput through parallelization and reducing reaction time via speculation on window boundaries. However, these methods use a fixed window size d, paying a fixed decoding time overhead for each window. In practice, we find this overhead of a fixed window size unnecessary in many cases due to the sparsity of average-case errors in QEC. Leveraging this insight, in this paper we propose an adaptive window decoding technique based on decoder confidence. This technique reduces the overhead in decoding time thus reducing reaction time without compromising on logical error rates. We benchmark adaptive window decoding across different codes and hardware inspired noise models. Our results show that this adaptive technique reaches the target error rate while maintaining a low decoding time overhead across different codes, and under different noise models.

Related papers

• Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding [51.48425605758328]
  We present Faster Flash Decoding (FFD), a novel hardware-algorithm co-design framework designed to break the memory wall in long-context decoding.<n>FFD integrates the selector and computer into a fully fused kernel, replacing external metadata indices with content-aware scanning.<n>It achieves up to 11.6x kernel-level speedup and scaling to 256K context length, with 2.37x end-to-end throughput improvement.
  arXiv  Detail & Related papers  (2026-08-31T15:13:20Z)
• Optimal Decoding of Small Codes by Density Matrix Propagation [0.0]
  We study the accuracy of practical decoding algorithms under circuit-level noise.<n>We apply this framework to small instances of the repetition code and a cellular automaton code.<n>We find significant deviations for the cellular code, with BP+OSD deteriorating already in experimentally relevant noise regimes.
  arXiv  Detail & Related papers  (2026-06-12T13:43:44Z)
• Adaptive Window Decoding based on Spatiotemporal Complementary Gap [2.257125280672635]
  We propose an adaptive decoding scheme in which window decoding is first performed with a small buffer size.<n>We show that the proposed scheme reduces the average buffer size by approximately 40% while maintaining the logical error rate.
  arXiv  Detail & Related papers  (2026-05-14T09:51:22Z)
• Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting [70.75913449565203]
  A Transformer-based encoder has been widely used with block processing.<n>We propose a new encoder, Spiralformer, tailored for block processing by combining layer dropping and early exiting.<n> Experimentally, we observed that our method achieved 21.6% reduction in the averaged token emission delay in Librispeech.
  arXiv  Detail & Related papers  (2025-10-01T14:56:45Z)
• AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism [17.858104076062897]
  Large language models (LLMs) are increasingly used for long-content generation.<n>We propose AdaDecode, which accelerates decoding without requiring auxiliary models or changes to the original model parameters.<n>AdaDecode consistently achieves superior decoding throughput with up to 1.73x speedup.
  arXiv  Detail & Related papers  (2025-06-04T08:32:30Z)
• WIND: Accelerated RNN-T Decoding with Windowed Inference for Non-blank Detection [17.950722198543897]
  Windowed Inference for Non-blank Detection (WIND) is a novel strategy that significantly accelerates RNN-T inference without compromising model accuracy.<n>We implement WIND for greedy decoding, batched greedy decoding with label-looping techniques, and also propose a novel beam-search decoding method.
  arXiv  Detail & Related papers  (2025-05-19T22:48:01Z)
• Fast correlated decoding of transversal logical algorithms [67.01652927671279]
  Quantum error correction (QEC) is required for large-scale computation, but incurs a significant resource overhead.<n>Recent advances have shown that by jointly decoding logical qubits in algorithms composed of logical gates, the number of syndrome extraction rounds can be reduced.<n>Here, we reform the problem of decoding circuits by directly decoding relevant logical operator products as they propagate through the circuit.
  arXiv  Detail & Related papers  (2025-05-19T18:00:00Z)
• Predictive Window Decoding for Fault-Tolerant Quantum Programs [5.258081366634739]
  Real-time decoding is a key ingredient in future fault-tolerant quantum systems.<n> Windowed decoding schemes require that some decoding tasks be delayed until others have completed.<n>We introduce a speculative window decoding scheme, taking inspiration from branch prediction in classical computer architecture.<n>We find that speculation reduces application runtimes by 40% on average compared to prior parallel window decoders.
  arXiv  Detail & Related papers  (2024-12-06T15:17:18Z)
• Let the Code LLM Edit Itself When You Edit the Code [50.46536185784169]
  underlinetextbfPositional textbfIntegrity textbfEncoding (PIE)<n>PIE reduces computational overhead by over 85% compared to the standard full recomputation approach.<n>Results demonstrate that PIE reduces computational overhead by over 85% compared to the standard full recomputation approach.
  arXiv  Detail & Related papers  (2024-07-03T14:34:03Z)
• Factor Graph Optimization of Error-Correcting Codes for Belief Propagation Decoding [62.25533750469467]
  Low-Density Parity-Check (LDPC) codes possess several advantages over other families of codes. The proposed approach is shown to outperform the decoding performance of existing popular codes by orders of magnitude.
  arXiv  Detail & Related papers  (2024-06-09T12:08:56Z)
• Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference [95.42299246592756]
  We study the UNet encoder and empirically analyze the encoder features. We find that encoder features change minimally, whereas the decoder features exhibit substantial variations across different time-steps. We validate our approach on other tasks: text-to-video, personalized generation and reference-guided generation.
  arXiv  Detail & Related papers  (2023-12-15T08:46:43Z)
• Fast Chain-of-Thought: A Glance of Future from Parallel Decoding Leads to Answers Faster [61.83949316226113]
  FastCoT is a model-agnostic framework based on parallel decoding. We show that FastCoT saves inference time by nearly 20% with only a negligible performance drop compared to the regular approach.
  arXiv  Detail & Related papers  (2023-11-14T15:56:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.