Suchergebnisse - decoding (algorithm OR algorithmssics)

  1. 721

    Decoding rank metric Reed-Muller codes von Couvreur, Alain, Pratihar, Rakhi

    Veröffentlicht 2025
    Inhaltsangabe: “… In this article, we investigate the decoding of the rank metric Reed--Muller codes introduced …”
    Volltext
    Preprint
  2. 722

    Recursive Subproduct Codes with Reed-Muller-like Structure von Siddheshwar, Aditya, Natarajan, Lakshmi Prasad, Krishnan, Prasad

    Veröffentlicht 2024
    Inhaltsangabe: “… belief propagation decoder and a local graph search algorithm, show instances of subproduct codes …”
    Volltext
    Preprint
  3. 723

    Deep Joint Source-Channel Coding for Efficient and Reliable Cross-Technology Communication von Yao, Shumin, Xu, Xiaodong, Chen, Hao, Sun, Yaping, Zhao, Qinglin

    Veröffentlicht 2024
    Inhaltsangabe: “… existing CTC coding algorithms as domain knowledge to guide the encoder-decoder pair to learn …”
    Volltext
    Preprint
  4. 724

    CodecNeRF: Toward Fast Encoding and Decoding, Compact, and High-quality Novel-view Synthesis von Kang, Gyeongjin, Lee, Younggeun, Oh, Seungjun, Park, Eunbyung

    Veröffentlicht 2024
    Inhaltsangabe: “… , such as images and videos, we need to fulfill three key objectives: 1. fast encoding and decoding time, 2 …”
    Volltext
    Preprint
  5. 725

    DOPRA: Decoding Over-accumulation Penalization and Re-allocation in Specific Weighting Layer von Wei, Jinfeng, Zhang, Xiaofeng

    Veröffentlicht 2024
    Inhaltsangabe: “… hallucinations by decoding specific weighted layer penalties and redistribution, offering an economical …”
    Volltext
    Preprint
  6. 726

    Continuous Speculative Decoding for Autoregressive Image Generation von Wang, Zili, Zhang, Robert, Ding, Kun, Yang, Qi, Li, Fei, Xiang, Shiming

    Veröffentlicht 2024
    Inhaltsangabe: “… Language Models (LLMs), speculative decoding has effectively accelerated discrete autoregressive inference …”
    Volltext
    Preprint
  7. 727

    PLD+: Accelerating LLM inference by leveraging Language Model Artifacts von Somasundaram, Shwetha, Phukan, Anirudh, Saxena, Apoorv

    Veröffentlicht 2024
    Inhaltsangabe: “… To reduce the latency associated with autoretrogressive LLM inference, speculative decoding has …”
    Volltext
    Preprint
  8. 728

    SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models von Chen, Fahao, Li, Peng, Luan, Tom H., Su, Zhou, Deng, Jing

    Veröffentlicht 2025
    Inhaltsangabe: “… Speculative decoding has been shown as an effective way to accelerate Large Language Model (LLM …”
    Volltext
    Preprint
  9. 729

    CLaSp: In-Context Layer Skip for Self-Speculative Decoding von Chen, Longze, Shan, Renke, Wang, Huiming, Wang, Lu, Liu, Ziqiang, Luo, Run, Wang, Jiawei, Alinejad-Rokny, Hamid, Yang, Min

    Veröffentlicht 2025
    Inhaltsangabe: “… Speculative decoding (SD) is a promising method for accelerating the decoding process of Large …”
    Volltext
    Preprint
  10. 730

    Radiation-Induced Fault Detection in Superconducting Quantum Devices von Vallero, Marzio, Casagranda, Gioele, Vella, Flavio, Rech, Paolo

    Veröffentlicht 2025
    Inhaltsangabe: “… propose the first algorithm to effectively exploit syndrome information for the efficient detection …”
    Volltext
    Preprint
  11. 731

    Federated Learning in Offline and Online EMG Decoding: A Privacy and Performance Perspective von Malcolm, Kai, Uribe, César, Yamagami, Momona

    Veröffentlicht 2025
    Inhaltsangabe: “… neural decoding using high-dimensional electromyography (EMG) across both offline simulations and a real …”
    Volltext
    Preprint
  12. 732

    Efficient Decoding Methods for Language Models on Encrypted Data von Avitan, Matan, Baruch, Moran, Drucker, Nir, Zimerman, Itamar, Goldberg, Yoav

    Veröffentlicht 2025
    Inhaltsangabe: “… for secure inference. However, neural text generation requires decoding methods like argmax and sampling …”
    Volltext
    Preprint
  13. 733

    SpecAttn: Speculating Sparse Attention von Shah, Harsh

    Veröffentlicht 2025
    Inhaltsangabe: “… SpecAttn, a novel training-free approach that seamlessly integrates with existing speculative decoding …”
    Volltext
    Preprint
  14. 734

    Conserved Kinematic Representations enable Zero-Shot Decoding in Handwriting BCIs von Ravishankar, Srinivas, de Sa, Virginia

    Veröffentlicht 2026
    Inhaltsangabe: “… machine learning algorithm for decoding unseen characters. Our model achieves 64% hits@3 retrieval …”
    Volltext
    Preprint
  15. 735

    Joint Coordinate Regression and Association For Multi-Person Pose Estimation, A Pure Neural Network Approach von Yu, Dongyang, Xie, Yunshi, An, Wangpeng, Zhang, Li, Yao, Yufeng

    Veröffentlicht 2023
    Inhaltsangabe: “… We introduce a novel one-stage end-to-end multi-person 2D pose estimation algorithm, known as Joint …”
    Volltext
    Preprint
  16. 736

    InversionView: A General-Purpose Method for Reading Information from Neural Activations von Huang, Xinting, Panwar, Madhur, Goyal, Navin, Hahn, Michael

    Veröffentlicht 2024
    Inhaltsangabe: “… to practically inspect this subset by sampling from a trained decoder model conditioned on activations …”
    Volltext
    Preprint
  17. 737

    Soft Partitioning of Latent Space for Semantic Channel Equalization von Hüttebräucker, Tomás, Sana, Mohamed, Strinati, Emilio Calvanese

    Veröffentlicht 2024
    Inhaltsangabe: “… semantic communications. This approach aims to align the latent spaces of an encoder and a decoder which …”
    Volltext
    Preprint
  18. 738

    Breaking the Attention Bottleneck von Hilsenbek, Kalle

    Veröffentlicht 2024
    Inhaltsangabe: “… in the transformer architecture. This algorithm is only uni-directional in the decoder and converges to a static …”
    Volltext
    Preprint
  19. 739

    Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters von Shyam, Vasudev, Pilault, Jonathan, Shepperd, Emily, Anthony, Quentin, Millidge, Beren

    Veröffentlicht 2024
    Inhaltsangabe: “… in parallel through a tree reduction. Our algorithm, called Tree Attention, for parallelizing exact attention …”
    Volltext
    Preprint
  20. 740

    Lightweight Transducer Based on Frame-Level Criterion von Wan, Genshun, Wang, Mengzhi, Mao, Tingzhi, Chen, Hang, Ye, Zhongfu

    Veröffentlicht 2024
    Inhaltsangabe: “… criterion, which uses the results of the CTC forced alignment algorithm to determine the label for each …”
    Volltext
    Preprint