Suchergebnisse - decoding (algorithm OR ((algorithmics OR Algorithmssics) OR Algorithmssics))

  1. 1601

    On Evaluating Performance of LLM Inference Serving Systems von Agrawal, Amey, Kedia, Nitin, Agarwal, Anmol, Mohan, Jayashree, Kwatra, Nipun, Kundu, Souvik, Ramjee, Ramachandran, Tumanov, Alexey

    Veröffentlicht 2025
    Inhaltsangabe: “… -phase nature combining distinct prefill and decode operations, its handling of highly heterogeneous …”
    Volltext
    Preprint
  2. 1602

    Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries von Cai, Pengfei, Song, Yan, Gu, Qing, Jiang, Nan, Song, Haoyu, McLoughlin, Ian

    Veröffentlicht 2025
    Inhaltsangabe: “… Most existing sound event detection~(SED) algorithms operate under a closed-set assumption …”
    Volltext
    Preprint
  3. 1603

    GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation von Zhang, Zhengqiang, Wu, Rongyuan, Sun, Lingchen, Zhang, Lei

    Veröffentlicht 2025
    Inhaltsangabe: “… regions. We first employ an entropy-driven algorithm to partition the image into texture-homogeneous …”
    Volltext
    Preprint
  4. 1604

    Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation von Potraghloo, Erfan Baghaei, Azizi, Seyedarmin, Kundu, Souvik, Pedram, Massoud

    Veröffentlicht 2025
    Inhaltsangabe: “… decoding, a computationally efficient greedy algorithm to solve the ECMM problem. Extensive empirical …”
    Volltext
    Preprint
  5. 1605
  6. 1606

    Near-Asymptotically-Good Quantum Codes with Transversal CCZ Gates and Sublinear-Weight Parity-Checks von Golowich, Louis, Guruswami, Venkatesan

    Veröffentlicht 2025
    Inhaltsangabe: “… the block length. We furthermore design an efficient decoding algorithm for these codes. The alphabet size …”
    Volltext
    Preprint
  7. 1607

    Efficient LLM Inference over Heterogeneous Edge Networks with Speculative Decoding von Zhu, Bingjie, Chen, Zhixiong, Zhao, Liqiang, Shin, Hyundong, Nallanathan, Arumugam

    Veröffentlicht 2025
    Inhaltsangabe: “… LLM inference systems typically adopt autoregressive decoding (AD), which only generates one token per …”
    Volltext
    Preprint
  8. 1608

    Efficient Vector Symbolic Architectures from Histogram Recovery von Deng, Zirui, Raviv, Netanel

    Veröffentlicht 2025
    Inhaltsangabe: “… problem by using algorithms related to list-decoding, and analyze the resulting noise resilience. Our …”
    Volltext
    Preprint
  9. 1609

    MindRec: A Diffusion-driven Coarse-to-Fine Paradigm for Generative Recommendation von Gao, Mengyao, Gao, Chongming, Liu, Haoyan, Cai, Qingpeng, Jiang, Peng, Chen, Jiajia, Yuan, Shuai, He, Xiangnan

    Veröffentlicht 2025
    Inhaltsangabe: “… optimum problem inherent in greedy decoding, we design a novel beam search algorithm, Diffusion Beam …”
    Volltext
    Preprint
  10. 1610

    AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization von Li, Qiyang, Kong, Rui, Li, Yuchen, Cai, Hengyi, Wang, Shuaiqiang, Kong, Linghe, Chen, Guihai, Yin, Dawei

    Veröffentlicht 2026
    Inhaltsangabe: “… latency often skyrockets, leading to decoding speeds slowing by over 2.5 times. Through a fine-grained …”
    Volltext
    Preprint
  11. 1611

    City-Scale Visibility Graph Analysis via GPU-Accelerated HyperBall von Hodge, Alex, Trinanes, Melissa Barrientos

    Veröffentlicht 2026
    Inhaltsangabe: “… BFS complexity from O(N|E|) to O(D|E|2^p); and (iii) GPU-accelerated CUDA kernels with a fused decode …”
    Volltext
    Preprint
  12. 1612

    Introspective Diffusion Language Models von Yu, Yifan, Jian, Yuqing, Wang, Junxiong, Zhou, Zhongzhu, Zhuang, Donglin, Fang, Xinyu, Yanamandra, Sri, Wu, Xiaoxia, Wu, Qingyang, Song, Shuaiwen Leon, Dao, Tri, Athiwaratkun, Ben, Zou, James, Lai, Fan, Xu, Chenfeng

    Veröffentlicht 2026
    Inhaltsangabe: “… novel introspective strided decoding (ISD) algorithm, which enables the model to verify previously …”
    Volltext
    Preprint
  13. 1613

    Kaczmarz Linear Attention von Zou, Jiaxuan, Ren, Ruifeng, Liu, Yong

    Veröffentlicht 2026
    Inhaltsangabe: “… , and chunkwise parallel algorithm. At the 0.4B scale with a 1B-token budget, KLA achieves the lowest validation …”
    Volltext
    Preprint
  14. 1614

    SPARQLe: Sub-Precision Activation Representation for Quantized LLM Inference von Parvathy, Aradhana Mohan, Ghosh, Soumendu Kumar, Kundu, Shamik, Raha, Arnab, Kundu, Souvik, Mathaikutty, Deepak A., Raghunathan, Anand

    Veröffentlicht 2026
    Inhaltsangabe: “… lightweight algorithm to increase MSB sparsity. SPARQLe reduces activation memory traffic and enables …”
    Volltext
    Preprint
  15. 1615

    Electronics‐Free Wearable Platform for Computationally Guided Sweat Biomarker Recognition von Shiyao Li, Zhongzeng Zhou, Xueling Lin, Litong Chen, Yindie Wu, Conghui Liu, Tailin Xu

    Veröffentlicht 2026
    Inhaltsangabe: “… ‐decoding” of sweat biomarkers. For active information acquisition, we engineered a highly porous iron …”
    Volltext
    Artículo Open Access
  16. 1616

    On the Performance of Downlink Channel Estimation‐Based Cell‐Free Massive MIMO Systems Under Correlated Rician Fading Channels von Jiarui Li, Yao Zhang, Fengjiao Gan, Na Liu, Longxiang Yang, Hongbo Zhu

    Veröffentlicht 2025
    Inhaltsangabe: “… decode downlink data solely based on uplink statistical channel state information (CSI). However …”
    Volltext
    Artículo Open Access
  17. 1617

    Predicting Classification Accuracy When Adding New Unobserved Classes von Slavutsky, Yuli, Benjamini, Yuval

    Veröffentlicht 2020
    Inhaltsangabe: “… -network-based algorithm, "CleaneX", which learns to estimate the accuracy of such classifiers …”
    Volltext
    Preprint
  18. 1618

    ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models von Belouadi, Jonas, Eger, Steffen

    Veröffentlicht 2022
    Inhaltsangabe: “… , and alliteration. We identify and address lack of training data and mismatching tokenization algorithms as possible …”
    Volltext
    Preprint
  19. 1619

    Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation von Peng, Tianhao, Gao, Ge, Sun, Heming, Zhang, Fan, Bull, David

    Veröffentlicht 2023
    Inhaltsangabe: “… with conventional coding algorithms in term of compression efficiency. However, most learning-based video …”
    Volltext
    Preprint
  20. 1620

    Decoding University Hierarchy and Prestige in China through Domestic Ph.D. Hiring Network von Tian, Chaolin, Jiang, Xunyi, Huang, Yurui, Ma, Langtian, Ma, Yifang

    Veröffentlicht 2024
    Inhaltsangabe: “… .-granting Chinese universities over three decades. We employ the minimum violation rankings algorithm …”
    Volltext
    Preprint