Risultati della ricerca - decoding (algorithmics OR (algorithm OR (algorithmssics OR (algorithm OR algorithm))))

  1. 1701

    Not every day is a sunny day: Synthetic cloud injection for deep land cover segmentation robustness evaluation across data sources di Mobsite, Sara, Hostache, Renaud, Equille, Laure Berti, Roux, Emmanuel, Guerin, Joris

    Pubblicazione 2025
    Sommario: “... cloud injection algorithm that simulates realistic cloud cover, allowing us to test how Sentinel-1 radar...”
    Testo
    Preprint
  2. 1702

    To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning di Song, Yuda, Rohatgi, Dhruv, Singh, Aarti, Bagnell, J. Andrew

    Pubblicazione 2025
    Sommario: “... simulated locomotion tasks--we investigate the algorithmic trade-off between privileged expert distillation...”
    Testo
    Preprint
  3. 1703

    Robust Analog Lagrange Coded Computing: Theory and Algorithms via Discrete Fourier Transforms di Borah, Rimpi, Harshan, J.

    Pubblicazione 2025
    Sommario: “... foundational step, we use error-correction algorithms for Discrete Fourier Transform (DFT) codes to build novel...”
    Testo
    Preprint
  4. 1704

    Understanding and Improving Communication Performance in Multi-node LLM Inference di Singhania, Prajwal, Singh, Siddharth, Hough, Lannie Dalton, Srivastava, Akarsh, Menon, Harshitha, Jekel, Charles Fredrick, Bhatele, Abhinav

    Pubblicazione 2025
    Sommario: “... hierarchical all-reduce algorithm based on recursive doubling with NVSHMEM. NVRAR achieves up to 1.9$\times...”
    Testo
    Preprint
  5. 1705

    On the Information-Theoretic Fragility of Robust Watermarking under Diffusion Editing di Ni, Yunyi, Yang, Ziyu, Niu, Ze, Davis, Emily, Carter, Finn

    Pubblicazione 2025
    Sommario: “... the watermarked image and the embedded payload approaches zero, causing watermark decoding to fail. We further...”
    Testo
    Preprint
  6. 1706

    $A^3$: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving di Zhou, Yuechi, Su, Yi, Zhang, Jianxin, Li, Juntao, Xia, Qingrong, Wang, Zhefeng, Duan, Xinyu, Huai, Baoxing

    Pubblicazione 2025
    Sommario: “... their ability to handle long sequences, the resulting decoding latency and memory overhead remain substantial...”
    Testo
    Preprint
  7. 1707

    Doppler Robust Vortex Wavefront Design for Integrated Sensing and Communication di Liu, Yuan, Long, Wen-Xuan, Shankar, M. R. Bhavani, Moretti, Marco, Chen, Rui, Ottersten, Björn

    Pubblicazione 2025
    Sommario: “...-consistency matching (VCM)-expectation maximization (EM) algorithm that jointly decodes the sensing matrix...”
    Testo
    Preprint
  8. 1708

    T2M Mamba: Motion Periodicity-Saliency Coupling Approach for Stable Text-Driven Motion Generation di Zhan, Xingzu, Xie, Chen, Chen, Honghang, Lin, Yixun, Mai, Xiaochun

    Pubblicazione 2026
    Sommario: “... through the decoder and producing unstable or erroneous motions. In this work, we propose T2M Mamba...”
    Testo
    Preprint
  9. 1709

    Learning to Solve Orienteering Problem with Time Windows and Variable Profits di Gao, Songqun, Ruan, Zanxi, Floor, Patrick, Roveri, Marco, Palopoli, Luigi, Fontanelli, Daniele

    Pubblicazione 2026
    Sommario: “.... In the first stage, a parallel decoding structure is employed to predict the path and the initial service time...”
    Testo
    Preprint
  10. 1710

    ScoutAttention: Efficient KV Cache Offloading via Layer-Ahead CPU Pre-computation for LLM Inference di Zhang, Qiuyang, Zhou, Kai, Tang, Ding, Lu, Kai, Li, Cheng, Yang, Zhenyu, Xu, Peng, Wan, Jiguang

    Pubblicazione 2026
    Sommario: “... inference, where KV cache memory consumption severely limits decode batch sizes. While existing research has...”
    Testo
    Preprint
  11. 1711

    Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs di Sternfeld, Alexander, Kucharavy, Andrei, Dolamic, Ljiljana

    Pubblicazione 2026
    Sommario: “... such as a weak algorithm or unsafe parameter (mean AUC 0.674). These results show that the threat model...”
    Testo
    Preprint
  12. 1712

    Enhancing secrecy in RIS–fountain code‐aided multi‐cluster satellite–terrestrial NOMA networks under eavesdropping threats di Nguyen Van Toan, Pham Ngoc Son, Tran Trung Duy, Lam‐Thanh Tu

    Pubblicazione 2026
    Sommario: “... to terrestrial relays, where the best relay selected using the PRS algorithm employs the decode‐and‐forward...”
    Testo
    Artículo Open Access
  13. 1713

    Human Motor Cortex Encodes Complex Handwriting Through a Sequence of Stable Neural States: Source code di Qi, Yu, Zhu, Xinyun, Xiong, Xinzhu

    Pubblicazione 2024
    Sommario: “... States". It contains the implemenation of the Temporal Functional Clustering (TFC) algorithm...”
    Testo
    Recurso digital
  14. 1714

    DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads di Xiao, Guangxuan, Tang, Jiaming, Zuo, Jingwei, Guo, Junxian, Yang, Shang, Tang, Haotian, Fu, Yao, Han, Song

    Pubblicazione 2024
    Sommario: “...-weight, constant-length KV cache for streaming heads, which reduces both LLM's decoding and pre-filling...”
    Testo
    Preprint
  15. 1715

    Private Frequency Estimation Via Residue Number Systems di Arcolezi, Héber H.

    Pubblicazione 2025
    Sommario: “...We present \textsf{ModularSubsetSelection} (MSS), a new algorithm for locally differentially...”
    Testo
    Preprint
  16. 1716

    Convolutional Neural Network‐Based CT Image Segmentation of Kidney Tumours di Cong Hu, Wenwen Jiang, Tian Zhou, Chunting Wan, Aijun Zhu

    Pubblicazione 2024
    Sommario: “... decision algorithm. Firstly, for the phenomenon of tumour false positives, the EfficientNetV2 feature...”
    Testo
    Artículo Open Access
  17. 1717

    Invertible generative models for inverse problems: mitigating representation error and dataset bias di Asim, Muhammad, Daniels, Mara, Leong, Oscar, Ahmed, Ali, Hand, Paul

    Pubblicazione 2019
    Sommario: “... or algorithmically by initialization. For compressive sensing, invertible priors can yield higher accuracy than...”
    Testo
    Preprint
  18. 1718

    Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping di Bhattacharya, Uttaran, Roncal, Christian, Mittal, Trisha, Chandra, Rohan, Kapsaskis, Kyra, Gray, Kurt, Bera, Aniket, Manocha, Dinesh

    Pubblicazione 2019
    Sommario: “... of psychologically-motivated affective features underlying the gaits. We train the decoder to reconstruct the motions...”
    Testo
    Preprint
  19. 1719

    Low Complexity Lookup Table Aided Soft Output Semidefinite Relaxation based Faster-than-Nyquist Signaling Detector di Cicek, Adem, Marsland, Ian, Cavus, Enver, Bedeer, Ebrahim, Yanikomeroglu, Halim

    Pubblicazione 2020
    Sommario: “...-likelihood ratios (LLRs) vital for soft channel decoders. In this study, we introduce a lookup table (LUT...”
    Testo
    Preprint
  20. 1720