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

  1. 1501

    Improving Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architectures von Zhang, Huijie, Lu, Yifu, Alkhouri, Ismail, Ravishankar, Saiprasad, Song, Dogyoon, Qu, Qing

    Veröffentlicht 2023
    Inhaltsangabe: “… involves segmenting the time interval into multiple stages where we employ custom multi-decoder U-net …”
    Volltext
    Preprint
  2. 1502

    Review of Deep Representation Learning Techniques for Brain-Computer Interfaces and Recommendations von Guetschel, Pierre, Ahmadi, Sara, Tangermann, Michael

    Veröffentlicht 2024
    Inhaltsangabe: “… for BCI decoding, to provide a comprehensive analysis of the current state-of-the-art. Each article …”
    Volltext
    Preprint
  3. 1503

    Multi-Task Decision-Making for Multi-User 360 Video Processing over Wireless Networks von Badnava, Babak, Chakareski, Jacob, Hashemi, Morteza

    Veröffentlicht 2024
    Inhaltsangabe: “… and offer computing assistance for decoding/rendering of video frames. However, this comes at the expense …”
    Volltext
    Preprint
  4. 1504

    Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance von Zhu, Yongshuo, Li, Lu, Chen, Keyan, Liu, Chenyang, Zhou, Fugen, Shi, Zhenwei

    Veröffentlicht 2024
    Inhaltsangabe: “… . Semantic-CC alleviates the dependency of high-generalization algorithms on extensive annotations …”
    Volltext
    Preprint
  5. 1505

    Enhanced Parking Perception by Multi-Task Fisheye Cross-view Transformers von Musabini, Antonyo, Novikov, Ivan, Soula, Sana, Leonet, Christel, Wang, Lihao, Benmokhtar, Rachid, Burger, Fabian, Boulay, Thomas, Perrotton, Xavier

    Veröffentlicht 2024
    Inhaltsangabe: “… Current parking area perception algorithms primarily focus on detecting vacant slots within a …”
    Volltext
    Preprint
  6. 1506
  7. 1507
  8. 1508

    Joint Detection and Decoding: A Graph Neural Network Approach von Clausius, Jannis, Rübenacke, Marvin, Tandler, Daniel, Brink, Stephan ten

    Veröffentlicht 2025
    Inhaltsangabe: “… be used to perform joint detection and decoding (JDD). For detection, the GNN is build upon the factor …”
    Volltext
    Preprint
  9. 1509

    An Analytical Study of the Min-Sum Approximation for Polar Codes von Chisnevski, Nir, Tal, Ido, Shamai, Shlomo

    Veröffentlicht 2025
    Inhaltsangabe: “… The min-sum approximation is widely used in the decoding of polar codes. Although it is a numerical …”
    Volltext
    Preprint
  10. 1510

    KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse von Yang, Huan, Zhang, Renji, Huang, Mingzhe, Wang, Weijun, Tang, Yin, Li, Yuanchun, Liu, Yunxin, Zhang, Deyu

    Veröffentlicht 2025
    Inhaltsangabe: “… and the attention deviations introduced by new tokens during the decoding stage. In this paper, we present a KV …”
    Volltext
    Preprint
  11. 1511

    GASCADE: Grouped Summarization of Adverse Drug Event for Enhanced Cancer Pharmacovigilance von Jamil, Sofia, Dabad, Aryan, Reddy, Bollampalli Areen, Saha, Sriparna, Misra, Rajiv, Shakur, Adil A.

    Veröffentlicht 2025
    Inhaltsangabe: “… extraction capabilities of Large Language Models (LLMs) with the summarization power of the encoder-decoder …”
    Volltext
    Preprint
  12. 1512

    HAMburger: Accelerating LLM Inference via Token Smashing von Liu, Jingyu, Zhang, Ce

    Veröffentlicht 2025
    Inhaltsangabe: “… optimization on algorithms, systems, and hardware. However, very few works have fundamentally changed …”
    Volltext
    Preprint
  13. 1513

    Branch-and-bound method for calculating Viterbi path in triplet Markov models von Soop, Oskar, Lember, Jüri

    Veröffentlicht 2025
    Inhaltsangabe: “… $ is Markov chain, then such path can be efficiently found using the celebrated Viterbi algorithm. However …”
    Volltext
    Preprint
  14. 1514

    OpenZL: A Graph-Based Model for Compression von Collet, Yann, Terrell, Nick, Handte, W. Felix, Rozenblit, Danielle, Zhang, Victor, Zhang, Kevin, Goldschlag, Yaelle, Lee, Jennifer, Gorokhovsky, Elliot, Komornik, Yonatan, Riegel, Daniel, Angelov, Stan, Rotem, Nadav

    Veröffentlicht 2025
    Inhaltsangabe: “… throughput and low resource utilization. In practice, application-specific compression algorithms …”
    Volltext
    Preprint
  15. 1515

    Decoupling Task-Solving and Output Formatting in LLM Generation von Deng, Haikang, Kung, Po-Nien, Peng, Nanyun

    Veröffentlicht 2025
    Inhaltsangabe: “… aspects could lead to improved performance. To this front, we introduce Deco-G, a decoding framework …”
    Volltext
    Preprint
  16. 1516
  17. 1517

    Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference von Bhendawade, Nikhil, Nishu, Kumari, Kundu, Arnav, Bartels, Chris, Cho, Minsik, Belousova, Irina

    Veröffentlicht 2025
    Inhaltsangabe: “… Speculative decoding accelerates LLM inference by using a draft model to look ahead, but gains …”
    Volltext
    Preprint
  18. 1518

    A Preliminary Study on the Promises and Challenges of Native Top-$k$ Sparse Attention von Xiu, Di, Tang, Hongyin, Rong, Bolin, Yan, Lizhi, Wang, Jingang, Lu, Yifan, Cai, Xunliang

    Veröffentlicht 2025
    Inhaltsangabe: “… into the effectiveness and theoretical mechanisms of the Top-$k$ Attention mechanism during both the decoding …”
    Volltext
    Preprint
  19. 1519

    Scalable, Energy-Efficient Optical-Neural Architecture for Multiplexed Deepfake Video Detection von Kashani, Parnian Ghapandar, Chen, Shiqi, Ozcan, Aydogan

    Veröffentlicht 2026
    Inhaltsangabe: “… on computationally intensive and energy-demanding inference algorithms, limiting their scalability. Here, we present …”
    Volltext
    Preprint
  20. 1520

    Bioinspired Sensory Transduction for Magnetic Profile Recognition and Encryption von Ziyue Miao, Xichen Hu, Kai Liu, Shanming Hu, Guihua Yan, Hongwei Tan, Olli Ikkala, Zhong‐Peng Lv, Bo Peng

    Veröffentlicht 2026
    Inhaltsangabe: “… signals. Machine learning algorithms decode the static and dynamic information with ∼100% and 87.5 …”
    Volltext
    Artículo Open Access