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

  1. 2081

    Segment Any Vehicle: Semantic and Visual Context Driven SAM and A Benchmark von Wang, Xiao, Wang, Ziwen, Wu, Wentao, Wang, Anjie, Wu, Jiashu, Pan, Yantao, Li, Chenglong

    Veröffentlicht 2025
    Inhaltsangabe: “… and segmentation, has placed increasingly higher demands on algorithmic performance. Pre-trained large segmentation …”
    Volltext
    Preprint
  2. 2082

    Flag at origin: a modular fault-tolerant preparation for CSS codes von Forlivesi, Diego, Amaro, David

    Veröffentlicht 2025
    Inhaltsangabe: “… , the circuit becomes FT. To manage the associated overhead, we propose an algorithm that discovers optimal …”
    Volltext
    Preprint
  3. 2083

    Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm von Yang, Kaisen, He, Lixuan, Shah, Rushi, Yang, Kaicheng, Ma, Qinwei, Liu, Dianbo, Lamb, Alex

    Veröffentlicht 2025
    Inhaltsangabe: “… algorithm enforcing strict plan adherence - with a subsequent Reinforcement Learning (RL) stage …”
    Volltext
    Preprint
  4. 2084

    A Unified Model for Multi-Task Drone Routing in Post-Disaster Road Assessment von Gong, Huatian, Sheu, Jiuh-Biing, Wang, Zheng, Yang, Xiaoguang, Yan, Ran

    Veröffentlicht 2025
    Inhaltsangabe: “… modern transformer encoder-decoder architecture. A lightweight adapter mechanism further enables …”
    Volltext
    Preprint
  5. 2085

    High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection von Chen, Zhiyuan, Guo, Yuelin, Huang, Zitong, He, Haoyu, Lu, Renhao, Zhang, Weizhe

    Veröffentlicht 2025
    Inhaltsangabe: “… of overfitting to synthetic patterns. Third, our cascade denoising algorithm dynamically adjusts training weights …”
    Volltext
    Preprint
  6. 2086
  7. 2087

    Improved Offline Reinforcement Learning via Quantum Metric Encoding von Lv, Outongyi, Yuan, Yewei, Liu, Nana

    Veröffentlicht 2025
    Inhaltsangabe: “… -Learning (IQL), two well-known RL algorithms, to demonstrate the effectiveness of our approach. From …”
    Volltext
    Preprint
  8. 2088

    LiteCache: A Query Similarity-Driven, GPU-Centric KVCache Subsystem for Efficient LLM Inference von Yi, Jiawei, Gong, Ping, Bai, Youhui, Jin, Zewen, Wang, Shengnan, Ruan, Jiaqi, He, Jia, Zhu, Jiaan, Wang, Pengcheng, Wang, Haibo, Wang, Weiguang, Zhu, Xia, Li, Cheng

    Veröffentlicht 2025
    Inhaltsangabe: “… and retrieve highly overlapping top-k KV states. This insight enables a simple head granularity cache algorithm …”
    Volltext
    Preprint
  9. 2089

    Taming the Memory Footprint Crisis: System Design for Production Diffusion LLM Serving von Fan, Jiakun, Zhang, Yanglin, Li, Xiangchen, Nikolopoulos, Dimitrios S.

    Veröffentlicht 2025
    Inhaltsangabe: “… Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research …”
    Volltext
    Preprint
  10. 2090
  11. 2091

    Mamba-3: Improved Sequence Modeling using State Space Principles von Lahoti, Aakash, Li, Kevin Y., Chen, Berlin, Wang, Caitlin, Bick, Aviv, Kolter, J. Zico, Dao, Tri, Gu, Albert

    Veröffentlicht 2026
    Inhaltsangabe: “… for algorithmic efficiency, failing on tasks such as state tracking. Moreover, their theoretically linear …”
    Volltext
    Preprint
  12. 2092

    TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification von Luo, Guan, Li, Xiu, Chen, Rui, Yi, Xuanyu, Lin, Jing, Chen, Chia-Hao, Liu, Jiahang, Zhang, Song-Hai, Zhang, Jianfeng

    Veröffentlicht 2026
    Inhaltsangabe: “… meshes into DMC-compliant representations via a remeshing algorithm that preserves sharp edges using an L …”
    Volltext
    Preprint
  13. 2093

    RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design von Kshirsagar, Meghana, Nie, Allen, Cheng, Ching-An, Xue, Fanglei, Dodhia, Rahul, Ferres, Juan Lavista, Yang, Kevin K., DiMaio, Frank

    Veröffentlicht 2026
    Inhaltsangabe: “… search algorithm capable of controlled exploration and exploitation, using rewards computed from …”
    Volltext
    Preprint
  14. 2094

    NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains von Peng, Shiyao, Zheng, Qianhe, Hao, Zhuodi, Tang, Zichen, Li, Rongjin, Huang, Qing, Huang, Jiayu, Liu, Jiacheng, Zhu, Yifan, E, Haihong

    Veröffentlicht 2026
    Inhaltsangabe: “… an innovative activated search algorithm to obtain a refined candidate space. Then it ensures precise evidence …”
    Volltext
    Preprint
  15. 2095

    Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models von Jiang, Yan, Qiu, Ruihong, Huang, Zi

    Veröffentlicht 2026
    Inhaltsangabe: “… size has therefore become a vital factor in dLLMs, since it determines the parallel decoding …”
    Volltext
    Preprint
  16. 2096

    Parallax: Parameterized Local Linear Attention for Language Modeling von Zuo, Yifei, Pai, Dhruv, Zeng, Zhichen, Dewulf, Alec, Hu, Shuming, Wang, Zhaoran

    Veröffentlicht 2026
    Inhaltsangabe: “… by the bandwidth, the probe construction and the affine structure. We propose a hardware-aware algorithm …”
    Volltext
    Preprint
  17. 2097

    Dynamic High‐Capacity Structural‐Color Encryption Via Inkjet Printing and Image Recognition von Rujun Li, Kaixuan Li, Xiao Deng, Congzhi Jiang, An Li, Luanluan Xue, Renxuan Yuan, Quan Liu, Zongbo Zhang, Huizeng Li, Yanlin Song

    Veröffentlicht 2024
    Inhaltsangabe: “… the high‐capacity information input in a low‐cost way. Moreover, through computer programming and algorithm …”
    Volltext
    Artículo Open Access
  18. 2098

    Implementation of Anti‐Interference and High‐Speed Underwater Acoustic Communication via Chip‐Level Parallel Ghost Imaging von Qi Xi, Bing‐He Ma, Ji‐Zhen Liu, Zong‐Lin Li, Zhi‐Chuang Chang, Zhi‐Yong Tian, Long‐Sheng Zeng, Yu‐Gui Peng, Xue‐Feng Zhu, Zhi‐Bo Ma

    Veröffentlicht 2025
    Inhaltsangabe: “… information is first launched via the speckle multiplexing technology, all of which can then be well decoded …”
    Volltext
    Artículo Open Access
  19. 2099
  20. 2100

    Heterogeneous Electronic Skin Integrated With a Neural Network for Simultaneous Sensing of Strain Direction and Intensity von Xuewei Shi, Alamusi Lee, Yaolu Liu, Chenxing Xiang, Huiming Ning, Haowen Liu, Hansheng Liao, Kexu An, Bo Yang, Kaiyan Huang, Bin Gu, Ning Hu

    Veröffentlicht 2026
    Inhaltsangabe: “… units with a backpropagation (BP) neural network algorithm. Each sensing unit features a heterogeneous …”
    Volltext
    Artículo Open Access