Suchergebnisse - decoding (Algorithmssicics OR (algorithm OR algorithm))

  1. 1721

    IG-MCTS: Human-in-the-Loop Cooperative Navigation under Incomplete Information von Chen, Shenghui, Zhao, Ruihan, Chinchali, Sandeep, Topcu, Ufuk

    Veröffentlicht 2025
    Inhaltsangabe: “… Information Gain Monte Carlo Tree Search (IG-MCTS), an online planning algorithm that jointly optimizes …”
    Volltext
    Preprint
  2. 1722

    Uplink OFDM Channel Prediction with Hybrid CNN-LSTM for 6G Non-Terrestrial Networks von De Filippo, Bruno, Amatetti, Carla, Vanelli-Coralli, Alessandro

    Veröffentlicht 2025
    Inhaltsangabe: “… response (CFR) matrix in absence of pilots. The algorithm employs an encoder-decoder convolutional neural …”
    Volltext
    Preprint
  3. 1723

    Exploring Contextual Attribute Density in Referring Expression Counting von Wang, Zhicheng, Pan, Zhiyu, Peng, Zhan, Cheng, Jian, Xiao, Liwen, Jiang, Wei, Cao, Zhiguo

    Veröffentlicht 2025
    Inhaltsangabe: “… Referring expression counting (REC) algorithms are for more flexible and interactive counting …”
    Volltext
    Preprint
  4. 1724

    SINR: Sparsity Driven Compressed Implicit Neural Representations von Jayasundara, Dhananjaya, Rajagopalan, Sudarshan, Ranasinghe, Yasiru, Tran, Trac D., Patel, Vishal M.

    Veröffentlicht 2025
    Inhaltsangabe: “… coding schemes employed. In this paper, we introduce SINR, an innovative compression algorithm …”
    Volltext
    Preprint
  5. 1725

    Decoding the mechanisms of the Hattrick football manager game using Bayesian network structure learning von Constantinou, Anthony C., Higgins, Nicholas, Kitson, Neville K.

    Veröffentlicht 2025
    Inhaltsangabe: “… . Hattrick's game-engine mechanics are partially hidden, and users have attempted to decode them …”
    Volltext
    Preprint
  6. 1726

    Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models von Liu, Yi, Liu, Dianqing, Zhu, Mingye, Guo, Junbo, Zhang, Yongdong, Mao, Zhendong

    Veröffentlicht 2025
    Inhaltsangabe: “… algorithm with iterative token-level decoding to address the common first-token latency issue in comparable …”
    Volltext
    Preprint
  7. 1727

    Mamba Drafters for Speculative Decoding von Choi, Daewon, Oh, Seunghyuk, Dingliwal, Saket, Tack, Jihoon, Kim, Kyuyoung, Song, Woomin, Kim, Seojin, Han, Insu, Shin, Jinwoo, Galstyan, Aram, Katiyar, Shubham, Bodapati, Sravan Babu

    Veröffentlicht 2025
    Inhaltsangabe: “… Speculative decoding has emerged as a promising approach to accelerating large language model (LLM …”
    Volltext
    Preprint
  8. 1728

    Leveraging erasure errors in logical qubits with metastable $^{171}$Yb atoms von Zhang, Bichen, Liu, Genyue, Bornet, Guillaume, Horvath, Sebastian P., Peng, Pai, Ma, Shuo, Huang, Shilin, Puri, Shruti, Thompson, Jeff D.

    Veröffentlicht 2025
    Inhaltsangabe: “… Implementing large-scale quantum algorithms with practical advantage will require fault-tolerance …”
    Volltext
    Preprint
  9. 1729

    $\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts von Cemri, Mert, Rajaraman, Nived, Tiwari, Rishabh, Liu, Xiaoxuan, Keutzer, Kurt, Stoica, Ion, Ramchandran, Kannan, Beirami, Ahmad, Sun, Ziteng

    Veröffentlicht 2025
    Inhaltsangabe: “… {SPECS}$, a latency-aware test-time scaling method inspired by speculative decoding. $\texttt{SPECS …”
    Volltext
    Preprint
  10. 1730

    INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling von Dong, Xin, Dong, Shichao, Wang, Jin, Huang, Jing, Zhou, Li, Sun, Zenghui, Jing, Lihua, Lan, Jingsong, Zhu, Xiaoyong, Zheng, Bo

    Veröffentlicht 2025
    Inhaltsangabe: “… further propose \textbf{INTER}: \textbf{Inter}action Guidance Sampling, a novel training-free algorithm …”
    Volltext
    Preprint
  11. 1731

    Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error von Giannoulis, Panagiotis, Pantis, Yorgos, Tzamos, Christos

    Veröffentlicht 2025
    Inhaltsangabe: “… . Unlike prior work that used custom architectures, our method employs a vanilla decoder-only Transformer …”
    Volltext
    Preprint
  12. 1732

    AMLA: MUL by ADD in FlashAttention Rescaling von Liao, Qichen, Hu, Chengqiu, Miao, Fangzheng, Li, Bao, Liu, Yiyang, Lyu, Junlong, Jiang, Lirui, Wang, Jun, Zheng, Lingchao, Li, Jun, Fan, Yuwei

    Veröffentlicht 2025
    Inhaltsangabe: “… . This poses challenges for efficient hardware implementation -- especially during the decode phase. This paper …”
    Volltext
    Preprint
  13. 1733

    The dimension and Bose distance of some BCH codes of length $\frac{q^{m}-1}λ$ von Zheng, Run, Sze, Nung-Sing, Huang, Zejun

    Veröffentlicht 2025
    Inhaltsangabe: “… structure, multi-error correcting capability, and efficient decoding algorithms. Despite their practical …”
    Volltext
    Preprint
  14. 1734

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

    Veröffentlicht 2025
    Inhaltsangabe: “… cloud injection algorithm that simulates realistic cloud cover, allowing us to test how Sentinel-1 radar …”
    Volltext
    Preprint
  15. 1735

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

    Veröffentlicht 2025
    Inhaltsangabe: “… simulated locomotion tasks--we investigate the algorithmic trade-off between privileged expert distillation …”
    Volltext
    Preprint
  16. 1736

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

    Veröffentlicht 2025
    Inhaltsangabe: “… foundational step, we use error-correction algorithms for Discrete Fourier Transform (DFT) codes to build novel …”
    Volltext
    Preprint
  17. 1737

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

    Veröffentlicht 2025
    Inhaltsangabe: “… hierarchical all-reduce algorithm based on recursive doubling with NVSHMEM. NVRAR achieves up to 1.9$\times …”
    Volltext
    Preprint
  18. 1738

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

    Veröffentlicht 2025
    Inhaltsangabe: “… the watermarked image and the embedded payload approaches zero, causing watermark decoding to fail. We further …”
    Volltext
    Preprint
  19. 1739

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

    Veröffentlicht 2025
    Inhaltsangabe: “… their ability to handle long sequences, the resulting decoding latency and memory overhead remain substantial …”
    Volltext
    Preprint
  20. 1740

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

    Veröffentlicht 2025
    Inhaltsangabe: “… -consistency matching (VCM)-expectation maximization (EM) algorithm that jointly decodes the sensing matrix …”
    Volltext
    Preprint