Resultados de búsqueda - decoding (algorithmics OR (algorithm OR (algorithm OR algorithm)))

  1. 1481

    Simulation and Experimental Validation of Optical Camera Communication por Narasimman, Srivathsan Chakaravarthi, Alphones, Arokiaswami

    Publicado 2025
    Tabla de Contenidos: “…. This will allow much needed data rate improvement by operating at the actual frequency a decoding algorithm ceases…”
    Enlace del recurso
    Preprint
  2. 1482

    Universal Representations for Classification-enhanced Lossy Compression por Nguyen, Nam

    Publicado 2025
    Tabla de Contenidos: “… has traditionally guided algorithm design. However, Blau and Michaeli [5] introduced a generalized…”
    Enlace del recurso
    Preprint
  3. 1483

    Hierarchical Compact Clustering Attention (COCA) for Unsupervised Object-Centric Learning por Küçüksözen, Can, Yemez, Yücel

    Publicado 2025
    Tabla de Contenidos: “… algorithm that leverages the physical concept of compactness, to highlight distinct object centroids in a…”
    Enlace del recurso
    Preprint
  4. 1484

    Autoencoder-Based Hybrid Replay for Class-Incremental Learning por Nori, Milad Khademi, Kim, Il-Min, Wang, Guanghui

    Publicado 2025
    Tabla de Contenidos: “… performance. The decoder later recovers the exemplar data stored in the latent space, rather than in raw…”
    Enlace del recurso
    Preprint
  5. 1485

    Data-efficient Meta-models for Evaluation of Context-based Questions and Answers in LLMs por Belikova, Julia, Polev, Konstantin, Parchiev, Rauf, Simakov, Dmitry

    Publicado 2025
    Tabla de Contenidos: “… approaches, which decode internal model representations. We propose a methodology combining efficient…”
    Enlace del recurso
    Preprint
  6. 1486

    Dataset combining EEG, eye-tracking, and high-speed video for ocular activity analysis across BCI paradigms por Guttmann-Flury, E., Sheng, X., Zhu, X.

    Publicado 2025
    Tabla de Contenidos: “… be considered as noise, affecting the efficiency and accuracy of decoding users' cognitive states and intentions…”
    Enlace del recurso
    Preprint
  7. 1487

    Near-Field SWIPT Using XL-MIMO: Power Allocation and Subarray Activation por Mumtaz, Muhammad Zeeshan, Mohammadi, Mohammadali, Ngo, Hien Quoc, Matthaiou, Michail

    Publicado 2025
    Tabla de Contenidos: “… decoding (ID) users and energy harvesting (EH) users. Non-stationary near-field channels are considered…”
    Enlace del recurso
    Preprint
  8. 1488

    LIMINAL: Exploring The Frontiers of LLM Decode Performance por Davies, Michael, Crago, Neal, Sankaralingam, Karthikeyan, Kozyrakis, Christos

    Publicado 2025
    Tabla de Contenidos: “…-imposed bottlenecks in auto-regressive decoding. We develop LIMINAL, an analytical performance model…”
    Enlace del recurso
    Preprint
  9. 1489

    Exploring a Graph-based Approach to Offline Reinforcement Learning for Sepsis Treatment por Khakharova, Taisiya, Sakizloglou, Lucas, Lambers, Leen

    Publicado 2025
    Tabla de Contenidos: “… are trained to produce latent state representations, jointly with decoders that predict the next patient state…”
    Enlace del recurso
    Preprint
  10. 1490

    Accelerating Large Language Model Inference via Early-Exiting Algorithms por Bae, Sangmin

    Publicado 2025
    Tabla de Contenidos: “… inference. This dissertation resolves this conflict by co-designing adaptive algorithms and model…”
    Enlace del recurso
    Preprint
  11. 1491

    Angular Dispersion Accelerates $k$-Nearest Neighbors Machine Translation por Tokarchuk, Evgeniia, Troshin, Sergey, Niculae, Vlad

    Publicado 2025
    Tabla de Contenidos: “…Augmenting neural machine translation with external memory at decoding time, in the form of k…”
    Enlace del recurso
    Preprint
  12. 1492

    Auto-Stega: An Agent-Driven System for Lifelong Strategy Evolution in LLM-Based Text Steganography por Zhou, Jiuan, Cheng, Yu, Xie, Yuan, Yin, Zhaoxia

    Publicado 2025
    Tabla de Contenidos: “… constraints. A decoding LLM recovers the information under the shared strategy. To handle high embedding rates…”
    Enlace del recurso
    Preprint
  13. 1493

    Exploring Cross-Client Memorization of Training Data in Large Language Models for Federated Learning por Udsa, Tinnakit, Udomcharoenchaikit, Can, Payoungkhamdee, Patomporn, Nutanong, Sarana, Rattanavipanon, Norrathep

    Publicado 2025
    Tabla de Contenidos: “… decoding strategies, prefix length, and FL algorithms. Our findings reveal that FL models do memorize…”
    Enlace del recurso
    Preprint
  14. 1494

    Inverse Design of Metasurface for Spectral Imaging por Chen, Rongzhou, Nie, Haitao, Zhu, Shuo, Zhao, Yaping, Wang, Chutian, Lam, Edmund Y.

    Publicado 2025
    Tabla de Contenidos: “…Inverse design of metasurfaces for the joint optimization of optical modulation and algorithmic…”
    Enlace del recurso
    Preprint
  15. 1495

    Generalization or Memorization: Dynamic Decoding for Mode Steering por Zhang, Xuanming

    Publicado 2025
    Tabla de Contenidos: “… Steering (DMS), a novel inference-time algorithm which comprises two components: (1) a lightweight…”
    Enlace del recurso
    Preprint
  16. 1496

    Deep Reinforcement Learning-Based Cooperative Rate Splitting for Satellite-to-Underground Communication Networks por Lin, Kaiqiang, Zhao, Kangchun, Mao, Yijie

    Publicado 2025
    Tabla de Contenidos: “… an aboveground relay decodes and forwards the common stream to underground devices (UDs). Based on this framework…”
    Enlace del recurso
    Preprint
  17. 1497

    Speculative Decoding Speed-of-Light: Optimal Lower Bounds via Branching Random Walks por Pankratov, Sergey, Alistarh, Dan

    Publicado 2025
    Tabla de Contenidos: “… ``tight'' lower bounds on the runtime of any deterministic speculative generation algorithm…”
    Enlace del recurso
    Preprint
  18. 1498

    Multi-Modal Semantic Communication por Mortaheb, Matin, Karakaya, Erciyes, Ulukus, Sennur

    Publicado 2025
    Tabla de Contenidos: “… channel bandwidth, we use an algorithm to transmit image patches at adaptive resolutions using…”
    Enlace del recurso
    Preprint
  19. 1499

    Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction por Kim, Jang-Hyun, Han, Dongyoon, Yun, Sangdoo

    Publicado 2026
    Tabla de Contenidos: “… seamlessly into both the prefill and decoding stages. The proposed gate training algorithm relies on forward…”
    Enlace del recurso
    Preprint
  20. 1500

    CoLT: Reasoning with Chain of Latent Tool Calls por Zhu, Fangwei, Sui, Zhifang

    Publicado 2026
    Tabla de Contenidos: “… length than baseline latent models, and is compatible with reinforcement learning algorithms…”
    Enlace del recurso
    Preprint