Risultati della ricerca - (Decoding OR coding) algorithm

  1. 621

    Reviving Any-Subset Autoregressive Models with Principled Parallel Sampling and Speculative Decoding di Guo, Gabe, Ermon, Stefano

    Pubblicazione 2025
    Sommario: “... distributions, via our Any-Subset Speculative Decoding (ASSD) algorithm. ASSD provably enables generation...”
    Testo
    Preprint
  2. 622

    LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding di Xu, Chenkai, Jin, Yijie, Li, Jiajun, Tu, Yi, Long, Guoping, Tu, Dandan, Song, Mingcong, Si, Hongjie, Hou, Tianqi, Yan, Junchi, Deng, Zhijie

    Pubblicazione 2025
    Sommario: “... Lookahead PArallel Decoding LoPA, a training-free, plug-and-play algorithm, to identify a superior TFO...”
    Testo
    Preprint
  3. 623

    DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models di Ye, Xi, Zhang, Wuwei, Yin, Fangcong, Yen, Howard, Chen, Danqi

    Pubblicazione 2026
    Sommario: “... context throughout decoding. In this work, we propose DYSCO, a novel decoding algorithm for improving long...”
    Testo
    Preprint
  4. 624

    Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass di Shen, Ethan, Fan, Alan, Pratt, Sarah M., Park, Jae Sung, Wallingford, Matthew, Kakade, Sham M., Holtzman, Ari, Krishna, Ranjay, Farhadi, Ali, Kusupati, Aditya

    Pubblicazione 2024
    Sommario: “... the computation cost of running $k$ inference passes, we propose Superposed Decoding, a new decoding algorithm...”
    Testo
    Preprint
  5. 625

    Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation di So, Junhyuk, Kook, Hyunho, Jang, Chaeyeon, Park, Eunhyeok

    Pubblicazione 2025
    Sommario: “..., which often requires thousands of steps to produce a single sample. While several Speculative Decoding...”
    Testo
    Preprint
  6. 626

    Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation di Potraghloo, Erfan Baghaei, Azizi, Seyedarmin, Kundu, Souvik, Pedram, Massoud

    Pubblicazione 2025
    Sommario: “... writing applications. The code is available at https://github.com/ErfanBaghaei/Top-H-Decoding. ...”
    Testo
    Preprint
  7. 627

    Decoding Quantum Search Advantage: The Critical Role of State Properties in Random Walks di Zhou, Si-Qi, Liang, Jin-Min, Ding, Ziheng, Chen, Zhihua, Fei, Shao-Ming, Ma, Zhihao

    Pubblicazione 2025
    Sommario: “...Quantum algorithms have demonstrated provable speedups over classical counterparts, yet...”
    Testo
    Preprint
  8. 628

    From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models di Welleck, Sean, Bertsch, Amanda, Finlayson, Matthew, Schoelkopf, Hailey, Xie, Alex, Neubig, Graham, Kulikov, Ilia, Harchaoui, Zaid

    Pubblicazione 2024
    Sommario: “... explore three areas under a unified mathematical formalism: token-level generation algorithms, meta...”
    Testo
    Preprint
  9. 629

    A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic Transformers di Huang, Chenyang, Zhou, Hao, Jen, Cameron, Zheng, Kangjie, Zaïane, Osmar R., Mou, Lili

    Pubblicazione 2025
    Sommario: “... decoding algorithm based on the Directed Acyclic Transformer (DAT). Our approach allows for multiple...”
    Testo
    Preprint
  10. 630

    Diverse Transformer Decoding for Offline Reinforcement Learning Using Financial Algorithmic Approaches di Elbaz, Dan, Salzman, Oren

    Pubblicazione 2025
    Sommario: “...Offline Reinforcement Learning (RL) algorithms learn a policy using a fixed training dataset, which...”
    Testo
    Preprint
  11. 631

    Movable Antenna Aided NOMA: Joint Antenna Positioning, Precoding, and Decoding Design di Xiao, Zhenyu, Li, Zhe, Zhu, Lipeng, Ning, Boyu, da Costa, Daniel Benevides, Xia, Xiang-Gen, Zhang, Rui

    Pubblicazione 2024
    Sommario: “... two-loop iterative optimization algorithm that combines the hippopotamus optimization (HO) method...”
    Testo
    Preprint
  12. 632

    Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech Decoding di Feghhi, Ebrahim, Kaasyap, Shreyas, Hadidi, Nima, Kao, Jonathan C.

    Pubblicazione 2025
    Sommario: “... speech directly from neural activity. To accelerate algorithmic progress, a recent benchmark released...”
    Testo
    Preprint
  13. 633

    Local Normalization Distortion and the Thermodynamic Formalism of Decoding Strategies for Large Language Models di Kempton, Tom, Burrell, Stuart

    Pubblicazione 2025
    Sommario: “... for language models by expressing popular decoding algorithms as equilibrium states in the language of ergodic...”
    Testo
    Preprint
  14. 634

    Quick Adaptive Ternary Segmentation: An Efficient Decoding Procedure For Hidden Markov Models di Mösching, Alexandre, Li, Housen, Munk, Axel

    Pubblicazione 2023
    Sommario: “... process -- a noisy version of the hidden chain. Decoding the original signal from the noisy observations...”
    Testo
    Preprint
  15. 635

    ProPD: Dynamic Token Tree Pruning and Generation for LLM Parallel Decoding di Zhong, Shuzhang, Yang, Zebin, Li, Meng, Gong, Ruihao, Wang, Runsheng, Huang, Ru

    Pubblicazione 2024
    Sommario: “... verification efficiency. Additionally, it introduces a dynamic token tree generation algorithm to balance...”
    Testo
    Preprint
  16. 636

    Adaptive Step Sizes and Implicit Regularization: Decoding the Generalization Landscape of Gradient Optimizers di Revista, Zen, IA, 10

    Pubblicazione 2025
    Sommario: “... to the efficacy of gradient-based optimization algorithms. Among these, adaptive step size methods like Adam...”
    Testo
    Recurso digital
  17. 637

    EVA: Recasting LLM Decoding into GEMM via an Efficient Vector Quantization Architecture di Duan, Bowen, Guo, Cong, Wei, Chiyue, Shan, Haoxuan, Fu, Yuzhe, Chen, Xinhua, Xu, Yifan, Zhang, Ziyue, Zhou, Changchun, Li, Hai, Chen, Yiran

    Pubblicazione 2026
    Sommario: “... and artifacts for the ISCA 2026 paper "EVA: Recasting LLM Decoding into GEMM via an Efficient Vector...”
    Testo
    Recurso digital
  18. 638

    Whisper in Medusa's Ear: Multi-head Efficient Decoding for Transformer-based ASR di Segal-Feldman, Yael, Shamsian, Aviv, Navon, Aviv, Hetz, Gill, Keshet, Joseph

    Pubblicazione 2024
    Sommario: “... to improve performance, including efficient hardware utilization and algorithmic enhancements. In this paper...”
    Testo
    Preprint
  19. 639

    Trustful LLMs: Customizing and Grounding Text Generation with Knowledge Bases and Dual Decoders di Zhu, Xiaofeng, Mandivarapu, Jaya Krishna

    Pubblicazione 2024
    Sommario: “...) a post-processing algorithm that leverages knowledge triplets in RAG context to correct...”
    Testo
    Preprint
  20. 640

    Rate-Distortion Region for Distributed Indirect Source Coding with Decoder Side Information di Tang, Jiancheng, Yang, Qianqian

    Pubblicazione 2025
    Sommario: “... develop a distributed Blahut-Arimoto (BA) algorithm to numerically compute the rate-distortion function...”
    Testo
    Preprint