Search Results - decoding (algorithm OR (Algorithmsssic OR algorithmsssic))

Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding by Nguyen, Tan Dat, Kim, Ji-Hoon, Choi, Jeongsoo, Choi, Shukjae, Park, Jinseok, Lee, Younglo, Chung, Joon Son

Table of Contents: “… decoding technique that utilises a Viterbi-based algorithm to select the optimal sequence of generated…”
Get full text

Token-Driven GammaTune: Adaptive Calibration for Enhanced Speculative Decoding by Gautam, Aayush, Shrestha, Susav, Reddy, Narasimha

Table of Contents: “…Speculative decoding accelerates large language model (LLM) inference by using a smaller draft…”
Get full text

Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models by Ye, Haotian, Jain, Himanshu, You, Chong, Suresh, Ananda Theertha, Lin, Haowei, Zou, James, Yu, Felix

Table of Contents: “… standards, or conforming to specialized formatting styles. To control the generation, constrained decoding…”
Get full text

Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Autospeculation by Hu, Hengyuan, Das, Aniket, Sadigh, Dorsa, Anari, Nima

Table of Contents: “…} (ASD), an extension of the widely used speculative decoding algorithm to DDPMs that does not require…”
Get full text

Quantum Error Correction Exploiting Degeneracy to Approach the Hashing Bound by Kasai, Kenta

Table of Contents: “… due to their structured sparsity and compatibility with iterative decoding algorithms whose…”
Get full text

TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding by Gong, Shukai, Fu, Yiyang, Ran, Fengyuan, Kong, Quyu, Zhou, Feng

Table of Contents: “… the structural similarities between thinning algorithms for TPPs and speculative decoding for language models, we…”
Get full text

Simultaneous Rational Function Codes: Improved Analysis Beyond Half the Minimum Distance with Multiplicities and Poles by Abbondati, Matteo, Guerrini, Eleonora, Lebreton, Romain

Table of Contents: “… of the decoding algorithm's failure probability that generalizes and improves several previous results…”
Get full text

Biomimetic Metamaterial-based Interface for Decoding Heterogeneous Mechanodermal Activity by Xu, Muzi, Zhang, Jiaqi, Dong, Chaoqun, Zhang, Zibo, Li, Duanyang, Yi, Wentian, Zou, Miaomiao, Tang, Chenyu, Malliaras, George G., Occhipinti, Luigi G.

Table of Contents: “… various scenarios. Combined with bespoke algorithms, the wireless BMMI device decodes MDA accurately…”
Get full text

Cryptographic Applications of Twisted Goppa Codes by Singh, Harshdeep, Bhagat, Anuj Kumar, Sarma, Ritumoni, Gupta, Indivar

Table of Contents: “… earlier methods limited to single twist at last position, we use the extended Euclidean algorithm…”
Get full text

SpecMoE: A Fast and Efficient Mixture-of-Experts Inference via Self-Assisted Speculative Decoding by Bang, Jehyeon, Cho, Eunyeong, Hwang, Ranggi, Chung, Jinha, Rhu, Minsoo

Table of Contents: “…-efficient MoE inference system based on our self-assisted speculative decoding algorithm. SpecMoE…”
Get full text

A Direct Comparison of Simultaneously Recorded Scalp, Around-Ear, and In-Ear EEG for Neural Selective Auditory Attention Decoding to Speech by Geirnaert, Simon, Kappel, Simon L., Kidmose, Preben

Table of Contents: “… hearing devices aim to overcome this limitation by decoding the listener's auditory attention from neural…”
Get full text

SPRITETOMESH: Automatic Mesh Generation for 2D Skeletal Animation Using Learned Segmentation and Contour-Aware Vertex Placement by Gimbert, Bastien

Table of Contents: “… this through a hybrid learned-algorithmic approach. A segmentation network (EfficientNet-B0 encoder with U-Net…”
Get full text

Knot Theory and Error-Correcting Codes by Kilic, Altan B., Nijsten, Anne, Pellikaan, Ruud, Ravagnani, Alberto

Table of Contents: “… parameters and an efficient decoding algorithm. …”
Get full text

Language Model Sentence Completion with a Parser-Driven Rhetorical Control Method by Zingale, Joshua, Kalita, Jugal

Table of Contents: “… that conforms to desired criteria. The current study presents a novel CTG algorithm that enforces adherence…”
Get full text

WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion by Wang, Bin, Deng, Fei, Jiang, Peifan, Wang, Shuang, Han, Xiao, Zhang, Zhixuan

Table of Contents: “… algorithms have been developed, primarily using Convolutional Neural Networks (CNNs) or Transformer Networks…”
Get full text

Regularized Multi-Decoder Ensemble for an Error-Aware Scene Representation Network by Xiong, Tianyu, Wurster, Skylar W., Guo, Hanqi, Peterka, Tom, Shen, Han-Wei

Table of Contents: “… in the absence of ground truth data. We propose a parameter-efficient multi-decoder SRN (MDSRN) ensemble…”
Get full text

Visual Feedback of Pattern Separability Improves Myoelectric Decoding Performance of Upper Limb Prostheses by Yang, Ruichen, Lévay, György M., Hunt, Christopher L., Czeiner, Dániel, Hodgson, Megan C., Agarwal, Damini, Kaliki, Rahul R., Thakor, Nitish V.

Table of Contents: “… into the decoder's classification space, providing intuitive, real-time insight into PR algorithm behavior…”
Get full text

Universal Maximum Likelihood (List) Decoding via Fast Vector-Matrix Multiplication by Ly, Hoang, Soljanin, Emina, Schleppy, Michael

Table of Contents: “…Maximum-likelihood (ML) decoding for arbitrary block codes remains fundamentally hard, with worst…”
Get full text

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining by Zhang, Yifan, Su, Zunhai, Hu, Shuhao, Yang, Rui, Wu, Wei, Qian, Yulei, Xie, Yuchen, Cai, Xunliang

Table of Contents: “… integration into the decoding phase of the DeepSeek Multi-head Latent Attention (MLA) architecture presents…”
Get full text

Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers by Zeng, Fanqin, Hong, Feng, Yu, Geng, Zheng, Huangjie, Cao, Xiaofeng, Zhang, Ya, Han, Bo, Wang, Yanfeng, Yao, Jiangchao

Table of Contents: “… still face a severe quality-speed trade-off: accelerating decoding by revealing multiple tokens often…”
Get full text