Risultati della ricerca - decoding (algorithmssics OR (algorithm OR (algorithm OR algorithm)))

A general reduced-order neural operator for spatio-temporal predictive learning on complex spatial domains di Meng, Qinglu, Li, Yingguang, Deng, Zhiliang, Liu, Xu, Chen, Gengxiang, Wu, Qiutong, Liu, Changqing, Hao, Xiaozhong

Sommario: “... on Riemannian Manifolds (RO-NORM), which consists of two parts: the unequal-domain encoder/decoder and the same...”
Testo

Using MRNet to Predict Lunar Rock Categories Detected by Chang'e 5 Probe di Cui, Jin, Zou, Yifei, Zhang, Siyuan

Sommario: “..., and the decoding part adds dilated convolution and commonly used U-Net structure on the original VGG16 decoding...”
Testo

Cyrus+: A DRL-based Puncturing Solution to URLLC/eMBB Multiplexing in O-RAN di Ghoreishi, Ehsan, Abolhassani, Bahman, Huang, Yan, Acharya, Shiva, Lou, Wenjing, Hou, Y. Thomas

Sommario: “.... This is inadequate as, after puncturing, eMBB data may or may not be successfully decoded at its receiver. This paper...”
Testo

On Evaluating Performance of LLM Inference Serving Systems di Agrawal, Amey, Kedia, Nitin, Agarwal, Anmol, Mohan, Jayashree, Kwatra, Nipun, Kundu, Souvik, Ramjee, Ramachandran, Tumanov, Alexey

Sommario: “...-phase nature combining distinct prefill and decode operations, its handling of highly heterogeneous...”
Testo

Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries di Cai, Pengfei, Song, Yan, Gu, Qing, Jiang, Nan, Song, Haoyu, McLoughlin, Ian

Sommario: “...Most existing sound event detection~(SED) algorithms operate under a closed-set assumption...”
Testo

GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation di Zhang, Zhengqiang, Wu, Rongyuan, Sun, Lingchen, Zhang, Lei

Sommario: “... regions. We first employ an entropy-driven algorithm to partition the image into texture-homogeneous...”
Testo

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

Sommario: “... decoding, a computationally efficient greedy algorithm to solve the ECMM problem. Extensive empirical...”
Testo

PepCompass: Navigating peptide embedding spaces using Riemannian Geometry di Możejko, Marcin, Bielecki, Adam, Prądzyński, Jurand, Traskowski, Marcin, Janowski, Antoni, Lee, Hyun-Su, Torres, Marcelo Der Torossian, Kmicikiewicz, Michał, Szymczak, Paulina, Jurasz, Karol, Kucharczyk, Michał, de la Fuente-Nunez, Cesar, Szczurek, Ewa

Sommario: “..., but conventionally ignore decoder-induced geometry and rely on flat Euclidean metrics, rendering exploration...”
Testo

Near-Asymptotically-Good Quantum Codes with Transversal CCZ Gates and Sublinear-Weight Parity-Checks di Golowich, Louis, Guruswami, Venkatesan

Sommario: “... the block length. We furthermore design an efficient decoding algorithm for these codes. The alphabet size...”
Testo

Efficient LLM Inference over Heterogeneous Edge Networks with Speculative Decoding di Zhu, Bingjie, Chen, Zhixiong, Zhao, Liqiang, Shin, Hyundong, Nallanathan, Arumugam

Sommario: “... LLM inference systems typically adopt autoregressive decoding (AD), which only generates one token per...”
Testo

Efficient Vector Symbolic Architectures from Histogram Recovery di Deng, Zirui, Raviv, Netanel

Sommario: “... problem by using algorithms related to list-decoding, and analyze the resulting noise resilience. Our...”
Testo

MindRec: A Diffusion-driven Coarse-to-Fine Paradigm for Generative Recommendation di Gao, Mengyao, Gao, Chongming, Liu, Haoyan, Cai, Qingpeng, Jiang, Peng, Chen, Jiajia, Yuan, Shuai, He, Xiangnan

Sommario: “... optimum problem inherent in greedy decoding, we design a novel beam search algorithm, Diffusion Beam...”
Testo

AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization di Li, Qiyang, Kong, Rui, Li, Yuchen, Cai, Hengyi, Wang, Shuaiqiang, Kong, Linghe, Chen, Guihai, Yin, Dawei

Sommario: “... latency often skyrockets, leading to decoding speeds slowing by over 2.5 times. Through a fine-grained...”
Testo

City-Scale Visibility Graph Analysis via GPU-Accelerated HyperBall di Hodge, Alex, Trinanes, Melissa Barrientos

Sommario: “... BFS complexity from O(N|E|) to O(D|E|2^p); and (iii) GPU-accelerated CUDA kernels with a fused decode...”
Testo

Introspective Diffusion Language Models di Yu, Yifan, Jian, Yuqing, Wang, Junxiong, Zhou, Zhongzhu, Zhuang, Donglin, Fang, Xinyu, Yanamandra, Sri, Wu, Xiaoxia, Wu, Qingyang, Song, Shuaiwen Leon, Dao, Tri, Athiwaratkun, Ben, Zou, James, Lai, Fan, Xu, Chenfeng

Sommario: “... novel introspective strided decoding (ISD) algorithm, which enables the model to verify previously...”
Testo

Kaczmarz Linear Attention di Zou, Jiaxuan, Ren, Ruifeng, Liu, Yong

Sommario: “..., and chunkwise parallel algorithm. At the 0.4B scale with a 1B-token budget, KLA achieves the lowest validation...”
Testo

SPARQLe: Sub-Precision Activation Representation for Quantized LLM Inference di Parvathy, Aradhana Mohan, Ghosh, Soumendu Kumar, Kundu, Shamik, Raha, Arnab, Kundu, Souvik, Mathaikutty, Deepak A., Raghunathan, Anand

Sommario: “... lightweight algorithm to increase MSB sparsity. SPARQLe reduces activation memory traffic and enables...”
Testo

Electronics‐Free Wearable Platform for Computationally Guided Sweat Biomarker Recognition di Shiyao Li, Zhongzeng Zhou, Xueling Lin, Litong Chen, Yindie Wu, Conghui Liu, Tailin Xu

Sommario: “...‐decoding” of sweat biomarkers. For active information acquisition, we engineered a highly porous iron...”
Testo

On the Performance of Downlink Channel Estimation‐Based Cell‐Free Massive MIMO Systems Under Correlated Rician Fading Channels di Jiarui Li, Yao Zhang, Fengjiao Gan, Na Liu, Longxiang Yang, Hongbo Zhu

Sommario: “... decode downlink data solely based on uplink statistical channel state information (CSI). However...”
Testo

Invertible generative models for inverse problems: mitigating representation error and dataset bias di Asim, Muhammad, Daniels, Mara, Leong, Oscar, Ahmed, Ali, Hand, Paul

Sommario: “... or algorithmically by initialization. For compressive sensing, invertible priors can yield higher accuracy than...”
Testo