Risultati della ricerca - decoding (algorithm OR Algorithmsics)

Spark Transformer: Reactivating Sparsity in FFN and Attention di You, Chong, Wu, Kan, Jia, Zhipeng, Chen, Lin, Bhojanapalli, Srinadh, Guo, Jiaxian, Evci, Utku, Wassenberg, Jan, Netrapalli, Praneeth, Willcock, Jeremiah J., Subramanian, Suvinay, Chern, Felix, Andreev, Alek, Pathak, Shreya, Yu, Felix, Jain, Prateek, Culler, David E., Levy, Henry M., Kumar, Sanjiv

Sommario: “... introduce statistical top-k, a hardware-accelerator-friendly, linear-time approximate algorithm that avoids...”
Testo

Machine Learning for Quantum Noise Reduction di Kendre, Karan

Sommario: “... require substantial qubit overhead and complex syndrome decoding, we propose a machine learning approach...”
Testo

OjaKV: Context-Aware Online Low-Rank KV Cache Compression di Zhu, Yuxuan, Yang, David H., Amiri, Mohammad Mohammadi, Murugesan, Keerthiram, Pedapati, Tejaswini, Chen, Pin-Yu

Sommario: “... basis using Oja's algorithm for online principal component analysis. This adaptation involves a...”
Testo

SparseServe: Unlocking Parallelism for Dynamic Sparse Attention in Long-Context LLM Serving di Zhou, Qihui, Yin, Peiqi, Zuo, Pengfei, Cheng, James

Sommario: “... length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV...”
Testo

Flexible-Sector 6DMA Base Station: Modeling and Design di Li, Yunli, Shi, Xiaoming, Shao, Xiaodan, Xu, Jie, Zhang, Rui

Sommario: “...-forcing (ZF) based receiver applied at the BS to decode multiuser signals, we derive the average sum rate...”
Testo

C2|Q>: A Robust Framework for Bridging Classical and Quantum Software Development di Ye, Boshuai, Khan, Arif Ali, Pihkakoski, Teemu, Liang, Peng, Akbar, Muhammad Azeem, Silveri, Matti, Malmi, Lauri

Sommario: “..., algorithm configuration, hardware selection, and result interpretation - making them difficult for classical...”
Testo

LUT-LLM: Efficient Large Language Model Inference with Memory-based Computations on FPGAs di He, Zifan, Ye, Shengyu, Ma, Rui, Wang, Yang, Cong, Jason

Sommario: “... and deploy language models due to algorithm and architecture design limitations. This paper introduces...”
Testo

MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping di Huang, Yushi, Wang, Zining, Yuan, Zhihang, Ding, Yifu, Gong, Ruihao, Guo, Jinyang, Liu, Xianglong, Zhang, Jun

Sommario: “... the optimal thresholds, we introduce a frontier search algorithm that exploits monotonicity properties...”
Testo

IndexCache: Accelerating Sparse Attention via Cross-Layer Index Reuse di Bai, Yushi, Dong, Qian, Jiang, Ting, Lv, Xin, Du, Zhengxiao, Zeng, Aohan, Tang, Jie, Li, Juanzi

Sommario: “... and optimize this configuration. Training-free IndexCache applies a greedy search algorithm that selects which...”
Testo

Expanders Meet Reed-Muller: Easy Instances of Noisy k-XOR di Błasiok, Jarosław, Lou, Paul, Rosen, Alon, Sudan, Madhu

Sommario: “... interpretation of the vertices of their graphs, the noisy XOR problem turns into the problem of decoding Reed...”
Testo

Token-Budget-Aware Pool Routing for Cost-Efficient LLM Inference di Chen, Huamin, Liu, Xunzhuo, Jiang, Junchen, He, Bowei, Liu, Xue

Sommario: “... at 10,000 req/s shows \$15.4M/yr in savings. The algorithm adds O(1) dispatch overhead, self-calibrates...”
Testo

Monolithic MoS 2 Strain‐Tunable Spectrometer for on‐Chip Hyperspectral Imaging di Qikun Li, Yong Wang, Wenqiang Lu, Qinglei Guo, Zewei Ren, Jianguang Lu, Chengming Jiang

Sommario: “... decoding mechanism, is presented. Leveraging the exceptional electromechanical coupling and strain‐tunable...”
Testo

FMint: Bridging Human Designed and Data Pretrained Models for Differential Equation Foundation Model for Dynamical Simulation di Zezheng Song, Jiaxin Yuan, Haizhao Yang

Sommario: “... decoder‐only transformer architecture with in‐context learning, FMint utilizes both numerical and textual...”
Testo

Reinnervation of Muscle Targets Enhances the Separability of Motor Unit Signals Following Peripheral Nerve Transfers di Kiara N Quinn, Siyu Wang, Lang Qin, Alessandro Ascani Orsini, Kenzi Griffith, Rachana Suresh, Fausto Kang, Pierce L Perkins, Neha Joshi, Alexis L Lowe, Sami Tuffaha, Nitish V Thakor

Sommario: “... to decode motor intention, which limits their ability to replicate natural limb movements. Decomposing EMG...”
Testo

A clustering‐based user pairing scheme for downlink 3D non‐orthogonal multiple access‐based visible light communication systems di Tanuja Dogra, Manoranjan Rai Bharti

Sommario: “... in literature to implement NOMA effectively so as to reduce the decoding order of successive interference...”
Testo

An Improved Power Allocation Scheme for Downlink NOMA‐Based MIMO Visible Light Communication Systems di Tanuja Dogra, Manoranjan Rai Bharti

Sommario: “... as on the user index in the decoding order. In the proposed power allocation scheme, multiple transmitting light...”
Testo

ADT‐UNet: An Innovative Algorithm for Glioma Segmentation in MR Images di Liu Zhipeng, Wu Jiawei, Jing Ye, Xuefeng Bian, Wu Qiwei, Rui Li, Yinxing Zhu

Sommario: “...‐UNet, an innovative algorithm for segmenting glioma tumors in MR images. ADT‐UNet leveraged attention...”
Testo

A Risk Stratification Study of Ultrasound Images of Thyroid Nodules Based on Improved DETR di Zhang Le, Yue Liang, Xiaokang Hu, Taorong Qiu, Pan Xu

Sommario: “... diagnosis system for thyroid nodule ultrasound images, and the existing algorithms for detecting...”
Testo

Software Reliability Prediction by Adaptive Gated Recurrent Unit‐Based Encoder‐Decoder Model With Ensemble Empirical Mode Decomposition di Minghao Yang, Shunkun Yang, Chong Bian

Sommario: “... quality assessment. With the rapid development of machine learning and intelligent algorithms, data‐driven...”
Testo

URRel : Joint Entity and Relation Extraction in Chinese Medical Texts via Unified Representation and Reinforcement Learning With Overlapping Relations di Zekai Xu, Jijun Tong, Yetao Tong, Shudong Xia, Qingli Zhou, Yuqiang Shen

Sommario: “... process and uses an Actor‐Critic RL algorithm to dynamically optimise the extraction strategy and reduce...”
Testo