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

ReALLM: A general framework for LLM compression and fine-tuning di Leconte, Louis, Bedin, Lisa, Nguyen, Van Minh, Moulines, Eric

Sommario: “... and a single forward pass with the decoder. Our weight-only quantization algorithm yields the best...”
Testo

Tele-Aloha: A Low-budget and High-authenticity Telepresence System Using Sparse RGB Cameras di Tu, Hanzhang, Shao, Ruizhi, Dong, Xue, Zheng, Shunyuan, Zhang, Hao, Chen, Lili, Wang, Meili, Li, Wenyu, Ma, Siyan, Zhang, Shengping, Zhou, Boyao, Liu, Yebin

Sommario: “... communication. As the core of Tele-Aloha, we propose an efficient novel view synthesis algorithm for upper-body...”
Testo

Fair Computation Offloading for RSMA-Assisted Mobile Edge Computing Networks di Xu, Ding, Duan, Lingjie, Zhao, Haitao, Zhu, Hongbo

Sommario: “... develop an efficient algorithm to obtain a suboptimal solution. Particularly, the time allocation...”
Testo

Knowledge Fusion By Evolving Weights of Language Models di Du, Guodong, Li, Jing, Liu, Hanting, Jiang, Runhua, Yu, Shuyang, Guo, Yifei, Goh, Sim Kuan, Tang, Ho-Kin

Sommario: “... by evolutionary algorithms, which does not need further training or additional training data. Specifically, our...”
Testo

Efficiently improving key weather variables forecasting by performing the guided iterative prediction in latent space di Li, Shuangliang, Li, Siwei

Sommario: “... large number of weather variables. Therefore, we propose an 'encoding-prediction-decoding' prediction...”
Testo

Multi-User SR-LDPC Codes di Ebert, Jamison R., Chamberland, Jean-Francois, Narayanan, Krishna R.

Sommario: “... the sent information, the decoder jointly processes the received signals using a low-complexity and highly...”
Testo

RIS-Aided Unsourced Multiple Access (RISUMA): Coding Strategy and Performance Limits di Ahmadi, Mohammad Javad, Kazemi, Mohammad, Duman, Tolga M.

Sommario: “... and a randomly spread polar codeword. The proposed decoder operates in two phases. In the first phase...”
Testo

FastFixer: An Efficient and Effective Approach for Repairing Programming Assignments di Liu, Fang, Liu, Zhenwei, Zhao, Qianhui, Jiang, Jing, Zhang, Li, Li, Ge, Sun, Zian, Li, Zhongqi, Ma, Yuchi

Sommario: “... remarkable inference speedup of 16.67 times compared to the autoregressive decoding algorithm. ...”
Testo

Channel Reflection: Knowledge-Driven Data Augmentation for EEG-Based Brain-Computer Interfaces di Wang, Ziwei, Li, Siyang, Luo, Jingwei, Liu, Jiajing, Wu, Dongrui

Sommario: “...) using different decoding algorithms demonstrated that: 1) CR is effective, i.e., it can noticeably...”
Testo

URoadNet: Dual Sparse Attentive U-Net for Multiscale Road Network Extraction di Song, Jie, Sun, Yue, Cai, Ziyun, Xiao, Liang, Huang, Yawen, Zheng, Yefeng

Sommario: “...The challenges of road network segmentation demand an algorithm capable of adapting to the sparse...”
Testo

Deep Learning in Wireless Communication Receiver: A Survey di Doha, Shadman Rahman, Abdelhadi, Ahmed

Sommario: “... receivers depend on mathematical models and algorithms, which do not have the ability to adapt or learn from...”
Testo

Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models di Zhang, Ce, Wan, Zifu, Kan, Zhehan, Ma, Martin Q., Stepputtis, Simon, Ramanan, Deva, Salakhutdinov, Russ, Morency, Louis-Philippe, Sycara, Katia, Xie, Yaqi

Sommario: “... Decoding with Generative Feedback (DeGF), a novel training-free algorithm that incorporates feedback from...”
Testo

Leveraging Small LLMs for Argument Mining in Education: Argument Component Identification, Classification, and Assessment di Favero, Lucile, Pérez-Ortiz, Juan Antonio, Käser, Tanja, Oliver, Nuria

Sommario: “...Argument mining algorithms analyze the argumentative structure of essays, making them a valuable...”
Testo

STAR-RIS-aided NOMA for Secured xURLLC di Lulu, Song, Di, Zhang, Shaobo, Jia, Pengcheng, Zhu, Yonghui, Li

Sommario: “...), which provides additional degree of freedom to enable a secure and fair decoding order and achieve a...”
Testo

SigChord: Sniffing Wide Non-sparse Multiband Signals for Terrestrial and Non-terrestrial Wireless Networks di Peng, Jinbo, Duan, Junwen, Lin, Zheng, Yuan, Haoxuan, Gao, Yue, Chen, Zhe

Sommario: “... on low-cost and sub-Nyquist sampling radios. We first design a deep and rule-based interleaving algorithm...”
Testo

SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting di Xu, Jiaming, Pan, Jiayi, Zhou, Yongkang, Chen, Siming, Li, Jinhao, Lian, Yaoxiu, Wu, Junyi, Dai, Guohao

Sommario: “... SpecEE, a fast LLM inference engine with speculative early exiting. (1) At the algorithm level, we...”
Testo

LMDepth: Lightweight Mamba-based Monocular Depth Estimation for Real-World Deployment di Long, Jiahuan, Zhou, Xin

Sommario: “..., existing depth estimation algorithms often struggle to effectively balance performance and computational...”
Testo

Antenna Activation and Resource Allocation in Multi-Waveguide Pinching-Antenna Systems di Wang, Kaidi, Ding, Zhiguo, Karagiannidis, George K.

Sommario: “...-theoretic algorithm is developed, in which the optimal decoding order is derived and incorporated. For power...”
Testo

One Trigger Token Is Enough: A Defense Strategy for Balancing Safety and Usability in Large Language Models di Gu, Haoran, Wang, Handing, Mei, Yi, Zhang, Mengjie, Jin, Yaochu

Sommario: “... simple yet effective defense algorithm that identifies and explicitly decodes safety trigger tokens...”
Testo

Semi-Clairvoyant Scheduling of Speculative Decoding Requests to Minimize LLM Inference Latency di Li, Ruixiao, Chen, Fahao, Li, Peng

Sommario: “...Speculative decoding accelerates Large Language Model (LLM) inference by employing a small...”
Testo