Résultats de la recherche - decoding (algorithmics OR (Algorithmsssssic OR (Algorithmsssssic OR algorithm)))

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

Table des matières: “… and a single forward pass with the decoder. Our weight-only quantization algorithm yields the best…”
Accéder au texte intégral

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

Table des matières: “… communication. As the core of Tele-Aloha, we propose an efficient novel view synthesis algorithm for upper-body…”
Accéder au texte intégral

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

Table des matières: “… develop an efficient algorithm to obtain a suboptimal solution. Particularly, the time allocation…”
Accéder au texte intégral

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

Table des matières: “… by evolutionary algorithms, which does not need further training or additional training data. Specifically, our…”
Accéder au texte intégral

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

Table des matières: “… large number of weather variables. Therefore, we propose an 'encoding-prediction-decoding' prediction…”
Accéder au texte intégral

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

Table des matières: “… the sent information, the decoder jointly processes the received signals using a low-complexity and highly…”
Accéder au texte intégral

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

Table des matières: “… and a randomly spread polar codeword. The proposed decoder operates in two phases. In the first phase…”
Accéder au texte intégral

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

Table des matières: “… remarkable inference speedup of 16.67 times compared to the autoregressive decoding algorithm. …”
Accéder au texte intégral

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

Table des matières: “…) using different decoding algorithms demonstrated that: 1) CR is effective, i.e., it can noticeably…”
Accéder au texte intégral

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

Table des matières: “…The challenges of road network segmentation demand an algorithm capable of adapting to the sparse…”
Accéder au texte intégral

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

Table des matières: “… receivers depend on mathematical models and algorithms, which do not have the ability to adapt or learn from…”
Accéder au texte intégral

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

Table des matières: “… Decoding with Generative Feedback (DeGF), a novel training-free algorithm that incorporates feedback from…”
Accéder au texte intégral

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

Table des matières: “…Argument mining algorithms analyze the argumentative structure of essays, making them a valuable…”
Accéder au texte intégral

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

Table des matières: “…), which provides additional degree of freedom to enable a secure and fair decoding order and achieve a…”
Accéder au texte intégral

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

Table des matières: “… on low-cost and sub-Nyquist sampling radios. We first design a deep and rule-based interleaving algorithm…”
Accéder au texte intégral

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

Table des matières: “… SpecEE, a fast LLM inference engine with speculative early exiting. (1) At the algorithm level, we…”
Accéder au texte intégral

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

Table des matières: “…, existing depth estimation algorithms often struggle to effectively balance performance and computational…”
Accéder au texte intégral

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

Table des matières: “…-theoretic algorithm is developed, in which the optimal decoding order is derived and incorporated. For power…”
Accéder au texte intégral

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

Table des matières: “… simple yet effective defense algorithm that identifies and explicitly decodes safety trigger tokens…”
Accéder au texte intégral

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

Table des matières: “…Speculative decoding accelerates Large Language Model (LLM) inference by employing a small…”
Accéder au texte intégral