Risultati della ricerca - decoding (algorithm OR Algorithmssic)

Preferential subspace identification (PSID) with forward-backward smoothing di Sani, Omid G., Shanechi, Maryam M.

Sommario: “... develop a novel forward-backward PSID smoothing algorithm where we first apply PSID with filtering...”
Testo

AI Enabled 6G for Semantic Metaverse: Prospects, Challenges and Solutions for Future Wireless VR di Mohsin, Muhammad Ahmed, Bhattacharya, Sagnik, Gorle, Abhiram, Jamshed, Muhammad Ali, Cioffi, John M.

Sommario: “... optimization approach for the users' energy allocation and decoding order appears to provide large improvements...”
Testo

Segment Any Vehicle: Semantic and Visual Context Driven SAM and A Benchmark di Wang, Xiao, Wang, Ziwen, Wu, Wentao, Wang, Anjie, Wu, Jiashu, Pan, Yantao, Li, Chenglong

Sommario: “... and segmentation, has placed increasingly higher demands on algorithmic performance. Pre-trained large segmentation...”
Testo

Flag at origin: a modular fault-tolerant preparation for CSS codes di Forlivesi, Diego, Amaro, David

Sommario: “..., the circuit becomes FT. To manage the associated overhead, we propose an algorithm that discovers optimal...”
Testo

Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm di Yang, Kaisen, He, Lixuan, Shah, Rushi, Yang, Kaicheng, Ma, Qinwei, Liu, Dianbo, Lamb, Alex

Sommario: “... algorithm enforcing strict plan adherence - with a subsequent Reinforcement Learning (RL) stage...”
Testo

A Unified Model for Multi-Task Drone Routing in Post-Disaster Road Assessment di Gong, Huatian, Sheu, Jiuh-Biing, Wang, Zheng, Yang, Xiaoguang, Yan, Ran

Sommario: “... modern transformer encoder-decoder architecture. A lightweight adapter mechanism further enables...”
Testo

High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection di Chen, Zhiyuan, Guo, Yuelin, Huang, Zitong, He, Haoyu, Lu, Renhao, Zhang, Weizhe

Sommario: “... of overfitting to synthetic patterns. Third, our cascade denoising algorithm dynamically adjusts training weights...”
Testo

GPR: Towards a Generative Pre-trained One-Model Paradigm for Large-Scale Advertising Recommendation di Zhang, Jun, Li, Yi, Liu, Yue, Wang, Changping, Wang, Yuan, Xiong, Yuling, Liu, Xun, Wu, Haiyang, Li, Qian, Zhang, Enming, Sun, Jiawei, Xu, Xin, Zhang, Zishuai, Liu, Ruoran, Huang, Suyuan, Zhang, Zhaoxin, Guo, Zhengkai, Yang, Shuojin, Guo, Meng-Hao, Yu, Huan, Jiang, Jie, Hu, Shi-Min

Sommario: “... heterogeneous data. Second, we develop the Heterogeneous Hierarchical Decoder (HHD), a dual-decoder architecture...”
Testo

Improved Offline Reinforcement Learning via Quantum Metric Encoding di Lv, Outongyi, Yuan, Yewei, Liu, Nana

Sommario: “...-Learning (IQL), two well-known RL algorithms, to demonstrate the effectiveness of our approach. From...”
Testo

LiteCache: A Query Similarity-Driven, GPU-Centric KVCache Subsystem for Efficient LLM Inference di Yi, Jiawei, Gong, Ping, Bai, Youhui, Jin, Zewen, Wang, Shengnan, Ruan, Jiaqi, He, Jia, Zhu, Jiaan, Wang, Pengcheng, Wang, Haibo, Wang, Weiguang, Zhu, Xia, Li, Cheng

Sommario: “... and retrieve highly overlapping top-k KV states. This insight enables a simple head granularity cache algorithm...”
Testo

Taming the Memory Footprint Crisis: System Design for Production Diffusion LLM Serving di Fan, Jiakun, Zhang, Yanglin, Li, Xiangchen, Nikolopoulos, Dimitrios S.

Sommario: “... Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research...”
Testo

Generative Recommendation for Large-Scale Advertising di Xue, Ben, Liu, Dan, Wang, Lixiang, Sun, Mingjie, Wang, Peng, Zhang, Pengfei, Shi, Shaoyun, Xu, Tianyu, Sha, Yunhao, Liu, Zhiqiang, Kong, Bo, Wang, Bo, Yang, Hang, Xue, Jieting, Wang, Junhao, Wang, Shengyu, Hui, Shuping, Ye, Wencai, Lin, Xiao, Li, Yongzhi, Chen, Yuhang, Yin, Zhihui, Chen, Quan, Wen, Shiyang, Wu, Wenjin, Li, Han, Zhou, Guorui, Li, Changcheng, Jiang, Peng, Gai, Kun

Sommario: “...AD introduces LazyAR, a lazy autoregressive decoder that relaxes layer-wise dependencies for short...”
Testo

Mamba-3: Improved Sequence Modeling using State Space Principles di Lahoti, Aakash, Li, Kevin Y., Chen, Berlin, Wang, Caitlin, Bick, Aviv, Kolter, J. Zico, Dao, Tri, Gu, Albert

Sommario: “... for algorithmic efficiency, failing on tasks such as state tracking. Moreover, their theoretically linear...”
Testo

TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification di Luo, Guan, Li, Xiu, Chen, Rui, Yi, Xuanyu, Lin, Jing, Chen, Chia-Hao, Liu, Jiahang, Zhang, Song-Hai, Zhang, Jianfeng

Sommario: “... meshes into DMC-compliant representations via a remeshing algorithm that preserves sharp edges using an L...”
Testo

RosettaSearch: Multi-Objective Inference-Time Search for Protein Sequence Design di Kshirsagar, Meghana, Nie, Allen, Cheng, Ching-An, Xue, Fanglei, Dodhia, Rahul, Ferres, Juan Lavista, Yang, Kevin K., DiMaio, Frank

Sommario: “... search algorithm capable of controlled exploration and exploitation, using rewards computed from...”
Testo

NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains di Peng, Shiyao, Zheng, Qianhe, Hao, Zhuodi, Tang, Zichen, Li, Rongjin, Huang, Qing, Huang, Jiayu, Liu, Jiacheng, Zhu, Yifan, E, Haihong

Sommario: “... an innovative activated search algorithm to obtain a refined candidate space. Then it ensures precise evidence...”
Testo

Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models di Jiang, Yan, Qiu, Ruihong, Huang, Zi

Sommario: “... size has therefore become a vital factor in dLLMs, since it determines the parallel decoding...”
Testo

Parallax: Parameterized Local Linear Attention for Language Modeling di Zuo, Yifei, Pai, Dhruv, Zeng, Zhichen, Dewulf, Alec, Hu, Shuming, Wang, Zhaoran

Sommario: “... by the bandwidth, the probe construction and the affine structure. We propose a hardware-aware algorithm...”
Testo

Dynamic High‐Capacity Structural‐Color Encryption Via Inkjet Printing and Image Recognition di Rujun Li, Kaixuan Li, Xiao Deng, Congzhi Jiang, An Li, Luanluan Xue, Renxuan Yuan, Quan Liu, Zongbo Zhang, Huizeng Li, Yanlin Song

Sommario: “... the high‐capacity information input in a low‐cost way. Moreover, through computer programming and algorithm...”
Testo

Implementation of Anti‐Interference and High‐Speed Underwater Acoustic Communication via Chip‐Level Parallel Ghost Imaging di Qi Xi, Bing‐He Ma, Ji‐Zhen Liu, Zong‐Lin Li, Zhi‐Chuang Chang, Zhi‐Yong Tian, Long‐Sheng Zeng, Yu‐Gui Peng, Xue‐Feng Zhu, Zhi‐Bo Ma

Sommario: “... information is first launched via the speckle multiplexing technology, all of which can then be well decoded...”
Testo