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

IG-MCTS: Human-in-the-Loop Cooperative Navigation under Incomplete Information di Chen, Shenghui, Zhao, Ruihan, Chinchali, Sandeep, Topcu, Ufuk

Sommario: “... Information Gain Monte Carlo Tree Search (IG-MCTS), an online planning algorithm that jointly optimizes...”
Testo

Uplink OFDM Channel Prediction with Hybrid CNN-LSTM for 6G Non-Terrestrial Networks di De Filippo, Bruno, Amatetti, Carla, Vanelli-Coralli, Alessandro

Sommario: “... response (CFR) matrix in absence of pilots. The algorithm employs an encoder-decoder convolutional neural...”
Testo

Exploring Contextual Attribute Density in Referring Expression Counting di Wang, Zhicheng, Pan, Zhiyu, Peng, Zhan, Cheng, Jian, Xiao, Liwen, Jiang, Wei, Cao, Zhiguo

Sommario: “...Referring expression counting (REC) algorithms are for more flexible and interactive counting...”
Testo

SINR: Sparsity Driven Compressed Implicit Neural Representations di Jayasundara, Dhananjaya, Rajagopalan, Sudarshan, Ranasinghe, Yasiru, Tran, Trac D., Patel, Vishal M.

Sommario: “... coding schemes employed. In this paper, we introduce SINR, an innovative compression algorithm...”
Testo

Decoding the mechanisms of the Hattrick football manager game using Bayesian network structure learning di Constantinou, Anthony C., Higgins, Nicholas, Kitson, Neville K.

Sommario: “.... Hattrick's game-engine mechanics are partially hidden, and users have attempted to decode them...”
Testo

Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models di Liu, Yi, Liu, Dianqing, Zhu, Mingye, Guo, Junbo, Zhang, Yongdong, Mao, Zhendong

Sommario: “... algorithm with iterative token-level decoding to address the common first-token latency issue in comparable...”
Testo

Mamba Drafters for Speculative Decoding di Choi, Daewon, Oh, Seunghyuk, Dingliwal, Saket, Tack, Jihoon, Kim, Kyuyoung, Song, Woomin, Kim, Seojin, Han, Insu, Shin, Jinwoo, Galstyan, Aram, Katiyar, Shubham, Bodapati, Sravan Babu

Sommario: “...Speculative decoding has emerged as a promising approach to accelerating large language model (LLM...”
Testo

Leveraging erasure errors in logical qubits with metastable $^{171}$Yb atoms di Zhang, Bichen, Liu, Genyue, Bornet, Guillaume, Horvath, Sebastian P., Peng, Pai, Ma, Shuo, Huang, Shilin, Puri, Shruti, Thompson, Jeff D.

Sommario: “...Implementing large-scale quantum algorithms with practical advantage will require fault-tolerance...”
Testo

$\texttt{SPECS}$: Faster Test-Time Scaling through Speculative Drafts di Cemri, Mert, Rajaraman, Nived, Tiwari, Rishabh, Liu, Xiaoxuan, Keutzer, Kurt, Stoica, Ion, Ramchandran, Kannan, Beirami, Ahmad, Sun, Ziteng

Sommario: “...{SPECS}$, a latency-aware test-time scaling method inspired by speculative decoding. $\texttt{SPECS...”
Testo

INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling di Dong, Xin, Dong, Shichao, Wang, Jin, Huang, Jing, Zhou, Li, Sun, Zenghui, Jing, Lihua, Lan, Jingsong, Zhu, Xiaoyong, Zheng, Bo

Sommario: “... further propose \textbf{INTER}: \textbf{Inter}action Guidance Sampling, a novel training-free algorithm...”
Testo

Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error di Giannoulis, Panagiotis, Pantis, Yorgos, Tzamos, Christos

Sommario: “.... Unlike prior work that used custom architectures, our method employs a vanilla decoder-only Transformer...”
Testo

AMLA: MUL by ADD in FlashAttention Rescaling di Liao, Qichen, Hu, Chengqiu, Miao, Fangzheng, Li, Bao, Liu, Yiyang, Lyu, Junlong, Jiang, Lirui, Wang, Jun, Zheng, Lingchao, Li, Jun, Fan, Yuwei

Sommario: “.... This poses challenges for efficient hardware implementation -- especially during the decode phase. This paper...”
Testo

The dimension and Bose distance of some BCH codes of length $\frac{q^{m}-1}λ$ di Zheng, Run, Sze, Nung-Sing, Huang, Zejun

Sommario: “... structure, multi-error correcting capability, and efficient decoding algorithms. Despite their practical...”
Testo

Not every day is a sunny day: Synthetic cloud injection for deep land cover segmentation robustness evaluation across data sources di Mobsite, Sara, Hostache, Renaud, Equille, Laure Berti, Roux, Emmanuel, Guerin, Joris

Sommario: “... cloud injection algorithm that simulates realistic cloud cover, allowing us to test how Sentinel-1 radar...”
Testo

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning di Song, Yuda, Rohatgi, Dhruv, Singh, Aarti, Bagnell, J. Andrew

Sommario: “... simulated locomotion tasks--we investigate the algorithmic trade-off between privileged expert distillation...”
Testo

Robust Analog Lagrange Coded Computing: Theory and Algorithms via Discrete Fourier Transforms di Borah, Rimpi, Harshan, J.

Sommario: “... foundational step, we use error-correction algorithms for Discrete Fourier Transform (DFT) codes to build novel...”
Testo

Understanding and Improving Communication Performance in Multi-node LLM Inference di Singhania, Prajwal, Singh, Siddharth, Hough, Lannie Dalton, Srivastava, Akarsh, Menon, Harshitha, Jekel, Charles Fredrick, Bhatele, Abhinav

Sommario: “... hierarchical all-reduce algorithm based on recursive doubling with NVSHMEM. NVRAR achieves up to 1.9$\times...”
Testo

On the Information-Theoretic Fragility of Robust Watermarking under Diffusion Editing di Ni, Yunyi, Yang, Ziyu, Niu, Ze, Davis, Emily, Carter, Finn

Sommario: “... the watermarked image and the embedded payload approaches zero, causing watermark decoding to fail. We further...”
Testo

$A^3$: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving di Zhou, Yuechi, Su, Yi, Zhang, Jianxin, Li, Juntao, Xia, Qingrong, Wang, Zhefeng, Duan, Xinyu, Huai, Baoxing

Sommario: “... their ability to handle long sequences, the resulting decoding latency and memory overhead remain substantial...”
Testo

Doppler Robust Vortex Wavefront Design for Integrated Sensing and Communication di Liu, Yuan, Long, Wen-Xuan, Shankar, M. R. Bhavani, Moretti, Marco, Chen, Rui, Ottersten, Björn

Sommario: “...-consistency matching (VCM)-expectation maximization (EM) algorithm that jointly decodes the sensing matrix...”
Testo