Résultats de la recherche - decoding (algorithmssics OR (algorithm OR (algorithmsssic OR Algorithmsssssic)))

The weight hierarchy of decreasing norm-trace codes par Camps-Moreno, Eduardo, López, Hiram H., Matthews, Gretchen L., San-José, Rodrigo

Table des matières: “… of type II, $t$-resilient functions, bounding the cardinality of the output in list decoding algorithms…”
Accéder au texte intégral

Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion par Zhu, Jianqing, Huang, Huang, Lin, Zhihang, Liang, Juhao, Tang, Zhengyang, Almubarak, Khalid, Alharthik, Abdulmohsen, An, Bang, He, Juncai, Wu, Xiangbo, Yu, Fei, Chen, Junying, Ma, Zhuoheng, Du, Yuhao, Zhang, He, Alghamdi, Emad A., Zhang, Lian, Sun, Ruoyu, Li, Haizhou, Wang, Benyou, Xu, Jinchao

Table des matières: “… for the tokenizer that could speed up decoding. However, using a different vocabulary often leads to a degradation…”
Accéder au texte intégral

Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning par Park, Sungjin, Liu, Xiao, Gong, Yeyun, Choi, Edward

Table des matières: “… reasoning benchmarks demonstrate that our approach outperforms both single language model decoding…”
Accéder au texte intégral

HashEvict: A Pre-Attention KV Cache Eviction Strategy using Locality-Sensitive Hashing par Liu, Minghui, Rabbani, Tahseen, O'Halloran, Tony, Sankaralingam, Ananth, Hartley, Mary-Anne, Huang, Furong, Fermüller, Cornelia, Aloimonos, Yiannis

Table des matières: “… significant GPU memory. In this work, we introduce HashEvict, an algorithm that uses locality-sensitive…”
Accéder au texte intégral

Shifting-Merging: Secure, High-Capacity and Efficient Steganography via Large Language Models par Bai, Minhao, Yang, Jinshuai, Pang, Kaiyi, Huang, Yongfeng, Gao, Yue

Table des matières: “… of ShiMer, we design a reordering algorithm to minimize the occurrence of interval splitting during decoding…”
Accéder au texte intégral

Realizing Lattice Surgery on Two Distance-Three Repetition Codes with Superconducting Qubits par Besedin, Ilya, Kerschbaum, Michael, Knoll, Jonathan, Hesner, Ian, Bödeker, Lukas, Colmenarez, Luis, Hofele, Luca, Lacroix, Nathan, Hellings, Christoph, Swiadek, François, Flasby, Alexander, Panah, Mohsen Bahrami, Zanuz, Dante Colao, Müller, Markus, Wallraff, Andreas

Table des matières: “… executing algorithms using hundreds of logical qubits. Recent experiments have demonstrated subthreshold…”
Accéder au texte intégral

Masked Generative Nested Transformers with Decode Time Scaling par Goyal, Sahil, Tula, Debapriya, Jain, Gagan, Shenoy, Pradeep, Jain, Prateek, Paul, Sujoy

Table des matières: “… computational efficiency. Most of these algorithms involve multiple passes over a transformer model to generate…”
Accéder au texte intégral

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

Table des matières: “… Information Gain Monte Carlo Tree Search (IG-MCTS), an online planning algorithm that jointly optimizes…”
Accéder au texte intégral

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

Table des matières: “… response (CFR) matrix in absence of pilots. The algorithm employs an encoder-decoder convolutional neural…”
Accéder au texte intégral

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

Table des matières: “…Referring expression counting (REC) algorithms are for more flexible and interactive counting…”
Accéder au texte intégral

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

Table des matières: “… coding schemes employed. In this paper, we introduce SINR, an innovative compression algorithm…”
Accéder au texte intégral

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

Table des matières: “…. Hattrick's game-engine mechanics are partially hidden, and users have attempted to decode them…”
Accéder au texte intégral

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

Table des matières: “… algorithm with iterative token-level decoding to address the common first-token latency issue in comparable…”
Accéder au texte intégral

Mamba Drafters for Speculative Decoding par 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

Table des matières: “…Speculative decoding has emerged as a promising approach to accelerating large language model (LLM…”
Accéder au texte intégral

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

Table des matières: “…Implementing large-scale quantum algorithms with practical advantage will require fault-tolerance…”
Accéder au texte intégral

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

Table des matières: “…{SPECS}$, a latency-aware test-time scaling method inspired by speculative decoding. $\texttt{SPECS…”
Accéder au texte intégral

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

Table des matières: “… further propose \textbf{INTER}: \textbf{Inter}action Guidance Sampling, a novel training-free algorithm…”
Accéder au texte intégral

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

Table des matières: “…. Unlike prior work that used custom architectures, our method employs a vanilla decoder-only Transformer…”
Accéder au texte intégral

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

Table des matières: “…. This poses challenges for efficient hardware implementation -- especially during the decode phase. This paper…”
Accéder au texte intégral

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

Table des matières: “… structure, multi-error correcting capability, and efficient decoding algorithms. Despite their practical…”
Accéder au texte intégral