Résultats de la recherche - decoding ((Algorithmssics OR algorithm) OR (algorithm OR algorithmicsics))

PostMark: A Robust Blackbox Watermark for Large Language Models par Chang, Yapei, Krishna, Kalpesh, Houmansadr, Amir, Wieting, John, Iyyer, Mohit

Table des matières: “… -- or watermark -- during the model's decoding process. Most existing watermarking methods require access…”
Accéder au texte intégral

Tuning a SAM-Based Model with Multi-Cognitive Visual Adapter to Remote Sensing Instance Segmentation par Zheng, Linghao, Pu, Xinyang, Xu, Feng

Table des matières: “…-tuning the SAM-Mona encoder along with a feature aggregator. Subsequently, a pixel decoder…”
Accéder au texte intégral

Breaking Through the Spike: Spike Window Decoding for Accelerated and Precise Automatic Speech Recognition par Zhang, Wei, Zhang, Tian-Hao, Luo, Chao, Zhou, Hui, Yang, Chao, Qian, Xinyuan, Yin, Xu-Cheng

Table des matières: “… Window Decoding algorithm, which greatly improves the inference speed by making the number of frames…”
Accéder au texte intégral

AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding par Li, Zikun, Chen, Zhuofu, Delacourt, Remi, Oliaro, Gabriele, Wang, Zeyu, Chen, Qinghan, Lin, Shuhuai, Yang, April, Zhang, Zhihao, Chen, Zhuoming, Lai, Sean, Cheng, Xinhao, Miao, Xupeng, Jia, Zhihao

Table des matières: “… system designed to support efficient multi-SLO serving through SLO-customized speculative decoding…”
Accéder au texte intégral

Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs par Zhu, Kan, Tang, Tian, Xu, Qinyu, Gu, Yile, Zeng, Zhichen, Kadekodi, Rohan, Zhao, Liangyu, Li, Ang, Krishnamurthy, Arvind, Kasikci, Baris

Table des matières: “… caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set…”
Accéder au texte intégral

AdaSpec: Adaptive Speculative Decoding for Fast, SLO-Aware Large Language Model Serving par Huang, Kaiyu, Wu, Hao, Shi, Zhubo, Zou, Han, Yu, Minchen, Shi, Qingjiang

Table des matières: “… latency and meeting Service Level Objectives (SLOs) under dynamic request patterns. Speculative decoding…”
Accéder au texte intégral

Offline Reinforcement Learning with Discrete Diffusion Skills par Qiao, RuiXi, Cheng, Jie, Dai, Xingyuan, Tian, Yonglin, Lv, Yisheng

Table des matières: “… decoder. Coupled with a high-level policy trained via offline RL techniques, our method establishes a…”
Accéder au texte intégral

Machine-Learning-Powered Neural Interfaces for Smart Prosthetics and Diagnostics par Shaeri, MohammadAli, Liu, Jinhan, Shoaran, Mahsa

Table des matières: “… in AI-driven decoding algorithms and energy-efficient System-on-Chip (SoC) platforms for next-generation…”
Accéder au texte intégral

Guided Speculative Inference for Efficient Test-Time Alignment of LLMs par Geuter, Jonathan, Mroueh, Youssef, Alvarez-Melis, David

Table des matières: “…We propose Guided Speculative Inference (GSI), a novel algorithm for efficient reward-guided…”
Accéder au texte intégral

The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Dataset par Landau, Gilad, Özdogan, Miran, Elvers, Gereon, Mantegna, Francesco, Somaiya, Pratik, Jayalath, Dulhan, Kurth, Luisa, Kwon, Teyun, Shillingford, Brendan, Farquhar, Greg, Jiang, Minqi, Jerbi, Karim, Abdelhedi, Hamza, Ramos, Yorguin Mantilla, Gulcehre, Caglar, Woolrich, Mark, Voets, Natalie, Jones, Oiwi Parker

Table des matières: “…The advance of speech decoding from non-invasive brain data holds the potential for profound…”
Accéder au texte intégral

D-CNN and VQ-VAE Autoencoders for Compression and Denoising of Industrial X-ray Computed Tomography Images par Hejazi, Bardia, Chand, Keerthana, Fritsch, Tobias, Bruno, Giovanni

Table des matières: “… autoencoders and examines how these compression algorithms affect the quality of the recovered data. Two…”
Accéder au texte intégral

DSDE: Dynamic Speculative Decoding with KLD Stability for Real-World Serving par Yang, Mingyu, Choi, Jae-Young, Moon, Kihyo, Jang, Minsung, Jeon, Eunjoo

Table des matières: “…Speculative decoding accelerates large language model inference, but its reliance on a fixed…”
Accéder au texte intégral

LLM DNA: Tracing Model Evolution via Functional Representations par Wu, Zhaomin, Zhao, Haodong, Wang, Ziyang, Guo, Jizhou, Wang, Qian, He, Bingsheng

Table des matières: “… the evolutionary tree of LLMs using phylogenetic algorithms, which align with shifts from encoder-decoder…”
Accéder au texte intégral

Layer codes as partially self-correcting quantum memories par Gu, Shouzhen, Caha, Libor, Choe, Shin Ho, He, Zhiyang, Kubica, Aleksander, Tang, Eugene

Table des matières: “… memories. First, we introduce two decoding algorithms for layer codes with provable guarantees for local…”
Accéder au texte intégral

A Gate-Based Quantum Genetic Algorithm for Real-Valued Global Optimization par Souza, Leandro C., Dardenne, Laurent E., Portugal, Renato

Table des matières: “…. In this model, individuals are represented by quantum circuits whose measurement outcomes are decoded into real…”
Accéder au texte intégral

EXACT: Explicit Attribute-Guided Decoding-Time Personalization par Yu, Xin, Xing, Hanwen, Xue, Lingzhou

Table des matières: “… context. While decoding-time personalization offers a scalable alternative to training-time methods…”
Accéder au texte intégral

CHESS: Context-aware Hierarchical Efficient Semantic Selection for Long-Context LLM Inference par Fei, Chao, Li, Guozhong, Liu, Chenxi, Kalnis, Panos

Table des matières: “…Long-context LLMs demand accurate inference at low latency, yet decoding becomes primarily…”
Accéder au texte intégral

A Universal Systematic Method to Generate Error Patterns on Memoryless Channels par Jalaleddine, Marwan, Li, Jiajie, Abbas, Syed Mohsin, Gross, Warren J.

Table des matières: “…The high computational cost of approaching the performance of Maximum-likelihood (ML) decoding has…”
Accéder au texte intégral

Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training par Feng, Xidong, Wan, Ziyu, Wen, Muning, McAleer, Stephen Marcus, Wen, Ying, Zhang, Weinan, Wang, Jun

Table des matières: “… the reasoning capabilities of LLMs by using tree-search algorithms to guide multi-step reasoning. These methods…”
Accéder au texte intégral

Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Losses par Abdelaleem, Eslam, Nemenman, Ilya, Martini, K. Michael

Table des matières: “… that in a decoder graph (defining a generative model for data). Using this approach, we rederive existing…”
Accéder au texte intégral