Suchergebnisse - decoding (algorithm OR (Algorithmsssic OR algorithmsssic))

GapDNER: A Gap-Aware Grid Tagging Model for Discontinuous Named Entity Recognition von Yang, Yawen, Ma, Fukun, Meng, Shiao, Liu, Aiwei, Wen, Lijie

Inhaltsangabe: “… or internal tokens, which face challenges of error propagation and decoding ambiguity due to the wide variety …”
Volltext

Semantic representations emerge in biologically inspired ensembles of cross-supervising neural networks von Urbach, Roy, Schneidman, Elad

Inhaltsangabe: “… or decoding, but typically rely on biologically-implausible implementations. We suggest that interactions …”
Volltext

Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding von Reisizadeh, Hadi, Ruan, Jiajun, Chen, Yiwei, Pal, Soumyadeep, Liu, Sijia, Hong, Mingyi

Inhaltsangabe: “… deterministic (greedy) decoding often suggest successful knowledge removal using standard benchmarks, we show …”
Volltext

Support Recovery in One-bit Compressed Sensing with Near-Optimal Measurements and Sublinear Time von Li, Xiaxin, Mazumdar, Arya

Inhaltsangabe: “… methods minimize the number of measurements but often incur $Ω(n)$ decoding complexity, limiting large …”
Volltext

AI/ML based Joint Source and Channel Coding for HARQ-ACK Payload von Doshi, Akash, Sen, Pinar, Ivanov, Kirill, Yang, Wei, Namgoong, June, Wang, Runxin, Wang, Rachel, Yoo, Taesang, Jiang, Jing, Ji, Tingfang

Inhaltsangabe: “… , we learn a transformer-based encoder using a novel "free-lunch" training algorithm and propose per …”
Volltext

Toward Robust, Reproducible, and Widely Accessible Intracranial Language Brain-Computer Interfaces: A Comprehensive Review of Neural Mechanisms, Hardware, Algorithms, Evaluation, C... von He, Dongyi, Siok, Wai Ting, Wang, Nizhuan

Inhaltsangabe: “… by fragmented evidence and unresolved design trade-offs across neuroscience, hardware, algorithm, evaluation …”
Volltext

Polar Complexity: A New Descriptive Complexity with Applications to Source and Joint Source-Channel Coding von Yao, Xinyuanmeng, Ma, Xiao

Inhaltsangabe: “… compression and successive cancellation decoding (SCD), and define the polar complexity of a sequence …”
Volltext

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference von Lin, Jian, Mi, Jiazhi, Hong, Zicong, Wang, Haodong, Liu, Qianli, Zhang, Haodyue, Li, Peng, Guo, Song

Inhaltsangabe: “… critical entries during decoding, but this strategy quickly hits a ceiling: sparsity cannot be pushed …”
Volltext

Shared autonomy between human electroencephalography and TD3 deep reinforcement learning: A multi‐agent copilot approach von Chun‐Ren Phang, Akimasa Hirata

Inhaltsangabe: “… Deep reinforcement learning (RL) algorithms enable the development of fully autonomous agents that can …”
Volltext

Unitary Complexity and the Uhlmann Transformation Problem von Bostanci, John, Efron, Yuval, Metger, Tony, Poremba, Alexander, Qian, Luowen, Yuen, Henry

Inhaltsangabe: “… this as the Uhlmann Transformation Problem, an algorithmic version of Uhlmann's theorem. Then, we prove structural …”
Volltext

Enhancing Perception Quality in Remote Sensing Image Compression via Invertible Neural Network von Li, Junhui, Hou, Xingsong

Inhaltsangabe: “… an existing image compression algorithm and encode it as a set of Gaussian-distributed latent variables via …”
Volltext

Learning to Estimate System Specifications in Linear Temporal Logic using Transformers and Mamba von Işık, İlker, Gol, Ebru Aydin, Cinbis, Ramazan Gokberk

Inhaltsangabe: “… : transformer encoder-decoder, decoder-only transformer, and Mamba, which is an emerging alternative …”
Volltext

QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation von Faria, Gonçalo R. A., Agrawal, Sweta, Farinhas, António, Rei, Ricardo, de Souza, José G. C., Martins, André F. T.

Inhaltsangabe: “… and minimum Bayes risk decoding). However, relying on a single translation with high estimated quality …”
Volltext

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

Inhaltsangabe: “… -- or watermark -- during the model's decoding process. Most existing watermarking methods require access …”
Volltext

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

Inhaltsangabe: “… -tuning the SAM-Mona encoder along with a feature aggregator. Subsequently, a pixel decoder …”
Volltext

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

Inhaltsangabe: “… Window Decoding algorithm, which greatly improves the inference speed by making the number of frames …”
Volltext

AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding von 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

Inhaltsangabe: “… system designed to support efficient multi-SLO serving through SLO-customized speculative decoding …”
Volltext

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

Inhaltsangabe: “… caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set …”
Volltext

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

Inhaltsangabe: “… latency and meeting Service Level Objectives (SLOs) under dynamic request patterns. Speculative decoding …”
Volltext

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

Inhaltsangabe: “… decoder. Coupled with a high-level policy trained via offline RL techniques, our method establishes a …”
Volltext