Résultats de la recherche - decoding (algorithm OR algorithmsssic)

Reduced bit median quantization: A middle process for Efficient Image Compression par Abebayew, Fikresilase Wondmeneh

Table des matières: “… the former problem by applying one specific or a combination of different algorithms. However, none…”
Accéder au texte intégral

Game of Coding: Sybil Resistant Decentralized Machine Learning with Minimal Trust Assumption par Nodehi, Hanzaleh Akbari, Cadambe, Viveck R., Maddah-Ali, Mohammad Ali

Table des matières: “… their rewards (utility) by ensuring that the decoder, as the data collector (DC), successfully recovers the data…”
Accéder au texte intégral

Nudging: Inference-time Alignment of LLMs via Guided Decoding par Fei, Yu, Razeghi, Yasaman, Singh, Sameer

Table des matières: “… computational overhead. In this work, we propose NUDGING, a simple, training-free algorithm that aligns any base…”
Accéder au texte intégral

DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models par Deng, Wenlong, Zhao, Yize, Vakilian, Vala, Chen, Minghui, Li, Xiaoxiao, Thrampoulidis, Christos

Table des matières: “… introduce DAREx (DARE the eXtreme), which features two algorithmic improvements: (1) DAREx-q, a rescaling…”
Accéder au texte intégral

Pyramid Vector Quantization for LLMs par van der Ouderaa, Tycho F. A., Croci, Maximilian L., Hilmkil, Agrin, Hensman, James

Table des matières: “… by projecting points onto the 1-sphere, which allows for efficient encoding and decoding without requiring…”
Accéder au texte intégral

AGSENet: A Robust Road Ponding Detection Method for Proactive Traffic Safety par Zhang, Ronghui, Yang, Shangyu, Lyu, Dakang, Wang, Zihan, Chen, Junzhou, Ren, Yilong, Gao, Bolin, Lv, Zhihan

Table des matières: “… by fusing spatial and channel information. The SSIE module, embedded in the decoder, refines edge features…”
Accéder au texte intégral

A scalable generative model for dynamical system reconstruction from neuroimaging data par Volkmann, Eric, Brändle, Alena, Durstewitz, Daniel, Koppe, Georgia

Table des matières: “… of signals render the SSM's decoder model non-invertible, a requirement for previous TF-based methods. Here…”
Accéder au texte intégral

PGSO: Prompt-based Generative Sequence Optimization Network for Aspect-based Sentiment Analysis par Dong, Hao, Wei, Wei

Table des matières: “… to paraphrase training targets for enhanced decoding, ignoring the internal optimizations on generative models…”
Accéder au texte intégral

Enhancing Large-scale UAV Route Planing with Global and Local Features via Reinforcement Graph Fusion par Zhou, Tao, Ye, Kai, Shi, Zeyu, Lin, Jiajing, Xu, Dejun, Jiang, Min

Table des matières: “… by graph fusion. Finally, we implement a decoding strategy customizable to the user's requirements…”
Accéder au texte intégral

Mask-RadarNet: Enhancing Transformer With Spatial-Temporal Semantic Context for Radar Object Detection in Autonomous Driving par Wu, Yuzhi, Liu, Jun, Jiang, Guangfeng, Liu, Weijian, Orlando, Danilo

Table des matières: “… decoder is added to our model to aggregate prior maps generated from the CMAM. Experiments on the CRUW…”
Accéder au texte intégral

Interoceptive Robots for Convergent Shared Control in Collaborative Construction Work par Zhou, Xiaoshan, Menassa, Carol C., Kamat, Vineet R.

Table des matières: “… by integrating the legacy of heuristic costs from grid/graph-based algorithms with recent advances…”
Accéder au texte intégral

High Efficiency Wiener Filter-based Point Cloud Quality Enhancement for MPEG G-PCC par Wei, Yuxuan, Wang, Zehan, Guo, Tian, Liu, Hao, Shen, Liquan, Yuan, Hui

Table des matières: “… be integrated into the encoder and decoder pipeline of G-PCC to improve the reconstruction quality as well…”
Accéder au texte intégral

Enhancing LLM-based Quantum Code Generation with Multi-Agent Optimization and Quantum Error Correction par Campbell, Charlie, Chen, Hao Mark, Luk, Wayne, Fan, Hongxiang

Table des matières: “… analyzer with multi-pass inference, alongside an error correction code decoder. We also examine…”
Accéder au texte intégral

SparseMeXT Unlocking the Potential of Sparse Representations for HD Map Construction par Jiang, Anqing, Chai, Jinhao, Gao, Yu, Wang, Yiru, Heng, Yuwen, Sun, Zhigang, Sun, Hao, Zhao, Zezhong, Sun, Li, Zhou, Jian, Zhu, Lijuan, Xu, Shugong, Zhao, Hao

Table des matières: “… and algorithmic improvements that bridge the gap with--and ultimately surpass--dense approaches. We introduce a…”
Accéder au texte intégral

VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning par Lu, Guanxing, Guo, Wenkai, Zhang, Chubin, Zhou, Yuheng, Jiang, Haonan, Gao, Zifeng, Tang, Yansong, Wang, Ziwei

Table des matières: “… this limitation. We present VLA-RL, an algorithmic and systematic framework that leverages online reinforcement…”
Accéder au texte intégral

MoESD: Unveil Speculative Decoding's Potential for Accelerating Sparse MoE par Huang, Zongle, Zhu, Lei, Zhan, Zongyuan, Hu, Ting, Mao, Weikai, Yu, Xianzhi, Liu, Yongpan, Zhang, Tianyu

Table des matières: “… achieve better performance with less computation. Speculative decoding (SD) is a widely used technique…”
Accéder au texte intégral

Design Automation in Quantum Error Correction par Ghosh, Archisman, Chatterjee, Avimita, Ghosh, Swaroop

Table des matières: “… algorithmic $T$-gate optimization, modified surface code architecture to incorporate lesser qubit overhead…”
Accéder au texte intégral

Exploiting scattering-based point spread functions for snapshot 5D and modality-switchable lensless imaging par Zheng, Ze, Liu, Baolei, Song, Jiaqi, Zhu, Muchen, Wang, Yao, Tian, Menghan, Xiong, Ying, Yang, Zhaohua, Zhong, Xiaolan, McGloin, David, Wang, Fan

Table des matières: “… diffuser, and subsequently decoded using a compressed sensing algorithm at the sampling rate of 2.5…”
Accéder au texte intégral

EC2MoE: Adaptive End-Cloud Pipeline Collaboration Enabling Scalable Mixture-of-Experts Inference par Yang, Zheming, Hu, Yunqing, Sun, Sheng, Ji, Wen

Table des matières: “… to accelerate MoE inference. This includes an encoder-decoder structure based on low-rank compression, which…”
Accéder au texte intégral

P/D-Device: Disaggregated Large Language Model between Cloud and Devices par Jin, Yibo, Xu, Yixu, Chen, Yue, Wang, Chengbin, Wang, Tao, Huang, Jiaqi, Zhang, Rongfei, Dong, Yiming, Yan, Yuting, Cheng, Ke, Zhu, Yingjie, Wang, Shulan, Tang, Qianqian, Meng, Shuaishuai, Cheng, Guanxin, Wang, Ze, Miao, Shuyan, Wang, Ketao, Liu, Wen, Yang, Yifan, Zhang, Tong, Wang, Anran, Lu, Chengzhou, Dong, Tiantian, Zhang, Yongsheng, Wang, Zhe, Guo, Hefei, Liu, Hongjie, Lu, Wei, Zhang, Zhengyong

Table des matières: “… for enhanced performance. However, too many tokens generated in decoding phase, i.e., occupying the resources…”
Accéder au texte intégral