Risultati della ricerca - encoding (Algorithmssssics OR (algorithm OR ((algorithm OR algorithm) OR Algorithmssssics)))

Gradient Flows and Riemannian Structure in the Gromov-Wasserstein Geometry di Zhang, Zhengxin, Goldfeld, Ziv, Greenewald, Kristjan, Mroueh, Youssef, Sriperumbudur, Bharath K.

Sommario: “..., which underpins the Wasserstein geometry and enables gradient flow algorithms. However, the Wasserstein...”
Testo

Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning di Miao, Yanting, Loh, William, Kothawade, Suraj, Poupart, Pascal, Rashwan, Abdullah, Li, Yeqing

Sommario: “... for fine-tuning. Unlike most existing methods, our approach does not require training a text encoder...”
Testo

Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance di Zhu, Yongshuo, Li, Lu, Chen, Keyan, Liu, Chenyang, Zhou, Fugen, Shi, Zhenwei

Sommario: “.... Semantic-CC alleviates the dependency of high-generalization algorithms on extensive annotations...”
Testo

X-Fake: Juggling Utility Evaluation and Explanation of Simulated SAR Images di Huang, Zhongling, Zhuang, Yihan, Zhong, Zipei, Xu, Feng, Cheng, Gong, Han, Junwei

Sommario: “... the scarce training data for deep learning algorithms. Consequently, evaluating the quality of the simulated...”
Testo

Trimming the Risk: Towards Reliable Continuous Training for Deep Learning Inspection Systems di Abbassi, Altaf Allah, Braiek, Houssem Ben, Khomh, Foutse, Reid, Thomas

Sommario: “..., which are challenging to automate with rule-based machine vision algorithms. DL-powered inspection...”
Testo

OPUS: Occupancy Prediction Using a Sparse Set di Wang, Jiabao, Liu, Zhaojiang, Meng, Qiang, Yan, Liujiang, Wang, Ke, Yang, Jie, Liu, Wei, Hou, Qibin, Cheng, Ming-Ming

Sommario: “... voxels necessitates complex algorithm designs. To this end, we present a novel perspective...”
Testo

Towards practical secure delegated quantum computing with semi-classical light di Bourdoncle, Boris, Emeriau, Pierre-Emmanuel, Hilaire, Paul, Mansfield, Shane, Music, Luka, Wein, Stephen

Sommario: “... acquire some information about their data or algorithm. They also allow end-users to check...”
Testo

Implicit Neural Representations for Speed-of-Sound Estimation in Ultrasound di Byra, Michal, Jarosik, Piotr, Karwat, Piotr, Klimonda, Ziemowit, Lewandowski, Marcin

Sommario: “..., ranging from tomography-inspired algorithms like CUTE to convolutional networks, and more recently...”
Testo

Maia-2: A Unified Model for Human-AI Alignment in Chess di Tang, Zhenwei, Jiao, Difan, McIlroy-Young, Reid, Kleinberg, Jon, Sen, Siddhartha, Anderson, Ashton

Sommario: “... of algorithmically-informed teaching in these domains through more relatable AI partners and deeper insights...”
Testo

Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications di Minhas, Mishal Fatima, Putra, Rachmad Vidya Wicaksana, Awwad, Falah, Hasan, Osman, Shafique, Muhammad

Sommario: “... the principles of Spiking Neural Networks (SNNs) which enable efficient CL algorithms executed in dynamically...”
Testo

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

Sommario: “... introduce DAREx (DARE the eXtreme), which features two algorithmic improvements: (1) DAREx-q, a rescaling...”
Testo

Multi-modal Policies with Physics-informed Representations in Complex Fluid Environments di Feng, Haodong, Hu, Peiyan, Wang, Yue, Fan, Dixia

Sommario: “... Representation (PIR) algorithm for multi-modal policies of control to leverage the sparse and random observations...”
Testo

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

Sommario: “... by projecting points onto the 1-sphere, which allows for efficient encoding and decoding without requiring...”
Testo

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

Sommario: “.... The CSIF module, integrated into the encoder, employs self-attention to highlight similar features...”
Testo

Transferable Adversarial Attacks on SAM and Its Downstream Models di Xia, Song, Yang, Wenhan, Yu, Yi, Lin, Xun, Ding, Henghui, Duan, Ling-Yu, Jiang, Xudong

Sommario: “...) algorithm to extract the intrinsic vulnerability inherent in the foundation model, which is then utilized...”
Testo

Optimal planning for heterogeneous autonomous teams with precedence and compatibility constraints and its application on power grid inspection with Unmanned Aerial Vehicles di Sojo, Antonio, Maza, Iván, Ollero, Aníbal

Sommario: “... the different algorithms developed to solve the Vehicle Routing Problem (VRP) for all the different vehicles...”
Testo

Phonology-Guided Speech-to-Speech Translation for African Languages di Ochieng, Peter, Kaburu, Dennis

Sommario: “... to cross-phylum pairs. These findings motivate \textbf{SPaDA}, a dynamic-programming alignment algorithm...”
Testo

Modelling to Generate Continuous Alternatives: Enabling Real-Time Feasible Portfolio Generation in Convex Planning Models di Lau, Michael, Wang, Xin, Patankar, Neha, Jenkins, Jesse D.

Sommario: “...-processing algorithm for convex planning problems which enables users to rapidly generate new interior...”
Testo

Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction di Zhao, Shiyu, Wang, Zhenting, Juefei-Xu, Felix, Xia, Xide, Liu, Miao, Wang, Xiaofang, Liang, Mingfu, Zhang, Ning, Metaxas, Dimitris N., Yu, Licheng

Sommario: “...Prevailing Multimodal Large Language Models (MLLMs) encode the input image(s) as vision tokens...”
Testo

TurboFFT: Co-Designed High-Performance and Fault-Tolerant Fast Fourier Transform on GPUs di Wu, Shixun, Zhai, Yujia, Liu, Jinyang, Huang, Jiajun, Jian, Zizhe, Dai, Huangliang, Di, Sheng, Cappello, Franck, Chen, Zizhong

Sommario: “... algorithm-based fault tolerance (ABFT) at the thread and threadblock levels to reduce additional memory...”
Testo