Risultati della ricerca - (coding OR decoding) (algorithm OR (Algorithmsssic OR Algorithmsssic))

Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning di Li, Xinran, Pan, Ling, Zhang, Jun

Sommario: “... in the context of actor-critic algorithms, which could help improve value estimations.Our empirical evaluations...”
Testo

Optimal Inferential Control of Convolutional Neural Networks di Vaziri, Ali, Fang, Huazhen

Sommario: “... leverage ensemble Kalman smoothing, a sequential Monte Carlo algorithm, to take advantage of its...”
Testo

LibEER: A Comprehensive Benchmark and Algorithm Library for EEG-based Emotion Recognition di Liu, Huan, Yang, Shusen, Zhang, Yuzhe, Wang, Mengze, Gong, Fanyu, Xie, Chengxi, Liu, Guanjian, Liu, Zejun, Liu, Yong-Jin, Lu, Bao-Liang, Zhang, Dalin

Sommario: “... benchmark and algorithm library designed to facilitate fair comparisons in EER. LibEER carefully selects...”
Testo

AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization di Wu, Junkang, Wang, Xue, Yang, Zhengyi, Wu, Jiancan, Gao, Jinyang, Ding, Bolin, Wang, Xiang, He, Xiangnan

Sommario: “... preference optimization algorithm designed to address these limitations by introducing a dynamic reward...”
Testo

AutoTurb: Using Large Language Models for Automatic Algebraic Model Discovery of Turbulence Closure di Zhang, Yu, Zheng, Kefeng, Liu, Fei, Zhang, Qingfu, Wang, Zhenkun

Sommario: “.... The deduced EARSM can be readily implemented in existing computational fluid dynamic (CFD) codes and promotes...”
Testo

POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization di Karaman, Batuhan K., Zabir, Ishmam, Benhaim, Alon, Chaudhary, Vishrav, Sabuncu, Mert R., Song, Xia

Sommario: “... that are highly safe but prone to overrefusal. POROver employs preference optimization algorithms and leverages...”
Testo

Automated Model Discovery for Tensional Homeostasis: Constitutive Machine Learning in Growth and Remodeling di Holthusen, Hagen, Brepols, Tim, Linka, Kevin, Kuhl, Ellen

Sommario: “.... To address this challenge, built-in physics machine learning algorithms offer significant potential...”
Testo

MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations di Xu, Liang, Hua, Shaoyang, Lin, Zili, Liu, Yifan, Ma, Feipeng, Yan, Yichao, Jin, Xin, Yang, Xiaokang, Zeng, Wenjun

Sommario: “... better motion text alignment, we also meticulously devise a motion caption generation algorithm...”
Testo

Ensemble-based, large-eddy reconstruction of wind turbine inflow in a near-stationary atmospheric boundary layer through generative artificial intelligence di Rybchuk, Alex, Martínez-Tossas, Luis A., Letizia, Stefano, Hamilton, Nicholas, Scholbrock, Andy, Maric, Emina, Houck, Daniel R., Herges, Thomas G., de Velder, Nathaniel B., Doubrawa, Paula

Sommario: “... and atmospheric model information through a diffusion model machine learning algorithm, allowing us to generate...”
Testo

Agent Skill Acquisition for Large Language Models via CycleQD di Kuroki, So, Nakamura, Taishi, Akiba, Takuya, Tang, Yujin

Sommario: “... of the algorithm, along with a model merging based crossover and an SVD-based mutation. In CycleQD, each task...”
Testo

AlphaChimp: Tracking and Behavior Recognition of Chimpanzees di Ma, Xiaoxuan, Lin, Yutang, Xu, Yuan, Kaufhold, Stephan P., Terwilliger, Jack, Meza, Andres, Zhu, Yixin, Rossano, Federico, Wang, Yizhou

Sommario: “... of their social interactions and the lack of specialized algorithms. Existing methods often struggle...”
Testo

Brain-like Variational Inference di Vafaii, Hadi, Galor, Dekel, Yates, Jacob L.

Sommario: “... and Gaussian-based predictive coding models in sparsity, reconstruction, and biological plausibility...”
Testo

Energy-Based Diffusion Language Models for Text Generation di Xu, Minkai, Geffner, Tomas, Kreis, Karsten, Nie, Weili, Xu, Yilun, Leskovec, Jure, Ermon, Stefano, Vahdat, Arash

Sommario: “... propose an efficient generation algorithm via parallel important sampling. Comprehensive experiments...”
Testo

Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning di Luo, Jianlan, Xu, Charles, Wu, Jeffrey, Levine, Sergey

Sommario: “... coordination. Our approach integrates demonstrations and human corrections, efficient RL algorithms, and other...”
Testo

How Do Developers Use Type Inference: An Exploratory Study in Kotlin di Flint, Samuel W., Keshk, Ali M., Dyer, Robert, Bagheri, Hamid

Sommario: “...Statically typed languages offer numerous benefits to developers, such as improved code quality...”
Testo

Bridge-IF: Learning Inverse Protein Folding with Markov Bridges di Zhu, Yiheng, Wu, Jialu, Li, Qiuyi, Yan, Jiahuan, Yin, Mingze, Wu, Wei, Li, Mingyang, Ye, Jieping, Wang, Zheng, Wu, Jian

Sommario: “... learning algorithms for this task has seen significant success, the prevailing approaches, which...”
Testo

SSFold: Learning to Fold Arbitrary Crumpled Cloth Using Graph Dynamics from Human Demonstration di Zhou, Changshi, Xu, Haichuan, Hu, Jiarui, Luan, Feng, Wang, Zhipeng, Dong, Yanchao, Zhou, Yanmin, He, Bin

Sommario: “... algorithm to gather and integrate human demonstration data into our novel end-to-end neural network...”
Testo

FedCVD: The First Real-World Federated Learning Benchmark on Cardiovascular Disease Data di Zhang, Yukun, Chen, Guanzhong, Xu, Zenglin, Wang, Jianyong, Zeng, Dun, Li, Junfan, Wang, Jinghua, Qi, Yuan, King, Irwin

Sommario: “... in realistic datasets that challenges current FL algorithms. To address these gaps, this paper presents...”
Testo

DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection di Li, Shawn, Gong, Huixian, Dong, Hao, Yang, Tiankai, Tu, Zhengzhong, Zhao, Yue

Sommario: “..., and nine base OOD algorithms demonstrate that DPU significantly improves OOD detection performance, setting...”
Testo

GROOT: Effective Design of Biological Sequences with Limited Experimental Data di Tran, Thanh V. T., Ngo, Nhat Khang, Nguyen, Viet Anh, Hy, Truong Son

Sommario: “... algorithms toward optimal outputs. However, existing methods struggle when labeled data is limited...”
Testo