Risultati della ricerca - coding (algorithm OR Algorithmsssic)

A Technical Survey of Reinforcement Learning Techniques for Large Language Models di Srivastava, Saksham Sahai, Aggarwal, Vaneet

Sommario: “... models, highlighting prominent algorithms such as Proximal Policy Optimization (PPO), Q-Learning...”
Testo

Interaction between skew-representability, tensor products, extension properties, and rank inequalities di Bérczi, Kristóf, Gehér, Boglárka, Imolay, András, Lovász, László, Padró, Carles, Schwarcz, Tamás

Sommario: “... and linear algebra. They play an important role in areas such as coding theory, optimization...”
Testo

Ensemble Foreground Management for Unsupervised Object Discovery di Wu, Ziling, Moemeni, Armaghan, Caleb-Solly, Praminda

Sommario: “... in UOD algorithms. However, the absence of ground truth provides existing UOD methods with two challenges...”
Testo

TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback di Pang, Lei, Luo, Jun, Jin, Ruinan

Sommario: “... reinforcement learning algorithm for fine-tuning large language models. GRPO replaces the value function...”
Testo

Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuning di Tian, Chang, Blaschko, Matthew B., Xing, Mingzhe, Li, Xiuxing, Yue, Yinliang, Moens, Marie-Francine

Sommario: “... of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because...”
Testo

SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication di Zhang, Ruijia, Zhao, Xinyan, Wang, Ruixiang, Chen, Sigen, Zhang, Guibin, Zhang, An, Wang, Kun, Wen, Qingsong

Sommario: “... pretrained GNNs or greedy algorithms, but often isolate pre- and post-task optimization, lacking a unified...”
Testo

CaPGNN: Optimizing Parallel Graph Neural Network Training with Joint Caching and Resource-Aware Graph Partitioning di Song, Xianfeng, Zou, Yi, Shi, Zheng

Sommario: “... algorithm that leverages both CPU and GPU memory, integrating lightweight cache update and prefetch...”
Testo

Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems di Shukla, Manish

Sommario: “... metrics such as goal drift and harm reduction but did not provide an algorithmic instantiation...”
Testo

STORI: A Benchmark and Taxonomy for Stochastic Environments di Barsainyan, Aryan Amit, Lim, Jing Yu, Liu, Dianbo

Sommario: “... algorithms can be tuned to succeed. The absence of a well-defined taxonomy of stochasticity further...”
Testo

$Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation di Wei, Yuan, Shan, Xiaohan, Miao, Ran, Li, Jianmin

Sommario: “...$ autonomously translates natural language task descriptions and environment code into executable RL solutions...”
Testo

A Multidimensional Self-Adaptive Numerical Simulation Framework for Semiconductor Boltzmann Transport Equation di Zhang, Zeyu, Zhang, Xiaoyu, Song, Zhigang, Fang, Qing

Sommario: “... transformation. On the programming front, a parallelized MATLAB algorithm is developed to optimize code execution...”
Testo

d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation di Wang, Guanghan, Turok, Gilad, Schiff, Yair, Arriola, Marianne, Kuleshov, Volodymyr

Sommario: “... gradient algorithm that relies on accurate estimates of the sampling trajectory likelihoods. Because...”
Testo

TriAlignXA: An Explainable Trilemma Alignment Framework for Trustworthy Agri-product Grading di Xie, Jianfei, Li, Ziyang

Sommario: “...' (TTI). We redefine the role of algorithms from 'decision-makers' to 'providers of transparent decision...”
Testo

The Current State of AI Bias Bounties: An Overview of Existing Programmes and Research di Kucenko, Sergej, Dennler, Nathaniel, He, Fengxiang

Sommario: “.... The five research publications included a report on the application of bug bounties to algorithmic harms...”
Testo

Hybrid Schemes of NIST Post-Quantum Cryptography Standard Algorithms and Quantum Key Distribution for Key Exchange and Digital Signature di Chen, Abel C. H.

Sommario: “...Since the security of post-quantum cryptography (PQC) algorithms is based on the hardness...”
Testo

OCTOPUS: A Versatile, User-Friendly, and Extensible Public Code for General-Relativistic Ray-Tracing in Spherically Symmetric and Static Spacetimes di Hu, Shiyang, Tan, Shijie, Li, Dan, Zhang, Lina, Deng, Chen, Cao, Wenfu

Sommario: “...This paper presents OCTOPUS, a relativistic ray-tracing algorithm developed within a Fortran-based...”
Testo

NetMCP: Network-Aware Model Context Protocol Platform for LLM Capability Extension di Li, Enhan, Du, Hongyang, Huang, Kaibin

Sommario: “... MCP tool routing algorithms with real-time awareness of network and server status. To provide a...”
Testo

Implementing Multi-GPU Scientific Computing Miniapps Across Performance Portable Frameworks di Villalobos, Johansell, Ruzicka, Josef, Rizzi, Silvio

Sommario: “... hardware platforms with minimal code changes. In this direction, this paper presents preliminary time...”
Testo

TYrPPG: Uncomplicated and Enhanced Learning Capability rPPG for Remote Heart Rate Estimation di Chen, Taixi, Cheung, Yiu-ming

Sommario: “... language processing tasks, demonstrating potential as a substitute for transformer-based algorithms...”
Testo

DKDS: A Benchmark Dataset of Degraded Kuzushiji Documents with Seals for Detection and Binarization di Ju, Rui-Yang, Yamashita, Kohei, Kameko, Hirotaka, Mori, Shinsuke

Sommario: “... algorithms, traditional algorithms combined with K-means clustering, two state-of-the-art (SOTA) generative...”
Testo