Risultati della ricerca - coding (algorithmicsics OR (algorithm OR (Algorithmsssssics OR (algorithm OR algorithm))))

Semantic Differentiation for Tackling Challenges in Watermarking Low-Entropy Constrained Generation Outputs di Le, Nghia T., Ritter, Alan, Goyal, Kartik

Sommario: “... with low-entropy output spaces. Therefore, we devise SeqMark, a sequence-level watermarking algorithm...”
Testo

Yuan3.0 Ultra: A Trillion-Parameter Enterprise-Oriented MoE LLM di ai, YuanLab., :, Wu, Shawn, Luo, Jiangang, Chen, Darcy, Wang, Sean, Li, Louie, Wang, Allen, Zhao, Xudong, Yu, Tong, Li, Bach, Shen, Joseph, Ma, Gawain, Jia, Jasper, Mao, Marcus, Wang, Claire, He, Hunter, Wang, Carol, Zhang, Zera, Wang, Jason, Shen, Chonly, Zhang, Leo, Chen, Logan, Meng, Qasim, Gong, James, Zhao, Daniel, Zheng, Penn, Zhu, Owen

Sommario: “... Layer-Adaptive Expert Pruning (LAEP) algorithm designed for the pre-training stage of MoE LLMs...”
Testo

Algorithmic Collusion at Test Time: A Meta-game Design and Evaluation di Luo, Yuhong, Schoepflin, Daniel, Wang, Xintong

Sommario: “...The threat of algorithmic collusion, and whether it merits regulatory intervention, remains debated...”
Testo

A Survey of Reinforcement Learning For Economics di Rawat, Pranjal

Sommario: “... such reduction. Reinforcement learning algorithms offer a natural, sample-based extension of dynamic programming...”
Testo

CICDWOA: A Collective Cognitive Sharing Whale Optimization Algorithm with Cauchy Inverse Cumulative Distribution for 2D/3D Path Planning and Engineering Design Problems di Wei, Junhao, Li, Yanxiao, Mirjalili, Seyedali, Yao, Dexing, Zhao, Yifu, Li, Haochen, Ye, Xudong, Li, Zikun, Xu, Qingyang, Lu, Baili, Cheong, Ngai, Yang, Dengcheng, Im, Sio-Kei, Wang, Yapeng, Yang, Xu

Sommario: “... WOA variant called CICDWOA. The proposed algorithm introduces a Good Nodes Set (GNS) method...”
Testo

Phased outcome-complete simulation di Kliuchnikov, Vadym, Paetznick, Adam, da Silva, Marcus P.

Sommario: “...We generalize the polynomial-time outcome-complete simulation algorithm for stabilizer circuits...”
Testo

Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning di Hu, Jiajun, Urpi, Nuria Armengol, Cheng, Jin, Coros, Stelian

Sommario: “...Zero-shot reinforcement learning (RL) algorithms aim to learn a family of policies from a reward...”
Testo

How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning di Chen, Jiangwei, Niu, Xinyuan, Sim, Rachael Hwee Ling, Liu, Zhengyuan, Chen, Nancy F., Low, Bryan Kian Hsiang

Sommario: “... unlearning algorithms, such as optimizing a weighted combination of losses, have tried to achieve...”
Testo

GMTHRASHpy: Forward Convolutions of Crossed Molecular Beams Experiments in Python di Fujioka, Kazuumi, Sun, Rui

Sommario: “.... The inputs and algorithm guiding it are explained. The code is open-source and can be downloaded...”
Testo

Construction of Multicyclic Codes of Arbitrary Dimension $r$ via Idempotents: A Unified Combinatorial-Algebraic Approach di Ramanandraibe, Jean Charles, Andriamifidisoa, Ramamonjy

Sommario: “...We propose a unified method to construct multicyclic codes of arbitrary dimension $r$ over $\mathbb...”
Testo

Efficient Information Reconciliation for High-Dimensional Quantum Key Distribution di Müller, Ronny, Ribezzo, Domenico, Zahidy, Mujtaba, Oxenløwe, Leif Katsuo, Bacco, Davide, Forchhammer, Søren

Sommario: “... and introduce two novel methods for reconciliation. The methods are based on nonbinary LDPC codes...”
Testo

REAL-AI-Benchmark: Real-World Reasoning and Physical-AI Benchmark Suite di Ivković, Jovan

Sommario: “... reasoning, algorithmic verification, code generation, reproducibility, and multimodal physical-AI decision...”
Testo

Protograph-Based LDPC Codes with Local Irregularity di Wüst, Vincent, Cil, Erdem Eray, Schmalen, Laurent

Sommario: “...Forward error correcting (FEC) codes are used in many communication standards with a wide range...”
Testo

Proximity-Informed Calibration for Deep Neural Networks di Xiong, Miao, Deng, Ailin, Koh, Pang Wei, Wu, Jiaying, Li, Shen, Xu, Jianqing, Hooi, Bryan

Sommario: “..., especially under safety-critical scenarios. However, we find that existing calibration algorithms often...”
Testo

Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers di Lin, Xiaoqiang, Wu, Zhaoxuan, Dai, Zhongxiang, Hu, Wenyang, Shu, Yao, Ng, See-Kiong, Jaillet, Patrick, Low, Bryan Kian Hsiang

Sommario: “... used the query-efficient Bayesian optimization (BO) algorithm to automatically optimize...”
Testo

NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generation di Dong, Hao, Frusque, Gaëtan, Zhao, Yue, Chatzi, Eleni, Fink, Olga

Sommario: “... introduce a novel algorithm for generating additional pseudo-anomalies on the basis of the limited labeled...”
Testo

The Effective Horizon Explains Deep RL Performance in Stochastic Environments di Laidlaw, Cassidy, Zhu, Banghua, Russell, Stuart, Dragan, Anca

Sommario: “.... These require strategic exploration algorithms that use relatively limited function classes for representing...”
Testo

CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving di Gao, Dechen, Cai, Shuangyu, Zhou, Hanchu, Wang, Hang, Soltani, Iman, Zhang, Junshan

Sommario: “... for training and testing such algorithms in sophisticated driving environments. To fill this void, we introduce...”
Testo

Fast and Globally Consistent Normal Orientation based on the Winding Number Normal Consistency di Lin, Siyou, Shi, Zuoqiang, Liu, Yebin

Sommario: “... their exciting progress, these algorithms either have high space/time complexity, or do not produce accurate...”
Testo

Annotation Cost-Efficient Active Learning for Deep Metric Learning Driven Remote Sensing Image Retrieval di Hoxha, Genc, Sumbul, Gencer, Henkel, Julia, Möllenbrok, Lars, Demir, Begüm

Sommario: “... pairs, we introduce two algorithms: 1) metric-guided uncertainty estimation (MGUE); and 2) binary...”
Testo