Resultados de búsqueda - coding (algorithmssics OR (algorithm OR (Algorithmssssssics OR (algorithm OR algorithm))))

AI-Researcher: Autonomous Scientific Innovation por Tang, Jiabin, Xia, Lianghao, Li, Zhonghang, Huang, Chao

Tabla de Contenidos: “…The powerful reasoning capabilities of Large Language Models (LLMs) in mathematics and coding…”
Enlace del recurso

ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models por Chen, Hao, Li, Haoze, Xiao, Zhiqing, Gao, Lirong, Zhang, Qi, Hu, Xiaomeng, Wang, Ningtao, Fu, Xing, Zhao, Junbo

Tabla de Contenidos: “… (ALPS), an efficient algorithm that localizes the most task-sensitive attention heads and prunes…”
Enlace del recurso

Maximizing Confidence Alone Improves Reasoning por Prabhudesai, Mihir, Chen, Lili, Ippoliti, Alex, Fragkiadaki, Katerina, Liu, Hao, Pathak, Deepak

Tabla de Contenidos: “…, science, and coding problems. However, central to any RL algorithm is the reward function, and reward…”
Enlace del recurso

Adversarial Attacks on Robotic Vision Language Action Models por Jones, Eliot Krzysztof, Robey, Alexander, Zou, Andy, Ravichandran, Zachary, Pappas, George J., Hassani, Hamed, Fredrikson, Matt, Kolter, J. Zico

Tabla de Contenidos: “…-controlled robots. Our main algorithmic contribution is the adaptation and application of LLM jailbreaking…”
Enlace del recurso

How to Write a Simulator for Quantum Circuits from Scratch: A Tutorial por McGuffin, Michael J., Robert, Jean-Marc, Ikeda, Kazuki

Tabla de Contenidos: “…. With roughly 1000-2000 lines of code, one can simulate Hadamard, Pauli X, Y, Z, SWAP, and other quantum logic…”
Enlace del recurso

Accurate Reduced Floating-Point Precision Implicit Monte Carlo por Butson, Simon, Cleveland, Mathew, Long, Alex, Palmer, Todd

Tabla de Contenidos: “… manipulations involve changes to order of operations and alternative summation algorithms to minimize errors…”
Enlace del recurso

Generalized Proof-Number Monte-Carlo Tree Search por Kowalski, Jakub, Soemers, Dennis J. N. J., Kosakowski, Szymon, Winands, Mark H. M.

Tabla de Contenidos: “… track proof numbers per player. This reduces code complexity in the sense that we no longer need…”
Enlace del recurso

From High-SNR Radar Signal to ECG: A Transfer Learning Model with Cardio-Focusing Algorithm for Scenarios with Limited Data por Zhang, Yuanyuan, Zhao, Haocheng, Xiong, Sijie, Yang, Rui, Lim, Eng Gee, Yue, Yutao

Tabla de Contenidos: “… with limited data and propose a cardio-focusing and -tracking (CFT) algorithm to precisely track the cardiac…”
Enlace del recurso

Unimodal Strategies in Density-Based Clustering por Nir, Oron, Tenenbaum, Jay, Shamir, Ariel

Tabla de Contenidos: “… for finding appropriate values for the radius more efficiently based on the Ternary Search algorithm…”
Enlace del recurso

PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning por Guo, Weiran, Liu, Guanjun, Zhou, Ziyuan, Wang, Ling

Tabla de Contenidos: “… the properties of PNAct and design an attack algorithm. Finally, we conduct experiments to evaluate…”
Enlace del recurso

Rapid mixing for Gibbs states within a logical sector: a dynamical view of self-correcting quantum memories por Bergamaschi, Thiago, Gheissari, Reza, Liu, Yunchao

Tabla de Contenidos: “… ground state, this gives a rapid Gibbs state preparation algorithm for the 4D toric code in $\mathrm…”
Enlace del recurso

iLSU-T: an Open Dataset for Uruguayan Sign Language Translation por Stassi, Ariel E., Boria, Yanina, Di Martino, J. Matías, Randall, Gregory

Tabla de Contenidos: “… algorithms is presented. The aim is to establish a baseline for this dataset and evaluate its usefulness…”
Enlace del recurso

Whole-body Representation Learning For Competing Preclinical Disease Risk Assessment por Seletkov, Dmitrii, Starck, Sophie, Erdur, Ayhan Can, Zhang, Yundi, Rueckert, Daniel, Braren, Rickmer

Tabla de Contenidos: “… treatment to proactive identification and prevention. However, image-based risk prediction algorithms often…”
Enlace del recurso

AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning por Yuan, Shihao, Liu, Yahui, Yue, Yang, Zhang, Jingyuan, Zuo, Wangmeng, Wang, Qi, Zhang, Fuzheng, Zhou, Guorui

Tabla de Contenidos: “… models. We adapt the Group Relative Policy Optimization (GRPO) algorithm to refine the vanilla…”
Enlace del recurso

Event-Aware Sentiment Factors from LLM-Augmented Financial Tweets: A Transparent Framework for Interpretable Quant Trading por Wang, Yueyi, Wei, Qiyao

Tabla de Contenidos: “… is its commitment to transparency and reproducibility; all code and methodologies are made publicly…”
Enlace del recurso

SRAM-based Physically Unclonable Function using Lightweight Hamming-Code Fuzzy Extractor for Energy Harvesting Beat Sensors por Pham, Hoang-Long, Bui, Duy-Hieu, Tran, Xuan-Tu, Aiello, Orazio

Tabla de Contenidos: “… an SRAM-based Physically Unclonable Function (PUF) combining a high-reliability bit selection algorithm…”
Enlace del recurso

CTC Transcription Alignment of the Bullinger Letters: Automatic Improvement of Annotation Quality por Peer, Marco, Scius-Bertrand, Anna, Fischer, Andreas

Tabla de Contenidos: “… collection. We introduce a self-training method based on a CTC alignment algorithm that matches full…”
Enlace del recurso

Making Qwen3 Think in Korean with Reinforcement Learning por Lee, Jungyup, Kim, Jemin, Park, Sang, Lee, SeungJae

Tabla de Contenidos: “… reinforcement learning with a customized Group Relative Policy Optimization (GRPO) algorithm to further enhance…”
Enlace del recurso

Linear Preference Optimization: Decoupled Gradient Control via Absolute Regularization por Wang, Rui, Sun, Qianguo, Song, Chao, Wu, Junlong, Chen, Tianrong, Zeng, Zhiyun, Li, Yu

Tabla de Contenidos: “… algorithm due to its simplicity and training stability. However, DPO is prone to overfitting and collapse…”
Enlace del recurso

PseudoMapTrainer: Learning Online Mapping without HD Maps por Löwens, Christian, Funke, Thorben, Xie, Jingchao, Condurache, Alexandru Paul

Tabla de Contenidos: “… network. In addition, we introduce a mask-aware assignment algorithm and loss function to handle partially…”
Enlace del recurso