Risultati della ricerca - coding (algorithm OR (algorithmics OR (algorithmssssics OR algorithmicsics)))

Differentiable programming across the PDE and Machine Learning barrier di Bouziani, Nacime, Ham, David A., Farsi, Ado

Sommario: “... physical laws as inductive bias to machine learning algorithms, also referred to as physics-driven machine...”
Testo

Learning to Better Search with Language Models via Guided Reinforced Self-Training di Moon, Seungyong, Park, Bumsoo, Song, Hyun Oh

Sommario: “... reinforced self-training (Guided-ReST), a fine-tuning algorithm designed to improve the model's capability...”
Testo

The Impact of Initial Composition on Massive Star Evolution and Nucleosynthesis di West, Christopher, Heger, Alexander, Cote, Benoit, Serxner, Lev, Sun, Haoxuan

Sommario: “... the KEPLER stellar evolution code, with 7 initial stellar masses, 12 initial metallicities, and two for each...”
Testo

Language Model Evolutionary Algorithms for Recommender Systems: Benchmarks and Algorithm Comparisons di Liu, Jiao, Sun, Zhu, Feng, Shanshan, Chen, Caishun, Ong, Yew-Soon

Sommario: “... of evolutionary algorithms (EAs), enabling them to tackle optimization problems involving structured language...”
Testo

Evaluating Single Event Upsets in Deep Neural Networks for Semantic Segmentation: an embedded system perspective di Gutiérrez-Zaballa, Jon, Basterretxea, Koldo, Echanobe, Javier

Sommario: “...As the deployment of artifical intelligence (AI) algorithms at edge devices becomes increasingly...”
Testo

From Code to Play: Benchmarking Program Search for Games Using Large Language Models di Eberhardinger, Manuel, Goodman, James, Dockhorn, Alexander, Perez-Liebana, Diego, Gaina, Raluca D., Çakmak, Duygu, Maghsudi, Setareh, Lucas, Simon

Sommario: “...Large language models (LLMs) have shown impressive capabilities in generating program code, opening...”
Testo

Facial Surgery Preview Based on the Orthognathic Treatment Prediction di Han, Huijun, Zhang, Congyi, Zhu, Lifeng, Singh, Pradeep, Hsung, Richard Tai Chiu, Leung, Yiu Yan, Komura, Taku, Wang, Wenping, Gu, Min

Sommario: “... parametric model for 3D reconstruction of the patient, medical-related losses to guide latent code prediction...”
Testo

Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision di Ye, Yaowen, Laidlaw, Cassidy, Steinhardt, Jacob

Sommario: “... supervision, SFT still retains some effectiveness, but DPO (a common RLHF algorithm) fails to improve...”
Testo

Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation di Sinha, Shiven, Goel, Shashwat, Kumaraguru, Ponnurangam, Geiping, Jonas, Bethge, Matthias, Prabhu, Ameya

Sommario: “... of algorithmic problem solving, where counterexamples can be evaluated automatically using code execution...”
Testo

Style Content Decomposition-based Data Augmentation for Domain Generalizable Medical Image Segmentation di Shen, Zhiqiang, Cao, Peng, Yang, Jinzhu, Zaiane, Osmar R., Chen, Zhaolin

Sommario: “... factorize an image into style codes and content maps, explicitly modeling the "style" and "content...”
Testo

Teaching Your Models to Understand Code via Focal Preference Alignment di Wu, Jie, Li, Haoling, Zhang, Xin, Liu, Xiao, Huang, Yangyu, Luo, Jianwen, Zhang, Yizhen, Li, Zuchao, Chu, Ruihang, Yang, Yujiu, Li, Scarlett

Sommario: “... entire failing code blocks rather than pinpointing specific errors, it lacks the granularity necessary...”
Testo

Multiple solutions to the static forward free-boundary Grad-Shafranov problem on MAST-U di Pentland, K., Amorisco, N. C., Farrell, P. E., Ham, C. J.

Sommario: “... and integral free-boundary conditions (commonly used in production-level equilibrium codes) has remained...”
Testo

Decoding Islamophobic Discourse: Using LLMs to Identify Tropes and Semi-Coded Hate Speech di Mustafa, Raza Ul, Dupart, Roi, Smith, Gabrielle, Ashraf, Noman, Japkowicz, Nathalie

Sommario: “...-coded Islamophobic terms such as (muzrat, pislam, mudslime, mohammedan, muzzies) floated on extremist...”
Testo

Migrating Code At Scale With LLMs At Google di Ziftci, Celal, Nikolov, Stoyan, Sjövall, Anna, Kim, Bo, Codecasa, Daniele, Kim, Max

Sommario: “... and traditionally manual migration project at Google, propose a novel automated algorithm that uses change location...”
Testo

The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants di Zhang, Yiqun, Li, Hao, Wang, Chenxu, Chen, Linyao, Zhang, Qiaosheng, Ye, Peng, Feng, Shi, Wang, Daling, Wang, Zhen, Wang, Xinrun, Xu, Jia, Bai, Lei, Ouyang, Wanli, Hu, Shuyue

Sommario: “... performance across 15 diverse datasets spanning mathematics, coding, logical reasoning, general knowledge...”
Testo

Robust Preference Optimization via Dynamic Target Margins di Sun, Jie, Wu, Junkang, Wu, Jiancan, Zhu, Zhibo, Lu, Xingyu, Zhou, Jun, Ma, Lintao, Wang, Xiang

Sommario: “..., we propose $γ$-PO, a dynamic target margin preference optimization algorithm that adjust reward...”
Testo

Towards an Oracle for Binary Decomposition Under Compilation Variance di Jia, Ang, Jiang, He, Ren, Zhilei, Li, Xiaochen, Yang, Zhipeng, Duan, Yaxin, Fan, Ming, Liu, Ting

Sommario: “...Third-Party Library (TPL) detection, which identifies reused libraries in binary code, is critical...”
Testo

Consistent Simulation of Fibonacci Anyon Braiding within a Qubit Quasicrystal Inflation Code di Amaral, Marcelo M.

Sommario: “... (QIC). The code is defined by a local Hamiltonian whose ground state manifold enforces Fibonacci tiling...”
Testo

Ludax: A GPU-Accelerated Domain Specific Language for Board Games di Todd, Graham, Padula, Alexander G., Soemers, Dennis J. N. J., Togelius, Julian

Sommario: “...: frameworks that compile domain-specific code into playable and simulatable game environments, allowing...”
Testo

Real-time adaptive quantum error correction by model-free multi-agent learning di Guatto, Manuel, Preti, Francesco, Schilling, Michael, Calarco, Tommaso, Cárdenas-López, Francisco Andrés, Motzoi, Felix

Sommario: “... QEC codes tailored for multi-level quantum architectures. At the second level we introduce BRAVE...”
Testo