Risultati della ricerca - coding (algorithm OR (algorithmics OR Algorithmssics))

VL Norm: Rethink Loss Aggregation in RLVR di He, Zhiyuan, Luo, Xufang, Zhang, Yike, Yang, Yuqing, Qiu, Lili

Sommario: “...-of-the-art RL algorithm DAPO, it achieves up to 2.67x faster convergence on the CountDown task. Our code...”
Testo

Quantum Grid Path Planning Using Parallel QAOA Circuits Based on Minimum Energy Principle di Liu, Jun

Sommario: “... energy calculation. A classical algorithm is employed to filter out unreasonable solutions...”
Testo

IntrinTrans: LLM-based Intrinsic Code Translator for RISC-V Vector di Han, Liutong, Tan, Zhiyuan, Zhang, Hongbin, Wang, Pengcheng, Kang, Chu, Xing, Mingjie, Wu, Yanjun

Sommario: “... for optimizing library performance. Many mainstream libraries implement a large number of vectorized algorithms...”
Testo

Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs di Zhao, Yujie, Hu, Lanxiang, Wang, Yang, Hou, Minmin, Zhang, Hao, Ding, Ke, Zhao, Jishen

Sommario: “...-policy models. We propose AT-GRPO, which includes (i) an agent- and turn-wise grouped RL algorithm...”
Testo

Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients di Mansouri, Omar El, Izzati, Fathinah Asma, Seddik, Mohamed El Amine, Lahlou, Salem

Sommario: “.... Empirically, we observe consistent improvements across math and code tasks when applying our noise correction...”
Testo

How Do Proteins Fold? di Bustamante, Carlos, Kaiser, Christian, Lindahl, Erik, Sosa, Robert, Volpe, Giovanni

Sommario: “...How proteins fold remains a central unsolved problem in biology. While the idea of a folding code...”
Testo

Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization di Ding, Yifeng, Le, Hung, Han, Songyang, Ruan, Kangrui, Jin, Zhenghui, Kumar, Varun, Wang, Zijian, Deoras, Anoop

Sommario: “... iteratively reason, generate code, and verify through execution - remains challenging for existing...”
Testo

Barcode and QR Code Object Detection: An Experimental Study on YOLOv8 Models di Pandya, Kushagra, Hathi, Heli, Buch, Het, N, Ravikumar R, Chauhan, Shailendrasinh, Singh, Sushil Kumar

Sommario: “...This research work dives into an in-depth evaluation of the YOLOv8 (You Only Look Once) algorithm...”
Testo

Using Small Language Models to Reverse-Engineer Machine Learning Pipelines Structures di Lacroix, Nicolas, Blay-Fornarino, Mireille, Mosser, Sébastien, Precioso, Frederic

Sommario: “...Background: Extracting the stages that structure Machine Learning (ML) pipelines from source code...”
Testo

Metal Pipe: A Broadly-Applicable Stellar Abundance Pipeline Using Isochronal Parameters di Kolecki, Jared R., Weiss, Lauren M.

Sommario: “... code for determining stellar parameters and abundances, which is designed for use across a wider range...”
Testo

C-AoEI-Aware Cross-Layer Optimization in Satellite IoT Systems: Balancing Data Freshness and Transmission Efficiency di Zhao, Yuhua, Lv, Tiejun, Wang, Ke

Sommario: “... algorithm that jointly optimizes coding and decision thresholds. Extensive simulations demonstrate...”
Testo

Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models di Bai, Jinbin, Li, Yixuan, Zhu, Yuchen, Xin, Yi, Shi, Qingyu, Feng, Aosong, Liu, Xiaohong, Tao, Molei, Xue, Jianru, Li, Xiangtai, Yang, Ming-Hsuan

Sommario: “... scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion...”
Testo

ContextEvolve: Multi-Agent Context Compression for Systems Code Optimization di Su, Hongyuan, Zheng, Yu, Li, Yong

Sommario: “...-critical algorithms for computer systems. Despite plausible codes generated by LLMs, producing solutions...”
Testo

Accelerating the Tesseract Decoder for Quantum Error Correction di Grbic, Dragana, Beni, Laleh Aghababaie, Shutty, Noah

Sommario: “... Most-Likely-Error (MLE) decoder for QEC that employs the A* search algorithm to explore...”
Testo

On Dual Connectivity in 6G Leo Constellations di Machumilane, Achilles, Gotta, Alberto

Sommario: “... duplication, packet switching, and network coding for traffic scheduling in DC. However, if not accurately...”
Testo

Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents di Santoni, Cosmo

Sommario: “... independent parallel sessions. We introduce a three-pass structurally lossless trimming algorithm...”
Testo

Scaling Data Difficulty: Improving Coding Models via Reinforcement Learning on Fresh and Challenging Problems di Li, Zongqian, Lv, Tengchao, Huang, Shaohan, Su, Yixuan, Sun, Qinzheng, Yin, Qiufeng, Xin, Ying, Li, Scarlett, Cui, Lei, Collier, Nigel, Wei, Furu

Sommario: “...Training next-generation code generation models requires high-quality datasets, yet existing...”
Testo

Implementation of QR factorization of tall and very skinny matrices on current GPUs di Thies, Jonas, Röhrig-Zöllner, Melven

Sommario: “... basic algorithms: Methods based on the normal equations (Gram matrix), in particular Cholesky-QR2...”
Testo

On the Carbon Footprint of Economic Research in the Age of Generative AI di Alonso-Robisco, Andres, Esparcia, Carlos, Jareño, Francisco

Sommario: “...Generative artificial intelligence (AI) is increasingly used to write and refactor research code...”
Testo

Inference-Time Code Selection via Symbolic Equivalence Partitioning di Cho, David, Wang, Yifan, Sui, Fanping, Grama, Ananth

Sommario: “...Sampling multiple candidate programs at inference time is an effective way to improve LLM code...”
Testo