Risultati della ricerca - coding (algorithmics OR (algorithmics OR (Algorithms OR (algorithmics OR algorithmics))))

TableMind++: An Uncertainty-Aware Programmatic Agent for Tool-Augmented Table Reasoning di Cheng, Mingyue, Yu, Shuo, Jiang, Chuang, Tao, Xiaoyu, Mao, Qingyang, Ouyang, Jie, Liu, Qi, Chen, Enhong

Sommario: “...) algorithm. While TableMind establishes a solid foundation for programmatic agents, the inherent...”
Testo

Bioalignment: Measuring and Improving LLM Disposition Toward Biological Systems for AI Safety di Northen, Trent R, Wang, Mingxun

Sommario: “..., and algorithms). A sample of 5 frontier and 5 open-weight models were measured using 50 curated Bioalignment...”
Testo

Refinements to the Solar Polar Magnetic Flux: Implications from Inversion Methodologies di Yamashiro, Bryan, Sun, Xudong, Milić, Ivan, Noda, Carlos Quintero, Yabar, Adur Pastor, Centeno, Rebecca, Liu, Jiayi, Gošić, Milan, Yang, Kai

Sommario: “...-Polarimeter, utilizing the Stokes Inversion based on Response functions code. The inversions provide height...”
Testo

An Alternative Trajectory for Generative AI di Belova, Margarita, Kansal, Yuval, Liang, Yihao, Xiao, Jiaxin, Jha, Niraj K.

Sommario: “... depth only in domains like mathematics and coding, where rigorous, pre-existing abstractions provide...”
Testo

ExpressMind: A Multimodal Pretrained Large Language Model for Expressway Operation di Wang, Zihe, Wang, Yihuan, Cui, Haiyang Yu. Zhiyong, Liao, Xiaojian, Wang, Chengcheng, Tian, Yonglin, Tong, Yongxin

Sommario: “...) are increasingly applied in intelligent transportation, advancing traffic models from algorithmic to cognitive...”
Testo

Amanous: Distribution-Switching for Superhuman Piano Density on Disklavier di Bae, Joonhyung

Sommario: “... on a physical Disklavier, demonstrating algorithmic self-consistency and sub-millisecond software...”
Testo

Transparent Fragments Contour Estimation via Visual-Tactile Fusion for Autonomous Reassembly di Lin, Qihao, Chen, Borui, Zhou, Yuping, Wu, Jianing, Guo, Yulan, Zheng, Weishi, Xia, Chongkun

Sommario: “.... Finally, a multi-dimensional similarity metrics based contour matching and reassembly algorithm...”
Testo

New Lower Bounds for C4-Free Subgraphs of the Hypercubes Q6, Q7, and Q8: Constructions, Structure, and Computational Method di Minamoto, Minamo

Sommario: “...-phase simulated annealing algorithm with Aut(Q_n)-based diversification. For Q_6 we provide an ILP-based...”
Testo

AgentOpt v0.1 Technical Report: Client-Side Optimization for LLM-Based Agent di Hua, Wenyue, Karne, Sripad, Xie, Qian, Agrawal, Armaan, Pagonas, Nikos, Kaffes, Kostis, Peng, Tianyi

Sommario: “..., OpenClaw, and coding agents. Existing research has primarily focused on server-side efficiency, proposing...”
Testo

Semantic Feature Multiple Access Empowered Integrated Learning and Communication Networks di Wang, Jiaxiang, Zhao, Zhouxiang, Ding, Yahao, Qin, Zhijin, Yang, Zhaohui, Chen, Mingzhe, Shikh-Bahaei, Mohammad

Sommario: “... alternating optimization algorithm that integrates dual-decomposition-assisted compression ratio allocation...”
Testo

Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration di Chen, Zhipeng, Qian, Tao, Zhao, Wayne Xin, Wen, Ji-Rong

Sommario: “... computational overhead by approximately 37.5\% while remaining compatible with a wide range of RLVR algorithms...”
Testo

Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision di He, Yinghui, Kaur, Simran, Bhaskar, Adithya, Yang, Yongjin, Liu, Jiarui, Ri, Narutatsu, Fowl, Liam, Panigrahi, Abhishek, Chen, Danqi, Arora, Sanjeev

Sommario: “.... On math and code reasoning benchmarks with Qwen3-4B-Instruct and Olmo-3-7B-Instruct, SD-Zero improves...”
Testo

NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains di Peng, Shiyao, Zheng, Qianhe, Hao, Zhuodi, Tang, Zichen, Li, Rongjin, Huang, Qing, Huang, Jiayu, Liu, Jiacheng, Zhu, Yifan, E, Haihong

Sommario: “... an innovative activated search algorithm to obtain a refined candidate space. Then it ensures precise evidence...”
Testo

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL di Wang, Sudong, Huang, Weiquan, Yu, Xiaomin, Yang, Zuhao, Lin, Hehai, Wu, Keming, Xiao, Chaojun, Chen, Chen, Wang, Wenxuan, Zhu, Beier, Zhang, Yunjian, Qin, Chengwei

Sommario: “... multiple RL algorithms (GRPO, DAPO, GSPO) and diverse multimodal benchmarks, improving average accuracy...”
Testo

XMAGNET -- Stir before serving: a Lagrangian perspective on mixing-driven condensation in the intracluster medium di Fournier, M., Grete, P., Brüggen, M., O'Shea, B. W., Voit, G. M., Wibking, B. D., Prasad, D.

Sommario: “... algorithm in the GPU-accelerated code AthenaPK, and run a purely hydrodynamical and a magnetohydrodynamical...”
Testo

Heterogeneous Model Fusion for Privacy-Aware Multi-Camera Surveillance via Synthetic Domain Adaptation di Lu, Peggy Joy, Chen, Wei-Yu, Huang, Yao-Tsung, Tseng, Vincent Shin-Mu

Sommario: “... integration algorithm to resolve label inconsistency and architecture heterogeneity across clients. Extensive...”
Testo

OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents di Chen, Shuang, Feng, Kaituo, Chen, Hangting, Huang, Wenxuan, Dai, Dasen, Shou, Quanxin, Lin, Yunlong, Yue, Xiangyu, Gao, Shenghua, Pang, Tianyu

Sommario: “... knowledge acquisition. Finally, we propose a multi-turn fatal-aware GRPO training algorithm that handles...”
Testo

Jagged AI in Scientific Peer Review: Evidence from POMP Data Analysis di Lee, Jin Wook, Szegda, William, Song, Zhisheng, Ionides, Edward L.

Sommario: “... in implementing complex algorithms, and decisions concerning methodological best practices. We studied 72 POMP...”
Testo

CERTIFY-ED: A Multi-Layer Verification Framework for Exact Diagonalization of Quantum Many-Body Systems di Vehale, Sarang, Goel, Ritu

Sommario: “.... The community typically relies on the implicit trust chain LAPACK $\to$ user code $\to$ result, with at most...”
Testo

Trust the Batch, On- or Off-Policy: Adaptive Policy Optimization for RL Post-Training di Fakoor, Rasool, Aubry, Murdock, Stranges, Nicholas, Smola, Alexander J.

Sommario: “..., which makes the algorithm more sensitive to its configuration and requires retuning whenever the task...”
Testo