Risultati della ricerca - (decoding OR coding) (algorithmsssicics OR (algorithm OR (algorithm OR algorithm)))

Multistability and intermingledness in complex high-dimensional data di Datseris, George, Lohmann, Johannes, Hamilton, Oisín, Haqq-Misra, Jacob

Sommario: “... that analyses potentially multistable simulation data and decides algorithmically what are the alternative...”
Testo

Robust Optimization for Mitigating Reward Hacking with Correlated Proxies di Liu, Zixuan, Sun, Xiaolin, Zheng, Zizhan

Sommario: “... environments show that our algorithms consistently outperform ORPO in worst-case returns, and offer improved...”
Testo

Wave-Based Dispatch for Circuit Cutting in Hybrid HPC--Quantum Systems di García-Raigada, Ricard S., Jorba, Josep, Iserte, Sergio

Sommario: “... layers to parse quantum code, a wave-based coordinator that achieves pipeline concurrency via non...”
Testo

CAR-EnKF: A Covariance-Adaptive and Recalibrated Ensemble Kalman Filter Framework di Jiang, Shida, Tao, Shengyu, Liu, Zihe, Moura, Scott

Sommario: “... online. The framework is algorithmically general and is specialized here to the stochastic EnKF...”
Testo

NLPOpt-Net: A Learning Method for Nonlinear Optimization with Feasibility Guarantees di Roy, Bimol Nath, Golder, Rahul, Hasan, MM Faruque

Sommario: “... the NN predictions further. NLPOpt-Net deploys an inversion-free, modified Chambolle-Pock algorithm...”
Testo

Hitting Time Isomorphism for Multi-Stage Planning with Foundation Policies di Boock, Magnus Victor, Akgül, Abdullah, Çelikok, Mustafa Mert, Kandemir, Melih

Sommario: “... Isomorphic Embedding Learning (IEL) as a new goal-agnostic foundation policy learning algorithm that anchors...”
Testo

WiCER: Wiki-memory Compile, Evaluate, Refine Iterative Knowledge Compilation for LLM Wiki Systems di Huerta, Juan M.

Sommario: “... algorithm inspired by counterexample-guided abstraction refinement (CEGAR) that closes this gap. WiCER...”
Testo

ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning di Chen, Honghua, Xu, Zitong, Duan, Huiyu, Zhang, Xinyun, Min, Xiongkuo, Zhai, Guangtao

Sommario: “... signals derived from RE-Reward and the Group Relative Policy Optimization (GRPO) algorithm to learn...”
Testo

Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback di Lee, Seohyun, Fang, Wenzhi, Han, Dong-Jun, Hosseinalipour, Seyyedali, Brinton, Christopher G.

Sommario: “... Advantage-Weighted Refinement), an efficient online learning algorithm for federated LLM fine-tuning. SPEAR...”
Testo

Learning CLI Agents with Structured Action Credit under Selective Observation di Su, Haoyang, Wen, Ying

Sommario: “.... Beyond this underused action structure, CLI learning also couples two bottlenecks for coding agents...”
Testo

Swarm Skills: A Portable, Self-Evolving Multi-Agent System Specification for Coordination Engineering di Zhang, Xinyu, Dou, Zhicheng, Li, Deyang, Tao, Jianjun, Cheng, Shuo, Shi, Ruifeng, Liu, Fangchao, Hu, Enrui, Ding, Yangkai, Wang, Hongbo, Ye, Qi, Jin, Xuefeng, Zhao, Zhangchun

Sommario: “... framework-internal code or static configurations, preventing them from being shared across systems...”
Testo

A categorical error sensitivity index (ISEC): A preventive ordinal decision-support measure for irrecoverable errors in manual data entry systems di Palma, Ricardo Raúl, Benetti, Mauro Anibal, Varretti, Fabricio Orlando Sanchez

Sommario: “... morphological transformation costs (through an adapted Damerau Levenshtein algorithm), and empirical frequency...”
Testo

High-Rate Quantized Matrix Multiplication II di Ordentlich, Or, Polyanskiy, Yury

Sommario: “... to the problem of weighted mean squared error (WMSE) source coding, whose classical (reverse) waterfilling...”
Testo

Linear-Time T-Gate Optimization via Random Abstraction di Albarghouthi, Aws

Sommario: “... must be encoded redundantly across many physical ones using quantum error-correcting codes. In most...”
Testo

Adaptive Generate-Rank-Verify: Inference-Time Search with Costly Verification di Dughmi, Shaddin, Haghifam, Mahdi, Kalayci, Yusuf Hakan

Sommario: “... verifier, such as exact answer checking in mathematical reasoning or hidden-test execution in code...”
Testo

Weasel: Out-of-Domain Generalization for Web Agents via Importance-Diversity Data Selection di Zadeh, Fatemeh Pesaran, Choi, Seyeon, Lù, Xing Han, Reddy, Siva, Kim, Gunhee

Sommario: “... diversity over states, websites, and interaction patterns, solving efficiently with a greedy algorithm. We...”
Testo

Vector Policy Optimization: Training for Diversity Improves Test-Time Search di Bahlous-Boldi, Ryan, Puri, Isha, Shenfeld, Idan, Kumar, Akarsh, Damani, Mehul, Risi, Sebastian, Khattab, Omar, Hong, Zhang-Wei, Agrawal, Pulkit

Sommario: “... Optimization (VPO), an RL algorithm that explicitly trains policies to anticipate diverse downstream reward...”
Testo

ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention di Sharratt, Joe

Sommario: “...Efficient attention algorithms are critical to mitigate the quadratic cost of attention in long...”
Testo

Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework di Park, Hyunjee, Chung, Hayoung

Sommario: “... for prescribed objectives and constraints through well-established numerical algorithms. Throughout the workflow...”
Testo

Polar: Agentic RL on Any Harness at Scale di Xu, Binfeng, Zhang, Hao, Zhang, Shaokun, Han, Songyang, Liu, Mingjie, Hu, Jian, Diao, Shizhe, Jin, Zhenghui, Zou, Yunheng, Demoret, Michael, Kautz, Jan, Dong, Yi

Sommario: “.... This decoupled design makes Polar agnostic to agent harnesses, training infrastructure, and RL algorithms while...”
Testo