Suchergebnisse - (endedededededededededededededededededededededededeDecoding OR coding) (algorithmics OR algorithm)

Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order von Petrov, Egor, Evseev, Grigoriy, Antonov, Aleksey, Veprikov, Andrey, Bushkov, Nikolay, Moiseev, Stanislav, Beznosikov, Aleksandr

Inhaltsangabe: “… ZO momentum-based algorithm that extends ZO SignSGD, requiring the same number of parameters …”
Volltext

BAQ: Efficient Bit Allocation Quantization for Large Language Models von Zhang, Chao, Wang, Li, Lasaulce, Samson, Debbah, Merouane

Inhaltsangabe: “… Quantization) algorithm. The proposed algorithm achieves a good trade-off between loss minimization …”
Volltext

AstroCompress: A benchmark dataset for multi-purpose compression of astronomical data von Truong, Tuan, Sudharsan, Rithwik, Yang, Yibo, Ma, Peter Xiangyuan, Yang, Ruihan, Mandt, Stephan, Bloom, Joshua S.

Inhaltsangabe: “… hand, holds the promise of learning compression algorithms end-to-end from data and outperforming …”
Volltext

SAMSelect: A Spectral Index Search for Marine Debris Visualization using Segment Anything von van Dalen, Joost, Asano, Yuki M., Russwurm, Marc

Inhaltsangabe: “… This work proposes SAMSelect, an algorithm to obtain a salient three-channel visualization …”
Volltext

CIRO7.2: A Material Network with Circularity of -7.2 and Reinforcement-Learning-Controlled Robotic Disassembler von Zocco, Federico, Malvezzi, Monica

Inhaltsangabe: “… on the design of the robotic disassembler compartment using state-of-the-art RL algorithms and assessing …”
Volltext

Bayesian Non-Negative Matrix Factorization with Correlated Mutation Type Probabilities for Mutational Signatures von Lang, Iris, Landy, Jenna, Parmigiani, Giovanni

Inhaltsangabe: “… , giving the algorithm more flexibility. This flexibility for the algorithm to learn the dependence …”
Volltext

Tomography for Plasma Imaging: a Unifying Framework for Bayesian Inference von Hamm, D., Theiler, C., Simeoni, M., Duval, B. P., Debarre, T., Simons, L., Queralt, J. R.

Inhaltsangabe: “… finite, and often limited, number of line-integrated measurements. Decades of algorithmic refinement have …”
Volltext

TurboReg: TurboClique for Robust and Efficient Point Cloud Registration von Yan, Shaocheng, Shi, Pengcheng, Zhao, Zhenjun, Wang, Kaixin, Cao, Kuang, Wu, Ji, Li, Jiayuan

Inhaltsangabe: “… highly parallelizable Pivot-Guided Search (PGS) algorithm. First, we define the TurboClique as a 3-clique …”
Volltext

A Technical Survey of Reinforcement Learning Techniques for Large Language Models von Srivastava, Saksham Sahai, Aggarwal, Vaneet

Inhaltsangabe: “… models, highlighting prominent algorithms such as Proximal Policy Optimization (PPO), Q-Learning …”
Volltext

Interaction between skew-representability, tensor products, extension properties, and rank inequalities von Bérczi, Kristóf, Gehér, Boglárka, Imolay, András, Lovász, László, Padró, Carles, Schwarcz, Tamás

Inhaltsangabe: “… and linear algebra. They play an important role in areas such as coding theory, optimization …”
Volltext

Ensemble Foreground Management for Unsupervised Object Discovery von Wu, Ziling, Moemeni, Armaghan, Caleb-Solly, Praminda

Inhaltsangabe: “… in UOD algorithms. However, the absence of ground truth provides existing UOD methods with two challenges …”
Volltext

TIC-GRPO: Provable and Efficient Optimization for Reinforcement Learning from Human Feedback von Pang, Lei, Luo, Jun, Jin, Ruinan

Inhaltsangabe: “… reinforcement learning algorithm for fine-tuning large language models. GRPO replaces the value function …”
Volltext

Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuning von Tian, Chang, Blaschko, Matthew B., Xing, Mingzhe, Li, Xiuxing, Yue, Yinliang, Moens, Marie-Francine

Inhaltsangabe: “… of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because …”
Volltext

SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication von Zhang, Ruijia, Zhao, Xinyan, Wang, Ruixiang, Chen, Sigen, Zhang, Guibin, Zhang, An, Wang, Kun, Wen, Qingsong

Inhaltsangabe: “… pretrained GNNs or greedy algorithms, but often isolate pre- and post-task optimization, lacking a unified …”
Volltext

CaPGNN: Optimizing Parallel Graph Neural Network Training with Joint Caching and Resource-Aware Graph Partitioning von Song, Xianfeng, Zou, Yi, Shi, Zheng

Inhaltsangabe: “… algorithm that leverages both CPU and GPU memory, integrating lightweight cache update and prefetch …”
Volltext

Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems von Shukla, Manish

Inhaltsangabe: “… metrics such as goal drift and harm reduction but did not provide an algorithmic instantiation …”
Volltext

STORI: A Benchmark and Taxonomy for Stochastic Environments von Barsainyan, Aryan Amit, Lim, Jing Yu, Liu, Dianbo

Inhaltsangabe: “… algorithms can be tuned to succeed. The absence of a well-defined taxonomy of stochasticity further …”
Volltext

$Agent^2$: An Agent-Generates-Agent Framework for Reinforcement Learning Automation von Wei, Yuan, Shan, Xiaohan, Miao, Ran, Li, Jianmin

Inhaltsangabe: “… $ autonomously translates natural language task descriptions and environment code into executable RL solutions …”
Volltext

A Multidimensional Self-Adaptive Numerical Simulation Framework for Semiconductor Boltzmann Transport Equation von Zhang, Zeyu, Zhang, Xiaoyu, Song, Zhigang, Fang, Qing

Inhaltsangabe: “… transformation. On the programming front, a parallelized MATLAB algorithm is developed to optimize code execution …”
Volltext

d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation von Wang, Guanghan, Turok, Gilad, Schiff, Yair, Arriola, Marianne, Kuleshov, Volodymyr

Inhaltsangabe: “… gradient algorithm that relies on accurate estimates of the sampling trajectory likelihoods. Because …”
Volltext