Suchergebnisse - (decoding OR coding) (Algorithmsssicics OR (algorithm OR (algorithm OR algorithm)))

Efficient Cloud-edge Collaborative Approaches to SPARQL Queries over Large RDF graphs von Ma, Shidan, Peng, Peng, Zhou, Xu, Özsu, M. Tamer, Zou, Lei, Chen, Guo

Inhaltsangabe: “… Nonlinear Programming (MINLP) problem and solve this problem using a modified branch-and-bound algorithm …”
Volltext

MoCo: A One-Stop Shop for Model Collaboration Research von Feng, Shangbin, Bai, Yuyang, Yang, Ziyuan, Wang, Yike, Tan, Zhaoxuan, Yan, Jiajie, Lei, Zhenyu, Ding, Wenxuan, Shi, Weijia, Wang, Haojin, Qi, Zhenting, Jiang, Yuru, Wang, Heng, Huang, Chengsong, Fei, Yu, Yao, Jihan, Du, Yilun, Zettlemoyer, Luke, Choi, Yejin, Tsvetkov, Yulia

Inhaltsangabe: “… , and comparing model collaboration algorithms at scale. MoCo features 26 model collaboration methods, spanning …”
Volltext

KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices von Zhou, Wuyang, Gu, Yuxuan, Iacovides, Giorgos, Mandic, Danilo

Inhaltsangabe: “… : 1) its iterative Sinkhorn-Knopp (SK) algorithm does not always yield exactly doubly stochastic …”
Volltext

Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification von Du, Siyi, Luo, Xinzhe, O'Regan, Declan P., Qin, Chen

Inhaltsangabe: “… beyond the conventional discard-or-impute paradigm. Central to DyMo is a novel selection algorithm …”
Volltext

Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning von Mahankali, Arvind, Wen, Kaiyue, Ma, Tengyu

Inhaltsangabe: “… the accuracy significantly, we design a multi-stage RL algorithm, with various data filtering strategies …”
Volltext

Benchmarking covariate-adjustment strategies for randomized clinical trials von Shao, Yulin, Lyu, Liangbo, Yu, Menggang, Wang, Bingkai

Inhaltsangabe: “… outcomes. However, machine-learning algorithms implemented with default hyperparameter settings do …”
Volltext

Predicting and improving test-time scaling laws via reward tail-guided search von Li, Muheng, Qian, Jian, Mou, Wenlong

Inhaltsangabe: “… test-time algorithm that dynamically allocates compute to identify and exploit intermediate states …”
Volltext

ROSA-Tuning: Enhancing Long-Context Modeling via Suffix Matching von Zheng, Yunao, Wang, Xiaojie, Ren, Lei, Chen, Wei

Inhaltsangabe: “… -to-end training, we employ the binary discretization strategy and the counterfactual gradient algorithm …”
Volltext

PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning von Lu, Wenquan, Huang, Hai, Liu, Enqi, Balestriero, Randall

Inhaltsangabe: “… Reinforcement learning algorithms such as group-relative policy optimization (GRPO) have shown …”
Volltext

Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic Dynamics von Zhong, Ruizhe, Lian, Jiesong, Mi, Xiaoyue, Zhou, Zixiang, Zhou, Yuan, Lu, Qinglin, Yan, Junchi

Inhaltsangabe: “… this framework with a Dual-Reward Group Relative Policy Optimization algorithm, combining latent process rewards …”
Volltext

rePIRL: Learn PRM with Inverse RL for LLM Reasoning von Wu, Xian, Zhu, Kaijie, Zhang, Ying, Wang, Lun, Guo, Wenbo

Inhaltsangabe: “… process that updates the policy and the PRM interchangeably. Our learning algorithm has customized …”
Volltext

Interpretable Dynamic Network Modeling of Tensor Time Series via Kronecker Time-Varying Graphical Lasso von Higashiguchi, Shingo, Kawabata, Koki, Matsubara, Yasuko, Sakurai, Yasushi

Inhaltsangabe: “… . In addition, our method can be extended to stream algorithms, making the computational time independent …”
Volltext

AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization von Zhang, Shaoqiu, Ding, Zizhong, Yang, Kaicheng, Wu, Junyi, Yan, Xianglong, Li, Xi, Duan, Bingnan, Fang, Jianping, Zhang, Yulun

Inhaltsangabe: “… the quantization policy search as a constrained pathfinding problem. We utilize a beam search algorithm guided …”
Volltext

A Collaborative Safety Shield for Safe and Efficient CAV Lane Changes in Congested On-Ramp Merging von Hegde, Bharathkumar, Bouroche, Melanie

Inhaltsangabe: “… through interaction topologies constructed as a graph using a simple algorithm. Further, a state …”
Volltext

IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs von Tan, Yifan, Sun, Yifu, Huang, Shirui, Liu, Hong, Yu, Guanghua, Zhu, Jianchen, Deng, Yangdong

Inhaltsangabe: “… (\textbf{IDPruner}), which leverages the Maximal Marginal Relevance (MMR) algorithm to achieve a Pareto …”
Volltext

REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents von Chu, Zheng, Wang, Xiao, Hong, Jack, Fan, Huiming, Huang, Yuqi, Yang, Yue, Xu, Guohai, Zhao, Chenxiao, Xiang, Cheng, Hu, Shengchao, Kuang, Dongdong, Liu, Ming, Qin, Bing, Yu, Xing

Inhaltsangabe: “… algorithmic iteration for reinforcement learning experiments. Across both textonly and multimodal searchagent …”
Volltext

HieraMAS: Optimizing Intra-Node LLM Mixtures and Inter-Node Topology for Multi-Agent Systems von Yao, Tianjun, Li, Zhaoyi, Shen, Zhiqiang

Inhaltsangabe: “… this, we use a two-stage algorithm: (1) multi-level reward attribution, which provides fine-grained …”
Volltext

FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning von Devkota, Alina, Thrasher, Jacob, Adjeroh, Donald, Bhattarai, Binod, Gyawali, Prashnna K.

Inhaltsangabe: “… algorithms, often further improving their results. Our code is available at https://github.com/alinadevkota …”
Volltext

Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement von Zhu, Shuchen, Hu, Rizhen, Wang, Mingze, Sun, Mou, Wang, Xue, Yuan, Kun, Wen, Zaiwen

Inhaltsangabe: “… that elucidates how common adaptive algorithms operate synergistically: the preconditioner induces a Riemannian …”
Volltext

EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation Detection von Tang, Wenxin, Xiao, Jingyu, Gong, Yanpei, Ran, Fengyuan, Xia, Tongchuan, Liu, Junliang, Lam, Man Ho, Wang, Wenxuan, Lyu, Michael R.

Inhaltsangabe: “… color-gradient-based algorithm that reliably detects content overflow and spatial sparsity without …”
Volltext