Resultados de búsqueda - coding (algorithm OR (Algorithmsssic OR algorithmssssic))

KAT-V1: Kwai-AutoThink Technical Report por Zhan, Zizheng, Deng, Ken, Tang, Huaixi, Xiang, Wen, Wu, Kun, Li, Weihao, Zhu, Wenqiang, Xu, Jingxuan, Huang, Lecheng, Feng, Zongxian, Wang, Shaojie, Yan, Shangpeng, Chen, Xuxing, Liu, Jiaheng, Peng, Zhongyuan, Gao, Zuchen, Huang, Haoyang, Zhang, Xiaojiang, Wang, Jinghui, Lin, Zheng, Li, Mengtong, Wang, Huiming, Zhan, Ziqi, Wu, Yanan, Zhang, Yuanxing, Yang, Jian, Chen, Guang, Zhang, Haotian, Chen, Bin, Yu, Bing

Tabla de Contenidos: “… prompting. Finally, we propose Step-SRPO, a reinforcement learning algorithm that incorporates intermediate…”
Enlace del recurso

R-process heating implementation in hydrodynamic simulations with neural networks por Just, Oliver, Xiong, Zewei, Martínez-Pinedo, Gabriel

Tabla de Contenidos: “… algorithms. The method requires the evolution of only a few additional quantities characterizing…”
Enlace del recurso

CompressedVQA-HDR: Generalized Full-reference and No-reference Quality Assessment Models for Compressed High Dynamic Range Videos por Sun, Wei, Cao, Linhan, Fu, Kang, Zhu, Dandan, Jia, Jun, Hu, Menghan, Min, Xiongkuo, Zhai, Guangtao

Tabla de Contenidos: “… compression algorithms. Although numerous compressed video quality assessment (VQA) methods have been proposed…”
Enlace del recurso

SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation por Ye, Hao, Qi, Mengshi, Liu, Zhaohong, Liu, Liang, Ma, Huadong

Tabla de Contenidos: “… novel multi-scale subgraph retrieval algorithm for efficient information retrieval. By incorporating…”
Enlace del recurso

Power Battery Detection por Zhao, Xiaoqi, Cao, Peiqian, Yu, Chenyang, Feng, Zonglei, Zhang, Lihe, Liu, Hanqi, Zuo, Jiaming, Pang, Youwei, Ouyang, Jinsong, Lin, Weisi, Fakhri, Georges El, Lu, Huchuan, Liu, Xiaofeng

Tabla de Contenidos: “… algorithms struggle with densely packed plates, low contrast, scale variation, and imaging artifacts…”
Enlace del recurso

Adaptive Confidence-Wise Loss for Improved Lens Structure Segmentation in AS-OCT por Xiao, Zunjie, Wu, Xiao, Liu, Tianhang, Hu, Lingxi, Zhang, Yinling, Zhang, Xiaoqing, Higashita, Risa, Liu, Jiang

Tabla de Contenidos: “… threshold optimization algorithm to adjust the confidence threshold of ACW dynamically. Additionally…”
Enlace del recurso

ST-Raptor: LLM-Powered Semi-Structured Table Question Answering por Tang, Zirui, Niu, Boyu, Zhou, Xuanhe, Li, Boxiu, Zhou, Wei, Wang, Jiannan, Li, Guoliang, Zhang, Xinyi, Wu, Fan

Tabla de Contenidos: “… with an effective algorithm for constructing the tree. Second, we define a set of basic tree operations to guide…”
Enlace del recurso

Dual-Thresholded Heatmap-Guided Proposal Clustering and Negative Certainty Supervision with Enhanced Base Network for Weakly Supervised Object Detection por Guo, Yuelin, He, Haoyu, Chen, Zhiyuan, Huang, Zitong, Lu, Renhao, Shi, Lu, Wang, Zejun, Zhang, Weizhe

Tabla de Contenidos: “… selector (HGPS) algorithm, which utilizes dual thresholds on heatmaps to pre-select proposals, enabling…”
Enlace del recurso

Machine Learning for Quantum Noise Reduction por Kendre, Karan

Tabla de Contenidos: “… mitigation essential for practical quantum computation. While traditional quantum error correction codes…”
Enlace del recurso

Language Models that Think, Chat Better por Bhaskar, Adithya, Ye, Xi, Chen, Danqi

Tabla de Contenidos: “… rule-based rewards in verifiable domains such as mathematics and code. However, RLVR leads to limited…”
Enlace del recurso

Active Attacks: Red-teaming LLMs via Adaptive Environments por Yun, Taeyoung, St-Charles, Pierre-Luc, Park, Jinkyoo, Bengio, Yoshua, Kim, Minsu

Tabla de Contenidos: “… exploration, we introduce \textit{Active Attacks}, a novel RL-based red-teaming algorithm that adapts its…”
Enlace del recurso

From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process Supervision por Ma, Jie, Qi, Shihao, Xing, Rui, Yin, Ziang, Wei, Bifan, Liu, Jun, Liu, Tongliang

Tabla de Contenidos: “…, it enhances the path expansion through a Monte Carlo algorithm with a temporally adaptive policy that begins…”
Enlace del recurso

Vision-Zero: Scalable VLM Self-Improvement via Strategic Gamified Self-Play por Wang, Qinsi, Liu, Bo, Zhou, Tianyi, Shi, Jing, Lin, Yueqian, Chen, Yiran, Li, Hai Helen, Wan, Kun, Zhao, Wentian

Tabla de Contenidos: “…-SPO), a novel training algorithm that alternates between Self-Play and reinforcement learning…”
Enlace del recurso

Who Should Have a Place on the Ark? Parameterized Algorithms for the Maximization of Phylogenetic Diversity por Schestag, Jannik

Tabla de Contenidos: “… after which they can no longer be saved.For Time-PD,we present color-coding algorithms that prove…”
Enlace del recurso

FOLK: Fast Open-Vocabulary 3D Instance Segmentation via Label-guided Knowledge Distillation por Wu, Hongrui, Gao, Zhicheng, Cao, Jin, Yao, Kelu, Shen, Wen, Wei, Zhihua

Tabla de Contenidos: “… propose a label-guided distillation algorithm to distill open-vocabulary knowledge from label-consistent 2…”
Enlace del recurso

Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning por Mihai-Cristian, Pîrvu, Leordeanu, Marius

Tabla de Contenidos: “… the distribution of hyper-edges on each forward pass. Additionally, the model adapts the standard MAE algorithm…”
Enlace del recurso

FedAdamW: A Communication-Efficient Optimizer with Convergence and Generalization Guarantees for Federated Large Models por Liu, Junkang, Shang, Fanhua, Liu, Hongying, Tian, Yuxuan, Liu, Yuanyuan, Liu, Jin, Zhu, Kewen, Lin, Zhouchen

Tabla de Contenidos: “… \underline{AdamW} algorithm, called \texttt{FedAdamW}, for training and fine-tuning various large models…”
Enlace del recurso

CORGI: Efficient Pattern Matching With Quadratic Guarantees por Weitekamp, Daniel

Tabla de Contenidos: “… automatically generate rules from example-driven induction or code synthesis, they can easily produce worst-case…”
Enlace del recurso

MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping por Huang, Yushi, Wang, Zining, Yuan, Zhihang, Ding, Yifu, Gong, Ruihao, Guo, Jinyang, Liu, Xianglong, Zhang, Jun

Tabla de Contenidos: “… the optimal thresholds, we introduce a frontier search algorithm that exploits monotonicity properties…”
Enlace del recurso

Solving Spatial Supersensing Without Spatial Supersensing por Udandarao, Vishaal, Karthik, Shyamgopal, Nath, Surabhi S., Hochlehnert, Andreas, Bethge, Matthias, Prabhu, Ameya

Tabla de Contenidos: “… object-count predictions unchanged; instead, Cambrian-S inference algorithm relies largely on a shortcut…”
Enlace del recurso