Resultados de búsqueda - coding ((algorithmssicsics OR (algorithm OR algorithm)) OR (algorithm OR algorithm))

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

Spira: Exploiting Voxel Data Structural Properties for Efficient Sparse Convolution in Point Cloud Networks por Adamopoulos, Dionysios, Poulopoulou, Anastasia, Goumas, Georgios, Giannoula, Christina

Tabla de Contenidos: “… for GPUs. Spira proposes (i) a high-performance one-shot search algorithm that builds the kernel map…”
Enlace del recurso

MICCAI STS 2024 Challenge: Semi-Supervised Instance-Level Tooth Segmentation in Panoramic X-ray and CBCT Images por Wang, Yaqi, Li, Zhi, Wu, Chengyu, Liu, Jun, Zhang, Yifan, Ni, Jiaxue, Luo, Qian, Chen, Jialuo, Zhang, Hongyuan, Liu, Jin, Han, Can, Fu, Kaiwen, Ji, Changkai, Cai, Xinxu, Hao, Jing, Zheng, Zhihao, Xu, Shi, Chen, Junqiang, Zhang, Qianni, Qian, Dahong, Wang, Shuai, Zhou, Huiyu

Tabla de Contenidos: “…) registered teams. To ensure algorithmic excellence and full transparency, we rigorously evaluated the valid…”
Enlace del recurso

Semantic Soft Bootstrapping: Long Context Reasoning in LLMs without Reinforcement Learning por Mitra, Purbesh, Ulukus, Sennur

Tabla de Contenidos: “… optimization (GRPO), which is a commonly used RLVR algorithm. Our code is available at https://github.com…”
Enlace del recurso

How Far are Modern Trackers from UAV-Anti-UAV? A Million-Scale Benchmark and New Baseline por Zhang, Chunhui, Liu, Li, Zhang, Zhipeng, Wang, Yong, Wen, Hao, Zhou, Xi, Ge, Shiming, Wang, Yanfeng

Tabla de Contenidos: “… of 50 modern deep tracking algorithms demonstrates that there is still significant room for improvement…”
Enlace del recurso

TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning por Yang, Shenzhi, Zhu, Guangcheng, Zheng, Xing, MA, Yingfan, Chen, Zhongqi, Song, Bowen, Wang, Weiqiang, Zhao, Junbo, Chen, Gang, Wang, Haobo

Tabla de Contenidos: “… an effective policy optimization algorithm, TraPO, that identifies reliable unlabeled samples by matching…”
Enlace del recurso

HERO-Sign: Hierarchical Tuning and Efficient Compiler-Time GPU Optimizations for SPHINCS+ Signature Generation por Zhou, Yaoyun, Wang, Qian

Tabla de Contenidos: “… algorithm that adapts fusion schemes to different GPU architectures. To further improve performance, HERO…”
Enlace del recurso

SP-Rank: A Dataset for Ranked Preferences with Secondary Information por Hosseini, Hadi, Mandal, Debmalya, Puhan, Amrit

Tabla de Contenidos: “… algorithms that leverage both first-order preferences and second-order predictions in ranking tasks. Each…”
Enlace del recurso

TowerMind: A Tower Defence Game Learning Environment and Benchmark for LLM as Agents por Wang, Dawei, Zhou, Chengming, Zhao, Di, Liu, Xinyuan, Ma, Marci Chi, Ushaw, Gary, Davison, Richard

Tabla de Contenidos: “… evaluate two classic reinforcement learning algorithms: Ape-X DQN and PPO. By offering a lightweight…”
Enlace del recurso

Streaming Operator Inference for Model Reduction of Large-Scale Dynamical Systems por Koike, Tomoki, Mohan, Prakash, de Frahan, Marc T. Henry, Bessac, Julie, Qian, Elizabeth

Tabla de Contenidos: “… access to the underlying code or full model operators, i.e., non-intrusively. Traditional OpInf operates…”
Enlace del recurso

FlexLLM: Composable HLS Library for Flexible Hybrid LLM Accelerator Design por Zhang, Jiahao, He, Zifan, Fraser, Nicholas, Blott, Michaela, Sun, Yizhou, Cong, Jason

Tabla de Contenidos: “… lines of code. The system includes: (1) a stage-customized accelerator with hardware-efficient…”
Enlace del recurso

Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning por Kim, Moo Jin, Gao, Yihuai, Lin, Tsung-Yi, Lin, Yen-Chen, Ge, Yunhao, Lam, Grace, Liang, Percy, Song, Shuran, Liu, Ming-Yu, Finn, Chelsea, Gu, Jinwei

Tabla de Contenidos: “…'s pretrained priors and core learning algorithm to capture complex action distributions. Additionally, Cosmos…”
Enlace del recurso

EdgeMask-DG*: Learning Domain-Invariant Graph Structures via Adversarial Edge Masking por Bhattacharya, Rishabh, Manwani, Naresh

Tabla de Contenidos: “… algorithm where an edge masker learns to find worst-case continuous masks subject to a sparsity constraint…”
Enlace del recurso

Mapping plasma properties of Cassiopeia A with XRISM/Resolve: a Bayesian analysis via UltraSPEX por Agarwal, Manan, Vink, Jacco, Gu, Liyi, Plucinsky, Paul P., Bamba, Aya, Sato, Toshiki, Rogantini, Daniele, Ohshiro, Yuken

Tabla de Contenidos: “… Bayesian framework that couples the SPEX plasma code with the UltraNest nested-sampling algorithm, yielding…”
Enlace del recurso

MonoLoss: A Training Objective for Interpretable Monosemantic Representations por Nasiri-Sarvi, Ali, Nguyen, Anh Tien, Rivaz, Hassan, Samaras, Dimitris, Hosseini, Mahdi S.

Tabla de Contenidos: “… training and evaluation. We study a recent MonoScore metric and derive a single-pass algorithm…”
Enlace del recurso

Unmasking Algorithmic Bias in Predictive Policing: A GAN-Based Simulation Framework with Multi-City Temporal Analysis por Barman, Pronob Kumar, Barman, Pronoy Kumar

Tabla de Contenidos: “…Predictive policing systems that direct patrol resources based on algorithmically generated crime…”
Enlace del recurso