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

TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation por Kim, Junhan, Park, Yeo Jeong, Son, Seungwoo, Lee, Chungman, Kim, Ho-young, Kim, Joonyoung, Jeon, Yongkweon

Tabla de Contenidos: “…. In this paper, we propose TurboBoA, a new backpropagation-free PTQ algorithm that preserves the accuracy…”
Enlace del recurso

ProAct: Agentic Lookahead in Interactive Environments por Yu, Yangbin, Yang, Mingyu, Li, Junyou, Gao, Yiming, Liu, Feiyu, Yang, Yijun, Lin, Zichuan, Lyu, Jiafei, Liu, Yicheng, Lu, Zhicong, Ye, Deheng, Jiang, Jie

Tabla de Contenidos: “… to enhance policy-gradient algorithms like PPO and GRPO. By leveraging lightweight environment rollouts…”
Enlace del recurso

Monte Carlo Maximum Likelihood Reconstruction for Digital Holography with Speckle por Chen, Xi, Maleki, Arian, Jalali, Shirin

Tabla de Contenidos: “… evaluation, the proposed algorithm supports accurate aperture modeling without the simplifying assumptions…”
Enlace del recurso

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining por Zhang, Yifan, Su, Zunhai, Hu, Shuhao, Yang, Rui, Wu, Wei, Qian, Yulei, Xie, Yuchen, Cai, Xunliang

Tabla de Contenidos: “… long-context efficiency through the following hardware-aware algorithm-kernel co-optimization…”
Enlace del recurso

SteuerLLM: Local specialized large language model for German tax law analysis por Wind, Sebastian, Sopa, Jeta, Schmid, Laurin, Jackl, Quirin, Kiefer, Sebastian, Wu, Fei, Mayr, Martin, Köstler, Harald, Wellein, Gerhard, Maier, Andreas, Arasteh, Soroosh Tayebi

Tabla de Contenidos: “…, structured legal argumentation, and numerical accuracy under rigid grading schemes. We algorithmically…”
Enlace del recurso

Gradient-Enhanced Partitioned Gaussian Processes for Real-Time Quadrotor Dynamics Modeling por Sang, Xinhuan, Rozman, Adam, Grace, Sheryl, Tron, Roberto

Tabla de Contenidos: “… effects, such as rotor-rotor interactions and apparent wind direction, we use the CHARM code, which is a…”
Enlace del recurso

Unbiased Gradient Estimation for Event Binning via Functional Backpropagation por Chen, Jinze, Zhai, Wei, Han, Han, Ma, Tiankai, Cao, Yang, Li, Bin, Zha, Zheng-Jun

Tabla de Contenidos: “… algorithms to rely solely on frame-based features. Attempts to directly learn from raw events avoid…”
Enlace del recurso

K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model por Cao, Shiyi, Mao, Ziming, Gonzalez, Joseph E., Stoica, Ion

Tabla de Contenidos: “… approaches typically treat Large Language Models (LLMs) merely as stochastic code generators within heuristic…”
Enlace del recurso

DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation por Yang, Zebin, Qi, Yijiahao, Xie, Tong, Yu, Bo, Liu, Shaoshan, Li, Meng

Tabla de Contenidos: “… to initiate layer-skipping. We also propose a skip-aware two-stage knowledge distillation algorithm…”
Enlace del recurso

Shifting in-DRAM por Tegge, William C., Jones, Alex K.

Tabla de Contenidos: “… algorithms like AES and Reed-Solomon error correction codes. Existing approaches to in-DRAM shifting require…”
Enlace del recurso

Operator Learning Using Weak Supervision from Walk-on-Spheres por Viswanath, Hrishikesh, Nam, Hong Chul, Deng, Xi, Berner, Julius, Anandkumar, Anima, Bera, Aniket

Tabla de Contenidos: “… algorithm to generate cheap, noisy, estimates of the PDE solution during training. This is formulated into a…”
Enlace del recurso

Graph-Based Self-Healing Tool Routing for Cost-Efficient LLM Agents por Bholani, Neeraj

Tabla de Contenidos: “… improves correctness but incurs high latency and inference cost, while pre-coded workflow graphs reduce…”
Enlace del recurso

Fast and Versatile RNA Design via Motif-level Divide-and-Conquer and Structure-level Rival Search por Zhou, Tianshuo, Mathews, David H., Huang, Liang

Tabla de Contenidos: “… both. We introduce a fast and versatile RNA design algorithm inspired by our previous work…”
Enlace del recurso

AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents por Zhu, Wenhui, Chen, Xiwen, Wang, Zhipeng, Wang, Jingjing, Dong, Xuanzhao, Huang, Minzhou, Cai, Rui, Sang, Hejian, Wang, Hao, Qiu, Peijie, Deng, Yueyue, Tiwari, Prayag, Rappazzo, Brendan Hogan, Wang, Yalin

Tabla de Contenidos: “… \emph{algorithmic bridge discovery} to reconstruct missing logical paths between retrieved facts…”
Enlace del recurso

THETA: A Textual Hybrid Embedding-based Topic Analysis Framework and AI Scientist Agent for Scalable Computational Social Science por Duan, Zhenke, Li, Xin

Tabla de Contenidos: “… research, as manual coding remains labor-intensive and conventional topic models often suffer from semantic…”
Enlace del recurso

Agentic Planning with Reasoning for Image Styling via Offline RL por Mukherjee, Subhojyoti, Petrangeli, Stefano, Kveton, Branislav, Bui, Trung, Dernoncourt, Franck, Mukherjee, Arko

Tabla de Contenidos: “… and code are publicly available at the HuggingFace repository. (3) Offline RL training methods for learning…”
Enlace del recurso

Rigorous foundations of adaptive mode tracking in single-parametric Hermitian eigenvalue problems: existence theorems, error indicators, and application to SAFE dispersion analysis por Xiao, Dong, Sharif-Khodaei, Zahra, Aliabadi, M. H.

Tabla de Contenidos: “… wavenumber sampling algorithm that automatically refines the discretization where the MAC separation falls…”
Enlace del recurso

FSMC-Pose: Frequency and Spatial Fusion with Multiscale Self-calibration for Cattle Mounting Pose Estimation por Li, Fangjing, Wang, Zhihai, Ding, Xinxin, Liu, Haiyang, Gao, Ronghua, Wang, Rong, Zhu, Yao, Jin, Ming

Tabla de Contenidos: “…. Specifically, we design two algorithmic components for CattleMountNet: the Spatial Frequency Enhancement Block…”
Enlace del recurso

EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection por Zhu, Chenyang, Wang, Maorong, Liu, Jun, Chang, Ching-Chun, Echizen, Isao

Tabla de Contenidos: “… Reinforcement Learning algorithm using only low-cost binary labels, it eliminates the reliance on fine-grained…”
Enlace del recurso

TENSURE: Fuzzing Sparse Tensor Compilers (Registered Report) por Mahathevan, Kabilan, Zhang, Yining, Gulzar, Muhammad Ali, Sundararajah, Kirshanthan

Tabla de Contenidos: “… that expose corner cases in the code-generation phases of STCs. We propose a novel constraint-based generation…”
Enlace del recurso