Resultados de búsqueda - (endedededecoding OR (coding OR decoding)) (algorithm OR (Algorithmsssic OR Algorithmsssic))

Refine Drugs, Don't Complete Them: Uniform-Source Discrete Flows for Fragment-Based Drug Discovery por Kaech, Benno, Wyss, Luis, Borgwardt, Karsten, Grasso, Gianvito

Tabla de Contenidos: “…. For property and lead optimization, we propose a hybrid scheme that combines a genetic algorithm with a…”
Enlace del recurso

Copy-Paste to Mitigate Large Language Model Hallucinations por Long, Yongchao, Wu, Xian, Zhang, Yingying, Wen, Xianbin, Zhou, Yuxi, Hong, Shenda

Tabla de Contenidos: “…-Parameter Copying Capturing algorithm. Interestingly, this reveals that CopyPasteLLM recalibrates reliance…”
Enlace del recurso

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models por Zhang, Tianao, Li, Zhiteng, Yan, Xianglong, Qin, Haotong, Guo, Yong, Zhang, Yulun

Tabla de Contenidos: “…-order Quantizer (DAQ) that learns ultra-low-bit weight representations via an optimization algorithm…”
Enlace del recurso

Destination-to-Chutes Task Mapping Optimization for Multi-Robot Coordination in Robotic Sorting Systems por Zhang, Yulun, Barbosa, Alexandre O. G., Pecora, Federico, Li, Jiaoyang

Tabla de Contenidos: “… Diversity algorithms to analyze the throughput of a diverse set of task mappings. Our code is available…”
Enlace del recurso

XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation por Bamba, Udbhav, Fang, Minghao, Yu, Yifan, Zheng, Haizhong, Lai, Fan

Tabla de Contenidos: “…Reinforcement learning algorithms such as GRPO have driven recent advances in large language model…”
Enlace del recurso

DeepPrune: Parallel Scaling without Inter-trace Redundancy por Tu, Shangqing, Li, Yaxuan, Bai, Yushi, Hou, Lei, Li, Juanzi

Tabla de Contenidos: “… 0.7072 AUROC on unseen reasoning models. Combined with an online greedy clustering algorithm…”
Enlace del recurso

Improving Reasoning for Diffusion Language Models via Group Diffusion Policy Optimization por Rojas, Kevin, Lin, Jiahe, Rasul, Kashif, Schneider, Anderson, Nevmyvaka, Yuriy, Tao, Molei, Deng, Wei

Tabla de Contenidos: “… new RL algorithm tailored for DLMs. GDPO leverages simple yet effective Semi-deterministic Monte Carlo…”
Enlace del recurso

Non-Orthogonal Pilot Sequence Design for Multi-Cells Interference Networks por Gu, Zhi, Mow, Wai Ho

Tabla de Contenidos: “…-cell systems and the signature sequences in overloaded code-division multiple-access (CDMA) systems…”
Enlace del recurso

REvolution: An Evolutionary Framework for RTL Generation driven by Large Language Models por Min, Kyungjun, Cho, Kyumin, Jang, Junhwan, Kang, Seokhyeong

Tabla de Contenidos: “…Large Language Models (LLMs) are used for Register-Transfer Level (RTL) code generation…”
Enlace del recurso

Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data por Nguyen, Duong M., Hoang, Trong Nghia, Huynh, Thanh Trung, Nguyen, Quoc Viet Hung, Nguyen, Phi Le

Tabla de Contenidos: “… can be algorithmically aggregated across clients with similar data-missing patterns to enhance…”
Enlace del recurso

Towards Personalized Treatment Plan: Geometrical Model-Agnostic Approach to Counterfactual Explanations por Sin, Daniel, Toutounchian, Milad

Tabla de Contenidos: “… algorithm generates decision boundary points on multiple orders of magnitude in the same given time when we…”
Enlace del recurso

Mathematical exploration and discovery at scale por Georgiev, Bogdan, Gómez-Serrano, Javier, Tao, Terence, Wagner, Adam Zsolt

Tabla de Contenidos: “…AlphaEvolve (Novikov et al., 2025) is a generic evolutionary coding agent that combines…”
Enlace del recurso

Pressure2Motion: Hierarchical Human Motion Reconstruction from Ground Pressure with Text Guidance por Li, Zhengxuan, Yang, Qinhui, Zhuang, Yiyu, Guo, Chuan, Zuo, Xinxin, Long, Xiaoxiao, Yao, Yao, Cao, Xun, Shen, Qiu, Zhu, Hao

Tabla de Contenidos: “…We present Pressure2Motion, a novel motion capture algorithm that reconstructs human motion from a…”
Enlace del recurso

A Visual Perception-Based Tunable Framework and Evaluation Benchmark for H.265/HEVC ROI Encryption por Zhang, Xiang, Wu, Geng, Huang, Wenbin, Fu, Daoyong, Peng, Fei, Fu, Zhangjie

Tabla de Contenidos: “… regions in the video, thereby ensuring security while minimizing the impact on coding efficiency. However…”
Enlace del recurso

Language-Guided Graph Representation Learning for Video Summarization por Li, Wenrui, Han, Wei, Man, Hengyu, Zuo, Wangmeng, Fan, Xiaopeng, Tian, Yonghong

Tabla de Contenidos: “… and solve it with the EM algorithm. Experimental results show that our method outperforms existing…”
Enlace del recurso

Reducing Hallucinations in LLM-Generated Code via Semantic Triangulation por Dai, Yihan, Liang, Sijie, Xu, Haotian, Xie, Peichu, Mechtaev, Sergey

Tabla de Contenidos: “…Large language models (LLMs) can generate executable code from natural language descriptions…”
Enlace del recurso

An Active Learning Interatomic Potential For Defect-Engineered CoCrFeMnNi High-Entropy Alloy por Sahoo, Manish, Deshmukh, Akash, Kokane, Yash, M, Jayaprakash H, Ranganathan, Raghavan

Tabla de Contenidos: “… the BFGS unconstrained optimization algorithm for the CoCrFeMnNi High-entropy alloy. Our training set…”
Enlace del recurso

ViSS-R1: Self-Supervised Reinforcement Video Reasoning por Fang, Bo, Song, Yuxin, Wu, Qiangqiang, Sun, Haoyuan, Wu, Wenhao, Chan, Antoni B.

Tabla de Contenidos: “… learning GRPO algorithm (Pretext-GRPO) within the standard R1 pipeline, in which positive rewards…”
Enlace del recurso

Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization por Guo, Jian-Ting, Chen, Yu-Cheng, Hsieh, Ping-Chun, Ho, Kuo-Hao, Huang, Po-Wei, Wu, Ti-Rong, Wu, I-Chen

Tabla de Contenidos: “… RL algorithms, opening a promising direction for learning human-like RL agents. Our code is available…”
Enlace del recurso

SNAP: Low-Latency Test-Time Adaptation with Sparse Updates por Cha, Hyeongheon, Kim, Dong Min, Chung, Hye Won, Gong, Taesik, Lee, Sung-Ju

Tabla de Contenidos: “… domains. Integrated with five state-of-the-art TTA algorithms, SNAP reduces latency by up to 93.12%, while…”
Enlace del recurso