Résultats de la recherche - (coding OR decoding) ((Algorithmssicsics OR algorithm) OR (algorithm OR (algorithm OR algorithm)))

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

Table des matières: “… Diversity algorithms to analyze the throughput of a diverse set of task mappings. Our code is available…”
Accéder au texte intégral

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

Table des matières: “…Reinforcement learning algorithms such as GRPO have driven recent advances in large language model…”
Accéder au texte intégral

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

Table des matières: “… 0.7072 AUROC on unseen reasoning models. Combined with an online greedy clustering algorithm…”
Accéder au texte intégral

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

Table des matières: “… new RL algorithm tailored for DLMs. GDPO leverages simple yet effective Semi-deterministic Monte Carlo…”
Accéder au texte intégral

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

Table des matières: “…-cell systems and the signature sequences in overloaded code-division multiple-access (CDMA) systems…”
Accéder au texte intégral

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

Table des matières: “…Large Language Models (LLMs) are used for Register-Transfer Level (RTL) code generation…”
Accéder au texte intégral

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

Table des matières: “… can be algorithmically aggregated across clients with similar data-missing patterns to enhance…”
Accéder au texte intégral

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

Table des matières: “… algorithm generates decision boundary points on multiple orders of magnitude in the same given time when we…”
Accéder au texte intégral

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

Table des matières: “…AlphaEvolve (Novikov et al., 2025) is a generic evolutionary coding agent that combines…”
Accéder au texte intégral

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

Table des matières: “…We present Pressure2Motion, a novel motion capture algorithm that reconstructs human motion from a…”
Accéder au texte intégral

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

Table des matières: “… regions in the video, thereby ensuring security while minimizing the impact on coding efficiency. However…”
Accéder au texte intégral

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

Table des matières: “… and solve it with the EM algorithm. Experimental results show that our method outperforms existing…”
Accéder au texte intégral

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

Table des matières: “…Large language models (LLMs) can generate executable code from natural language descriptions…”
Accéder au texte intégral

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

Table des matières: “… the BFGS unconstrained optimization algorithm for the CoCrFeMnNi High-entropy alloy. Our training set…”
Accéder au texte intégral

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

Table des matières: “… learning GRPO algorithm (Pretext-GRPO) within the standard R1 pipeline, in which positive rewards…”
Accéder au texte intégral

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

Table des matières: “… RL algorithms, opening a promising direction for learning human-like RL agents. Our code is available…”
Accéder au texte intégral

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

Table des matières: “… domains. Integrated with five state-of-the-art TTA algorithms, SNAP reduces latency by up to 93.12%, while…”
Accéder au texte intégral

TPG-INR: Target Prior-Guided Implicit 3D CT Reconstruction for Enhanced Sparse-view Imaging par Cao, Qinglei, Tang, Ziyao, Tang, Xiaoqin

Table des matières: “…. Additionally, we introduce a CUDA-based algorithm for rapid estimation of high-quality 3D target priors from…”
Accéder au texte intégral

Learning Robust Social Strategies with Large Language Models par Piche, Dereck, Muqeeth, Mohammed, Aghajohari, Milad, Duque, Juan, Noukhovitch, Michael, Courville, Aaron

Table des matières: “… algorithm, Advantage Alignment, to fine-tune LLMs toward multi-agent cooperation and non-exploitability. We…”
Accéder au texte intégral

Primal: A Unified Deterministic Framework for Quasi-Orthogonal Hashing and Manifold Learning par Khasia, Vladimer

Table des matières: “… formalize two distinct algorithmic variants: (1) StaticPrime, a sequence generation method that produces…”
Accéder au texte intégral