Risultati della ricerca - (endededededededededededecoding OR (coding OR decoding)) (algorithm OR Algorithmssssssics)

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents di Lai, Hanyu, Liu, Xiao, Zhao, Yanxiao, Xu, Han, Zhang, Hanchen, Jing, Bohao, Ren, Yanyu, Yao, Shuntian, Dong, Yuxiao, Tang, Jie

Sommario: “... significant improvements for general agents in desktop automation. Our code and the new OfficeWorld benchmark...”
Testo

Snap-Snap: Taking Two Images to Reconstruct 3D Human Gaussians in Milliseconds di Lu, Jia, Yi, Taoran, Fang, Jiemin, Yang, Chen, Wu, Chuiyun, Shen, Wei, Liu, Wenyu, Tian, Qi, Wang, Xinggang

Sommario: “... algorithm is applied to supplement the missing color information, and then the complete human point clouds...”
Testo

Competition and Attraction Improve Model Fusion di Abrantes, João, Lange, Robert Tjarko, Tang, Yujin

Sommario: “...), an evolutionary algorithm with three key features: (1) dynamic adjustment of merging boundaries to progressively...”
Testo

A Praxis of Influence: Framing the Observation and Measurement of Information Power di Bronk, Chris, Pittman, Jason, Semmler, Carolyn

Sommario: “...), computing (data movement and algorithmic delivery), and psychology (attention, affect, memory, and belief...”
Testo

Designing across domains with declarative thinking: Insights from the 96-Eyes ptychographic imager project di Chan, Antony C

Sommario: “... traceability, and minimizes costly misalignment across optical, algorithmic, hardware-accelerated compute...”
Testo

cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending di Satheesh, Anirudh, Powell, Keenan, Wei, Hua

Sommario: “...Many multi-agent reinforcement learning (MARL) algorithms are trained in fixed simulation...”
Testo

Automatic Pronunciation Error Detection and Correction of the Holy Quran's Learners Using Deep Learning di Abdelfattah, Abdullah, Khalil, Mahmoud I., Abbas, Hazem

Sommario: “... Tasmeea algorithm; (2) 850+ hours of audio (~300K annotated utterances); (3) A novel ASR-based approach...”
Testo

Can Large Language Models Master Complex Card Games? di Wang, Wei, Bie, Fuqing, Chen, Junzhe, Zhang, Dan, Huang, Shiyu, Kharlamov, Evgeny, Tang, Jie

Sommario: “... intelligence algorithms. AlphaGo, AlphaZero, and MuZero have defeated top human players in Go and Chess...”
Testo

SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning di Xue, Zhenghai, Zheng, Longtao, Liu, Qian, Li, Yingru, Zheng, Xiaosen, Ma, Zejun, An, Bo

Sommario: “... this challenge, we introduce SimpleTIR , a plug-and-play algorithm that stabilizes multi-turn TIR training. Its...”
Testo

Sparse Sensor Allocation for Inverse Problems of Detecting Sparse Leaking Emission Sources di Liu, Xinchao, Hwang, Youngdeok, Phan, Dzung, Klein, Levente, Liu, Xiao, Yeo, Kyongmin

Sommario: “... algorithms, including the repeated Sample Average Approximation (rSAA) and the Stochastic Gradient Descent...”
Testo

PySensors 2.0: A Python Package for Sparse Sensor Placement di Karnik, Niharika, Bhangale, Yash, Abdo, Mohammad G., Klishin, Andrei A., Cogliati, Joshua J., Brunton, Bingni W., Kutz, J. Nathan, Brunton, Steven L., Manohar, Krithika

Sommario: “.... To highlight these additions, we provide a brief description of the mathematical algorithms and theory...”
Testo

Agents of Discovery di Diefenbacher, Sascha, Hallin, Anna, Kasieczka, Gregor, Krämer, Michael, Lauscher, Anne, Lukas, Tim

Sommario: “..., these tools are typically special-purpose algorithms that rely, for example, on encoded physics knowledge...”
Testo

PIPES: A Meta-dataset of Machine Learning Pipelines di Maia, Cynthia Moreira, de Amorim, Lucas B. V., Cavalcanti, George D. C., Cruz, Rafael M. O.

Sommario: “... computational costs associated with evaluating various algorithms' performances on a given dataset. To mitigate...”
Testo

SAQ: Pushing the Limits of Vector Quantization through Code Adjustment and Dimension Segmentation di Li, Hui, Deng, Shiyuan, Yan, Xiao, Zhi, Xiangyu, Cheng, James

Sommario: “.... An efficient dynamic programming algorithm is developed to optimize dimension segmentation and bit allocation...”
Testo

Diffusion-Based Cross-Modal Feature Extraction for Multi-Label Classification di Lan, Tian, Zheng, Yiming, Yin, Jianxin

Sommario: “... for images (under DiT-XL/2-256$\times$256). We devise a heuristic local-search algorithm that pinpoints...”
Testo

Graph-based Clustering Revisited: A Relaxation of Kernel $k$-Means Perspective di Lyu, Wenlong, Jia, Yuheng, Liu, Hui, Hou, Junhui

Sommario: “... algorithm for their optimization. Extensive experiments validate the effectiveness of our approaches...”
Testo

FAST: Foreground-aware Diffusion with Accelerated Sampling Trajectory for Segmentation-oriented Anomaly Synthesis di Xu, Xichen, Wang, Yanshu, Wang, Jinbao, Lei, Xiaoning, Xie, Guoyang, Jiang, Guannan, Lu, Zhichao

Sommario: “... sampling algorithm specifically designed for segmentation-oriented industrial anomaly synthesis, which...”
Testo

Learning More with Less: A Dynamic Dual-Level Down-Sampling Framework for Efficient Policy Optimization di Wang, Chao, Yang, Tao, Tian, Hongtao, Shi, Yunsheng, Ma, Qiyao, Liu, Xiaotao, Yao, Ting, Ding, Wenbo

Sommario: “... and Llama3.1 demonstrate that integrating D$^3$S into advanced RL algorithms achieves state-of-the-art...”
Testo

ProxyAttn: Guided Sparse Attention via Representative Heads di Wang, Yixuan, He, Huang, Bao, Siqi, Wu, Hua, Wang, Haifeng, Zhu, Qingfu, Che, Wanxiang

Sommario: “... rates. In this work, we propose ProxyAttn, a training-free sparse attention algorithm that achieves more...”
Testo

Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs di Xian, Jia Jun Cheng, Li, Muchen, Yang, Haotian, Tao, Xin, Wan, Pengfei, Sigal, Leonid, Liao, Renjie

Sommario: “... and compatible with existing preference-based algorithms. We extend both DPO and KTO to our setting, resulting...”
Testo