Search Results - (coding OR decoding) (algorithm OR (Algorithmsssic OR Algorithmsssic))

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

Table of Contents: “… significant improvements for general agents in desktop automation. Our code and the new OfficeWorld benchmark…”
Get full text

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

Table of Contents: “… algorithm is applied to supplement the missing color information, and then the complete human point clouds…”
Get full text

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

Table of Contents: “…), an evolutionary algorithm with three key features: (1) dynamic adjustment of merging boundaries to progressively…”
Get full text

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

Table of Contents: “…), computing (data movement and algorithmic delivery), and psychology (attention, affect, memory, and belief…”
Get full text

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

Table of Contents: “… traceability, and minimizes costly misalignment across optical, algorithmic, hardware-accelerated compute…”
Get full text

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

Table of Contents: “…Many multi-agent reinforcement learning (MARL) algorithms are trained in fixed simulation…”
Get full text

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

Table of Contents: “… Tasmeea algorithm; (2) 850+ hours of audio (~300K annotated utterances); (3) A novel ASR-based approach…”
Get full text

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

Table of Contents: “… intelligence algorithms. AlphaGo, AlphaZero, and MuZero have defeated top human players in Go and Chess…”
Get full text

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

Table of Contents: “… this challenge, we introduce SimpleTIR , a plug-and-play algorithm that stabilizes multi-turn TIR training. Its…”
Get full text

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

Table of Contents: “… algorithms, including the repeated Sample Average Approximation (rSAA) and the Stochastic Gradient Descent…”
Get full text

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

Table of Contents: “…. To highlight these additions, we provide a brief description of the mathematical algorithms and theory…”
Get full text

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

Table of Contents: “…, these tools are typically special-purpose algorithms that rely, for example, on encoded physics knowledge…”
Get full text

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

Table of Contents: “… computational costs associated with evaluating various algorithms' performances on a given dataset. To mitigate…”
Get full text

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

Table of Contents: “…. An efficient dynamic programming algorithm is developed to optimize dimension segmentation and bit allocation…”
Get full text

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

Table of Contents: “… for images (under DiT-XL/2-256$\times$256). We devise a heuristic local-search algorithm that pinpoints…”
Get full text

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

Table of Contents: “… algorithm for their optimization. Extensive experiments validate the effectiveness of our approaches…”
Get full text

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

Table of Contents: “… sampling algorithm specifically designed for segmentation-oriented industrial anomaly synthesis, which…”
Get full text

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

Table of Contents: “… and Llama3.1 demonstrate that integrating D$^3$S into advanced RL algorithms achieves state-of-the-art…”
Get full text

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

Table of Contents: “… rates. In this work, we propose ProxyAttn, a training-free sparse attention algorithm that achieves more…”
Get full text

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

Table of Contents: “… and compatible with existing preference-based algorithms. We extend both DPO and KTO to our setting, resulting…”
Get full text