Risultati della ricerca - coding (algorithmics OR (algorithm OR algorithm))

De novo Drug Design using Reinforcement Learning with Multiple GPT Agents di Hu, Xiuyuan, Liu, Guoqing, Zhao, Yang, Zhang, Hao

Sommario: “..., we propose MolRL-MGPT, a reinforcement learning algorithm with multiple GPT agents for drug molecular...”
Testo

To the Max: Reinventing Reward in Reinforcement Learning di Veviurko, Grigorii, Böhmer, Wendelin, de Weerdt, Mathijs

Sommario: “... environments and can be easily combined with state-of-the-art RL algorithms. In the experiments, we study...”
Testo

EFUF: Efficient Fine-grained Unlearning Framework for Mitigating Hallucinations in Multimodal Large Language Models di Xing, Shangyu, Zhao, Fei, Wu, Zhen, An, Tuo, Chen, Weihao, Li, Chunhui, Zhang, Jianbing, Dai, Xinyu

Sommario: “... paired responses with and without hallucinations, and then employ various alignment algorithms to improve...”
Testo

Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent di Li, Yingru, Xu, Jiawei, Han, Lei, Luo, Zhi-Quan

Sommario: “...We propose HyperAgent, a reinforcement learning (RL) algorithm based on the hypermodel framework...”
Testo

Autonomous Mapless Navigation on Uneven Terrains di Jardali, Hassan, Ali, Mahmoud, Liu, Lantao

Sommario: “...-aware subgoal that leads the robot to its final destination. The algorithm is designed to run in real...”
Testo

Blur2Blur: Blur Conversion for Unsupervised Image Deblurring on Unknown Domains di Pham, Bang-Dang, Tran, Phong, Tran, Anh, Pham, Cuong, Nguyen, Rang, Hoai, Minh

Sommario: “...This paper presents an innovative framework designed to train an image deblurring algorithm...”
Testo

Hybrid Tree Tensor Networks for quantum simulation di Schuhmacher, Julian, Ballarin, Marco, Baiardi, Alberto, Magnifico, Giuseppe, Tacchino, Francesco, Montangero, Simone, Tavernelli, Ivano

Sommario: “..., their practical usefulness and many operational aspects of hTN-based algorithms, like the optimization of hTNs...”
Testo

Structured Click Control in Transformer-based Interactive Segmentation di Xu, Long, Chen, Yongquan, Huang, Rui, Wu, Feng, Lai, Shiwu

Sommario: “.... However, it's hard for existing algorithms to obtain precise and robust responses after multiple clicks...”
Testo

Integration of Scanning Probe Microscope with High-Performance Computing: fixed-policy and reward-driven workflows implementation di Liu, Yu, Pratiush, Utkarsh, Bemis, Jason, Proksch, Roger, Emery, Reece, Rack, Philip D., Liu, Yu-Chen, Yang, Jan-Chi, Udovenko, Stanislav, Trolier-McKinstry, Susan, Kalinin, Sergei V.

Sommario: “...The rapid development of computation power and machine learning algorithms has paved the way...”
Testo

A Fair Post-Processing Method based on the MADD Metric for Predictive Student Models di Verger, Mélina, Fan, Chunyang, Lallé, Sébastien, Bouchet, François, Luengo, Vanda

Sommario: “... sufficiently accurate and fair in their predictions. To evaluate algorithmic fairness, a new metric has been...”
Testo

Dynamic Label Injection for Imbalanced Industrial Defect Segmentation di Caruso, Emanuele, Pelosin, Francesco, Simoni, Alessandro, Boschetti, Marco

Sommario: “... Injection (DLI) algorithm to impose a uniform distribution in the input batch. Our algorithm computes...”
Testo

End-to-End and Highly-Efficient Differentiable Simulation for Robotics di Lidec, Quentin Le, Montaut, Louis, de Mont-Marin, Yann, Schramm, Fabian, Carpentier, Justin

Sommario: “... of reinforcement learning and trajectory optimization algorithms, especially for problems involving physical...”
Testo

RPC: A Modular Framework for Robot Planning, Control, and Deployment di Bang, Seung Hyeon, Gonzalez, Carlos, Moore, Gabriel, Kang, Dong Ho, Seo, Mingyo, Sentis, Luis

Sommario: “...-friendly operator interface. RPC enables users to thoroughly evaluate and develop control algorithms...”
Testo

PuzzleBoard: A New Camera Calibration Pattern with Position Encoding di Stelldinger, Peer, Schönherr, Nils, Biermann, Justus

Sommario: “... position coding that can be decoded at very low resolutions. The decoding algorithm includes error...”
Testo

Automatic Authoring of Physical and Perceptual/Affective Motion Effects for Virtual Reality di Lee, Jiwan, Choi, Seungmoon

Sommario: “... solely by manual authoring or coding, and this costly process prevents the faster and wider dissemination...”
Testo

Improving User Experience in Preference-Based Optimization of Reward Functions for Assistive Robots di Dennler, Nathaniel, Shi, Zhonghao, Nikolaidis, Stefanos, Matarić, Maja

Sommario: “... interactions. In this work, we design an algorithm to generate trajectories for users to rank that we call...”
Testo

Scaling Inter-procedural Dataflow Analysis on the Cloud di Sun, Zewen, Zhang, Yujin, Xu, Duanchen, Zhang, Yiyu, Qi, Yun, Wang, Yueyang, Li, Yi, Wang, Zhaokang, Li, Yue, Li, Xuandong, Zuo, Zhiqiang, Lu, Qingda, Peng, Wenwen, Guo, Shengjian

Sommario: “... dedicated distributed worklist algorithms for both whole-program analysis and incremental analysis. We...”
Testo

Training Deep Learning Models with Norm-Constrained LMOs di Pethick, Thomas, Xie, Wanyun, Antonakopoulos, Kimon, Zhu, Zhenyu, Silveti-Falls, Antonio, Cevher, Volkan

Sommario: “... a norm-ball. We propose a new stochastic family of algorithms that uses the LMO to adapt...”
Testo

Fault-Resilience of Dissipative Processes for Quantum Computing di Purcell, James, Rajput, Abhishek, Cubitt, Toby

Sommario: “... concerning the error-resilience capabilities of two types of dissipative algorithms: dissipative ground state...”
Testo

SLOs-Serve: Optimized Serving of Multi-SLO LLMs di Chen, Siyuan, Jia, Zhipeng, Khan, Samira, Krishnamurthy, Arvind, Gibbons, Phillip B.

Sommario: “... uses a multi-SLO dynamic programming-based algorithm to continuously optimize token allocations under...”
Testo