Suchergebnisse - (endedededededededededededededededededededededededeDecoding OR coding) (algorithmics OR algorithm)

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX von Rutherford, Alexander, Ellis, Benjamin, Gallici, Matteo, Cook, Jonathan, Lupu, Andrei, Ingvarsson, Gardar, Willi, Timon, Hammond, Ravi, Khan, Akbir, de Witt, Christian Schroeder, Souly, Alexandra, Bandyopadhyay, Saptarashmi, Samvelyan, Mikayel, Jiang, Minqi, Lange, Robert Tjarko, Whiteson, Shimon, Lacerda, Bruno, Hawes, Nick, Rocktaschel, Tim, Lu, Chris, Foerster, Jakob Nicolaus

Inhaltsangabe: “… Benchmarks are crucial in the development of machine learning algorithms, with available …”
Volltext

Temporal Action Localization for Inertial-based Human Activity Recognition von Bock, Marius, Moeller, Michael, Van Laerhoven, Kristof

Inhaltsangabe: “… As of today, state-of-the-art activity recognition from wearable sensors relies on algorithms being …”
Volltext

Efficient Reinforcement Learning via Decoupling Exploration and Utilization von Yang, Jingpu, Wang, Helin, Zhao, Qirui, Shi, Zhecheng, Song, Zirui, Fang, Miao

Inhaltsangabe: “… as well as limited generalization abilities. This methodology frequently leads to algorithms settling …”
Volltext

Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models von Qin, Zhen, Sun, Weigao, Li, Dong, Shen, Xuyang, Sun, Weixuan, Zhong, Yiran

Inhaltsangabe: “… consumption. However, due to the issue with cumulative summation (cumsum), current linear attention algorithms …”
Volltext

Refined Inverse Rigging: A Balanced Approach to High-fidelity Blendshape Animation von Racković, Stevo, Soares, Cláudia, Jakovetić, Dušan

Inhaltsangabe: “… animation, using high-quality corrective blendshapes. Our algorithm introduces novel enhancements in three …”
Volltext

WideSA: A High Array Utilization Mapping Scheme for Uniform Recurrences on the Versal ACAP Architecture von Dai, Tuo, Shi, Bizhao, Luo, Guojie

Inhaltsangabe: “… systolic array mappings. Concurrently, we have developed a routing-aware PLIO assignment algorithm tailored …”
Volltext

CPR++: Object Localization via Single Coarse Point Supervision von Yu, Xuehui, Chen, Pengfei, Wang, Kuiran, Han, Xumeng, Li, Guorong, Han, Zhenjun, Ye, Qixiang, Jiao, Jianbin

Inhaltsangabe: “… to alleviate semantic variance from an algorithmic perspective. CPR reduces the semantic variance by selecting …”
Volltext

Blending Data-Driven Priors in Dynamic Games von Lidard, Justin, Hu, Haimin, Hancock, Asher, Zhang, Zixu, Contreras, Albert Gimó, Modi, Vikash, DeCastro, Jonathan, Gopinath, Deepak, Rosman, Guy, Leonard, Naomi Ehrich, Santos, María, Fisac, Jaime Fernández

Inhaltsangabe: “… , an algorithm for solving non-cooperative dynamic game with Kullback-Leibler (KL) regularization with respect …”
Volltext

Exploring Time Delay Interferometry Ranging as a Practical Ranging Approach in the Bayesian Framework von Du, Minghui, Wu, Pengzhan, Luo, Ziren, Xu, Peng

Inhaltsangabe: “… ranging mainly relies on the pseudo-random noise (PRN) code signal modulated onto the lasers. To ensure …”
Volltext

Part-aware Prompted Segment Anything Model for Adaptive Segmentation von Zhao, Chenhui, Shen, Liyue

Inhaltsangabe: “… new challenges for segmentation algorithms in adapting to new patients, due to the large variability …”
Volltext

Balanced Substructures in Bicolored Graphs von Ardra, P. S., Krithika, R., Saurabh, Saket, Sharma, Roohani

Inhaltsangabe: “… linear function. We use this result combined with dynamic programming algorithms based on color coding …”
Volltext

HeR-DRL:Heterogeneous Relational Deep Reinforcement Learning for Decentralized Multi-Robot Crowd Navigation von Zhou, Xinyu, Piao, Songhao, Chi, Wenzheng, Chen, Liguo, Li, Wei

Inhaltsangabe: “… " hinders generalizability and restricts progress towards robust navigation algorithms. In this paper, we …”
Volltext

Reconstruction of Poloidal Magnetic Fluxes on EAST based on Neural Networks with Measured Signals von Long, Feifei, Xia, Xiangze, Liu, Jian, Liu, Zixi, Wu, Xiaodong, Wu, Xiaohe, Wan, Chenguang, Gao, Xiang, Li, Guoqiang, Luo, Zhengping, Qian, Jinping, Team, EAST

Inhaltsangabe: “… fluxes. Equilibrium fitting codes, such as EFIT relying on traditional equilibrium algorithms, require …”
Volltext

Forward Learning of Graph Neural Networks von Park, Namyong, Wang, Xing, Simoulin, Antoine, Yang, Shuai, Yang, Grey, Rossi, Ryan, Trivedi, Puja, Ahmed, Nesreen

Inhaltsangabe: “… ) algorithm, which is the de facto standard for training deep neural networks (NNs). However, despite its …”
Volltext

SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget von Wang, Zihao, Cui, Bin, Gan, Shaoduo

Inhaltsangabe: “… to saving the cost of inference. Most of the existing KV-cache compression algorithms attempted to sparsify …”
Volltext

Stability and Generalization in Free Adversarial Training von Cheng, Xiwei, Fu, Kexin, Farnia, Farzan

Inhaltsangabe: “… to the min-max optimization algorithm used in their training. In this work, we analyze the interconnections …”
Volltext

Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs von Wang, Kang, Shen, Zhishu, Lei, Zhen, Zhang, Tiehua

Inhaltsangabe: “… learning algorithm. Within this algorithm, individual agents are deployed at each intersection with a …”
Volltext

Non-iterative Optimization of Trajectory and Radio Resource for Aerial Network von Lyu, Hyeonsu, Jang, Jonggyu, Lee, Harim, Yang, Hyun Jong

Inhaltsangabe: “… -planning algorithms such as the genetic algorithm, tree search, and reinforcement learning. Extensive …”
Volltext

DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ von Belouadi, Jonas, Ponzetto, Simone Paolo, Eger, Steffen

Inhaltsangabe: “… -based inference algorithm that enables DeTikZify to iteratively refine its outputs without the need …”
Volltext

Rewarded Region Replay (R3) for Policy Learning with Discrete Action Space von Li, Bangzheng, Ma, Ningshan, Wang, Zifan

Inhaltsangabe: “… We introduce a new on-policy algorithm called Rewarded Region Replay (R3), which significantly …”
Volltext