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

Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback di Ivison, Hamish, Wang, Yizhong, Liu, Jiacheng, Wu, Zeqiu, Pyatkin, Valentina, Lambert, Nathan, Smith, Noah A., Choi, Yejin, Hajishirzi, Hannaneh

Sommario: “...-based learning is applied varies wildly, with differing data, learning algorithms, and evaluations used...”
Testo

Decouple then Converge: Handling Unknown Unlabeled Distributions in Long-Tailed Semi-Supervised Learning di Gan, Kai, Wei, Tong, Zhang, Min-Ling

Sommario: “...-world classification tasks, existing LTSSL algorithms typically assume that labeled and unlabeled data...”
Testo

Residual-MPPI: Online Policy Customization for Continuous Control di Wang, Pengcheng, Li, Chenran, Weaver, Catherine, Kawamoto, Kenta, Tomizuka, Masayoshi, Tang, Chen, Zhan, Wei

Sommario: “... and access to the original training metrics and parameters. In contrast, an online planning algorithm...”
Testo

SOAP-RL: Sequential Option Advantage Propagation for Reinforcement Learning in POMDP Environments di Ishida, Shu, Henriques, João F.

Sommario: “...This work compares ways of extending Reinforcement Learning algorithms to Partially Observed Markov...”
Testo

Accelerating Spectral Clustering on Quantum and Analog Platforms di Xu, Xingzi, Sahai, Tuhin

Sommario: “...We introduce a novel hybrid quantum-analog algorithm to perform graph clustering that exploits...”
Testo

Behavior Pattern Mining-based Multi-Behavior Recommendation di Li, Haojie, Cheng, Zhiyong, Yu, Xu, Liu, Jinhuan, Liu, Guanfeng, Du, Junwei

Sommario: “... algorithms, showing an average improvement of 268.29% in Recall@10 and 248.02% in NDCG@10 metrics. The code...”
Testo

Simultaneous Sensing Data Acquisition and Sharing in Low-Altitude Wireless Networks: Fundamental Limits and Optimal Signaling di Dong, Fuwang, Liu, Fan, Xiong, Yifeng, Cui, Yuanhao, Wang, Wei, Jin, Shi

Sommario: “... for the SDAS systems. The proposed MSST elucidates the relationship between achievable distortion, coding rate...”
Testo

FedModule: A Modular Federated Learning Framework di Chen, Chuyi, Zhang, Zhe, Zhao, Yanchao

Sommario: “... benchmarks for complex experimental scenarios. FedModule adheres to the "one code, all scenarios" principle...”
Testo

Tracking Everything in Robotic-Assisted Surgery di Zhan, Bohan, Zhao, Wang, Fang, Yi, Du, Bo, Vasconcelos, Francisco, Stoyanov, Danail, Elson, Daniel S., Huang, Baoru

Sommario: “... (TAP) algorithm was proposed to overcome these limitations and achieve dense accurate long-term...”
Testo

CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset di Wang, Xiao, Wang, Fuling, Li, Yuehang, Ma, Qingchuan, Wang, Shiao, Jiang, Bo, Li, Chuanfu, Tang, Jin

Sommario: “..., the recently released CheXpert Plus dataset lacks comparative evaluation algorithms and their results...”
Testo

Estimating Exoplanet Mass using Machine Learning on Incomplete Datasets di Lalande, Florian, Tasker, Elizabeth, Doya, Kenji

Sommario: “... machine learning algorithms that can utilize multidimensional incomplete datasets to estimate missing...”
Testo

MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging di Pan, Zhenghao, Zeng, Haijin, Cao, Jiezhang, Chen, Yongyong, Zhang, Kai, Xu, Yong

Sommario: “... algorithms are designed based on the traditional Bayer pattern. When applied to videos captured by quad-Bayer...”
Testo

EEG-DIF: Early Warning of Epileptic Seizures through Generative Diffusion Model-based Multi-channel EEG Signals Forecasting di Jiang, Zekun, Dai, Wei, Wei, Qu, Qin, Ziyuan, Li, Kang, Zhang, Le

Sommario: “... such as epilepsy. Currently, various EEG diagnostic algorithms based on deep learning have been developed. However...”
Testo

CovFUZZ: Coverage-based fuzzer for 4G&5G protocols di Siroš, Ilja, Singelée, Dave, Preneel, Bart

Sommario: “... layers except the physical layer. To guide the fuzzing process, we introduce a novel algorithm...”
Testo

GS2Pose: Two-stage 6D Object Pose Estimation Guided by Gaussian Splatting di Mei, Jilan, Li, Junbo, Meng, Cai

Sommario: “... with similar algorithms, yielding highly competitive results. The code for GS2Pose will soon be released...”
Testo

BASSET: Bandpass-Adaptive Single-pulse SEarch Toolkit -- Optimized Sub-Band Pulse Search Strategies for Faint Narrow-Band FRBs di Cao, J. -H., Wang, P., Li, D., Pan, Q. -H., Mao, K., Niu, C. -H., Zhang, Y. -K., Qu, Q. -Y., Lu, W. -J., Zhang, J. -S., Zhu, Y. -H., Wang, Y. -D., Chen, H. -X., Chen, X. -L., Gügercinoğlu, E., Fang, J. -H., Feng, Y., Gao, H., Huang, Y. -F., Li, J., Miao, C. -C., Tsai, C. -W., Yao, J. -M., You, S. -P., Zhao, R. -S., Liu, Q. -Z., Weng, S. -M., Yew, S. -H., Zhang, J., Zhang, L., Zhou, D. -K., Zhu, W. -W.

Sommario: “...The existing single-pulse search algorithms for fast radio bursts (FRBs) do not adequately consider...”
Testo

A Framework for Fractional Matrix Programming Problems with Applications in FBL MU-MIMO di Soleymani, Mohammad, Jorswieck, Eduard, Schober, Robert, Hanzo, Lajos

Sommario: “... Dinkelbach-based algorithms. Specifically, the generalized Dinkelbach algorithm can only solve multiple-ratio...”
Testo

CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective di Feng, Yuan, Lv, Junlin, Guo, Haoyu, Cao, Yukun, Zhou, S Kevin, Xie, Xike

Sommario: “... perturbation-constrained selection algorithm that optimizes the worst-case output perturbation to identify...”
Testo

EventSTR: A Benchmark Dataset and Baselines for Event Stream based Scene Text Recognition di Wang, Xiao, Jiang, Jingtao, Li, Dong, Wang, Futian, Zhu, Lin, Wang, Yaowei, Tian, Yongyong, Tang, Jin

Sommario: “...Mainstream Scene Text Recognition (STR) algorithms are developed based on RGB cameras which...”
Testo

An SMT Formalization of Mixed-Precision Matrix Multiplication: Modeling Three Generations of Tensor Cores di Valpey, Benjamin, Li, Xinyi, Pai, Sreepathi, Gopalakrishnan, Ganesh

Sommario: “..., or for algorithm designers to be confident in their code. To address these gaps, prior studies have probed...”
Testo