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

TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate von Zandieh, Amir, Daliri, Majid, Hadian, Majid, Mirrokni, Vahab

Inhaltsangabe: “… Vector quantization, a problem rooted in Shannon's source coding theory, aims to quantize high …”
Volltext

ClassWise-CRF: Category-Specific Fusion for Enhanced Semantic Segmentation of Remote Sensing Imagery von Zhu, Qinfeng, Jiang, Yunxi, Fan, Lei

Inhaltsangabe: “… categories from a pool of candidate networks using a greedy algorithm; second, it integrates the segmentation …”
Volltext

Semantic Intelligence: Integrating GPT-4 with A Planning in Low-Cost Robotics von Barkley, Jesse, George, Abraham, Farimani, Amir Barati

Inhaltsangabe: “… assess GPT-4's ability to act as a path planner compared to the A* algorithm, then present a hybrid …”
Volltext

StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data von Mu, Yuxuan, Ling, Hung Yu, Shi, Yi, Ojeda, Ismael Baira, Xi, Pengcheng, Shu, Chang, Zinno, Fabio, Peng, Xue Bin

Inhaltsangabe: “… can be easily annotated - through manual labeling or heuristic algorithms - and enable training …”
Volltext

UPMAD-Net: A Brain Tumor Segmentation Network with Uncertainty Guidance and Adaptive Multimodal Feature Fusion von Jia, Zhanyuan, Yao, Ni, Sun, Danyang, Han, Chuang, Li, Yanting, Nan, Jiaofen, Zhu, Fubao, Zhao, Chen, Zhou, Weihua

Inhaltsangabe: “… learning with prior knowledge derived from a region-growing algorithm. Methods: The proposed method …”
Volltext

FedRS-Bench: Realistic Federated Learning Datasets and Benchmarks in Remote Sensing von Zhao, Haodong, Peng, Peng, Chen, Chiyu, Huang, Linqing, Liu, Gongshen

Inhaltsangabe: “… implement 10 baseline FL algorithms and evaluation metrics to construct the comprehensive FedRS-Bench …”
Volltext

WavReward: Spoken Dialogue Models With Generalist Reward Evaluators von Ji, Shengpeng, Liang, Tianle, Li, Yangzhuo, Zuo, Jialong, Fang, Minghui, He, Jinzheng, Chen, Yifu, Liu, Zhengqing, Jiang, Ziyue, Cheng, Xize, Zheng, Siqi, Xu, Jin, Lin, Junyang, Zhao, Zhou

Inhaltsangabe: “… -training. By utilizing multi-sample feedback via the reinforcement learning algorithm, we construct a …”
Volltext

Towards Low-Latency Event Stream-based Visual Object Tracking: A Slow-Fast Approach von Wang, Shiao, Wang, Xiao, Jin, Liye, Jiang, Bo, Zhu, Lin, Chen, Lan, Tian, Yonghong, Luo, Bin

Inhaltsangabe: “… Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled …”
Volltext

Let's Verify Math Questions Step by Step von Shen, Chengyu, Wong, Zhen Hao, He, Runming, Liang, Hao, Qiang, Meiyi, Meng, Zimo, Zhao, Zhengyang, Zeng, Bohan, Zhu, Zhengzhou, Cui, Bin, Zhang, Wentao

Inhaltsangabe: “… or design algorithms to construct high-quality math question-answer (QA) data for training. However …”
Volltext

Detecting Flow Gaps in Data Streams von Dong, Siyuan, Tian, Yuxuan, Ma, Wenhan, Yang, Tong, Zhang, Chenye, Wu, Yuhan, Yang, Kaicheng, Wang, Yaojing

Inhaltsangabe: “… of our algorithms. The results reveal that GapFilter-AO requires, on average, 1/32 of the memory to match …”
Volltext

Reinforced Latent Reasoning for LLM-based Recommendation von Zhang, Yang, Xu, Wenxin, Zhao, Xiaoyan, Wang, Wenjie, Feng, Fuli, He, Xiangnan, Chua, Tat-Seng

Inhaltsangabe: “… is based on a modified GRPO algorithm, which reduces computational overhead during training and introduces …”
Volltext

A distillation-teleportation protocol for fault-tolerant QRAM von Dalzell, Alexander M., Gilyén, András, Hann, Connor T., McArdle, Sam, Salton, Grant, Nguyen, Quynh T., Kubica, Aleksander, Brandão, Fernando G. S. L.

Inhaltsangabe: “… algorithm. In fact, the fidelity of the device can be as low as $1/\mathrm{poly}(n)$. The protocol queries …”
Volltext

Rethinking Continual Learning with Progressive Neural Collapse von Wang, Zheng, Yu, Wanhao, Yang, Li, Lin, Sen

Inhaltsangabe: “… next develop a new CL framework by plugging ProNC into commonly used CL algorithm designs, where …”
Volltext

Writing-Zero: Bridge the Gap Between Non-verifiable Tasks and Verifiable Rewards von Jia, Ruipeng, Yang, Yunyi, Gai, Yongbo, Luo, Kai, Huang, Shihao, Lin, Jianhe, Jiang, Xiaoxi, Jiang, Guanjun

Inhaltsangabe: “… , such as mathematics and code generation. However, a significant gap remains for non-verifiable tasks, like creative …”
Volltext

UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection von Fan, Jigang, Wu, Quanlin, Luo, Shengjie, Wang, Liwei

Inhaltsangabe: “… as a discontinuous workflow, employing binary segmentation and subsequent clustering algorithms; (3 …”
Volltext

TracLLM: A Generic Framework for Attributing Long Context LLMs von Wang, Yanting, Zou, Wei, Geng, Runpeng, Jia, Jinyuan

Inhaltsangabe: “… attribution methods. To improve the efficiency, we develop an informed search based algorithm in TracLLM. We …”
Volltext

Classifying Dental Care Providers Through Machine Learning with Features Ranking von Al-Batah, Mohammad Subhi, Alzboon, Mowafaq Salem, Alqaraleh, Muhyeeddin, Abu-Arqoub, Mohammed Hasan, Marie, Rashiq Rafiq

Inhaltsangabe: “… and annotation codes in distinguishing provider types, while demographic variables (AGE_GROUP, CALENDAR_YEAR) had …”
Volltext

LLM-First Search: Self-Guided Exploration of the Solution Space von Herr, Nathan, Rocktäschel, Tim, Raileanu, Roberta

Inhaltsangabe: “… evaluate LFS on Countdown and Sudoku against three classic widely-used search algorithms, Tree-of-Thoughts …”
Volltext

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity von Shojaee, Parshin, Mirzadeh, Iman, Alizadeh, Keivan, Horton, Maxwell, Bengio, Samy, Farajtabar, Mehrdad

Inhaltsangabe: “… insufficiently understood. Current evaluations primarily focus on established math and coding benchmarks …”
Volltext

Learnable Spatial-Temporal Positional Encoding for Link Prediction von Tieu, Katherine, Fu, Dongqi, Li, Zihao, Maciejewski, Ross, He, Jingrui

Inhaltsangabe: “… its temporal link prediction out-performance on 13 classic datasets and with 10 algorithms in both …”
Volltext