Résultats de la recherche - coding ((algorithmics OR Algorithmsssics) OR (algorithm OR (algorithm OR algorithm)))

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

Table des matières: “…Vector quantization, a problem rooted in Shannon's source coding theory, aims to quantize high…”
Accéder au texte intégral

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

Table des matières: “… categories from a pool of candidate networks using a greedy algorithm; second, it integrates the segmentation…”
Accéder au texte intégral

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

Table des matières: “… assess GPT-4's ability to act as a path planner compared to the A* algorithm, then present a hybrid…”
Accéder au texte intégral

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

Table des matières: “… can be easily annotated - through manual labeling or heuristic algorithms - and enable training…”
Accéder au texte intégral

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

Table des matières: “… learning with prior knowledge derived from a region-growing algorithm. Methods: The proposed method…”
Accéder au texte intégral

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

Table des matières: “… implement 10 baseline FL algorithms and evaluation metrics to construct the comprehensive FedRS-Bench…”
Accéder au texte intégral

WavReward: Spoken Dialogue Models With Generalist Reward Evaluators par 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

Table des matières: “…-training. By utilizing multi-sample feedback via the reinforcement learning algorithm, we construct a…”
Accéder au texte intégral

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

Table des matières: “…Existing tracking algorithms typically rely on low-frame-rate RGB cameras coupled…”
Accéder au texte intégral

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

Table des matières: “… or design algorithms to construct high-quality math question-answer (QA) data for training. However…”
Accéder au texte intégral

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

Table des matières: “… of our algorithms. The results reveal that GapFilter-AO requires, on average, 1/32 of the memory to match…”
Accéder au texte intégral

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

Table des matières: “… is based on a modified GRPO algorithm, which reduces computational overhead during training and introduces…”
Accéder au texte intégral

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

Table des matières: “… algorithm. In fact, the fidelity of the device can be as low as $1/\mathrm{poly}(n)$. The protocol queries…”
Accéder au texte intégral

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

Table des matières: “… next develop a new CL framework by plugging ProNC into commonly used CL algorithm designs, where…”
Accéder au texte intégral

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

Table des matières: “…, such as mathematics and code generation. However, a significant gap remains for non-verifiable tasks, like creative…”
Accéder au texte intégral

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

Table des matières: “… as a discontinuous workflow, employing binary segmentation and subsequent clustering algorithms; (3…”
Accéder au texte intégral

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

Table des matières: “… attribution methods. To improve the efficiency, we develop an informed search based algorithm in TracLLM. We…”
Accéder au texte intégral

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

Table des matières: “… and annotation codes in distinguishing provider types, while demographic variables (AGE_GROUP, CALENDAR_YEAR) had…”
Accéder au texte intégral

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

Table des matières: “… evaluate LFS on Countdown and Sudoku against three classic widely-used search algorithms, Tree-of-Thoughts…”
Accéder au texte intégral

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

Table des matières: “… insufficiently understood. Current evaluations primarily focus on established math and coding benchmarks…”
Accéder au texte intégral

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

Table des matières: “… its temporal link prediction out-performance on 13 classic datasets and with 10 algorithms in both…”
Accéder au texte intégral