Résultats de la recherche - (coding OR decoding) ((Algorithmssicsics OR (algorithm OR algorithm)) OR (algorithm OR algorithm))

Singular Value Decomposition on Kronecker Adaptation for Large Language Model par Chong, Yee Hin, Qu, Peng

Table des matières: “… selection algorithm uses energy-threshold and elbow-point criteria to prune negligible components…”
Accéder au texte intégral

Information-computation trade-offs in non-linear transforms par Ding, Connor, Gorle, Abhiram Rao, Jeong, Jiwon, Sagan, Naomi, Weissman, Tsachy

Table des matières: “… compressors that retain the asymptotic universality guarantees of the LZ78 algorithm. Collectively…”
Accéder au texte intégral

Code Generation for Near-Roofline Finite Element Actions on GPUs from Symbolic Variational Forms par Kulkarni, Kaushik, Klöckner, Andreas

Table des matières: “… meshes. We base our approach on code transformations, wherein we construct a space of scheduling…”
Accéder au texte intégral

Integrating LLMs and Digital Twins for Adaptive Multi-Robot Task Allocation in Construction par Deng, Min, Fu, Bo, Li, Lingyao, Wang, Xi

Table des matières: “… human-in-the-loop flexibility without manual coding. A digital twin-based system has been developed…”
Accéder au texte intégral

Harnessing the Power of Reinforcement Learning for Language-Model-Based Information Retriever via Query-Document Co-Augmentation par Liu, Jingming, Li, Yumeng, Shi, Wei, Ding, Yao-Xiang, Su, Hui, Zhou, Kun

Table des matières: “… specifically designed RL algorithm that enables effective training with these sampled rewards. Experimental…”
Accéder au texte intégral

Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations par Zheng, Brian Siyuan, Liu, Alisa, Ahia, Orevaoghene, Hayase, Jonathan, Choi, Yejin, Smith, Noah A.

Table des matières: “…Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token…”
Accéder au texte intégral

Bayesian Posteriors with Stellar Population Synthesis on GPUs par Zacharegkas, Georgios, Hearin, Andrew, Benson, Andrew

Table des matières: “… Monte Carlo (HMC) algorithms in which individual chains are parallelized across independent GPU threads…”
Accéder au texte intégral

AI Assistants to Enhance and Exploit the PETSc Knowledge Base par Smith, Barry, Zhang, Junchao, Zhang, Hong, McInnes, Lois Curfman, Keceli, Murat, Vasan, Archit, Balay, Satish, Isaac, Toby, Chen, Le, Vishwanath, Venkatram

Table des matières: “… of development, spanning source code, documentation, mailing lists, GitLab issues, Discord conversations…”
Accéder au texte intégral

OTSurv: A Novel Multiple Instance Learning Framework for Survival Prediction with Heterogeneity-aware Optimal Transport par Ren, Qin, Wang, Yifan, Fang, Ruogu, Ling, Haibin, You, Chenyu

Table des matières: “… with an efficient, hardware-friendly matrix scaling algorithm. Empirically, OTSurv sets new state-of-the-art results…”
Accéder au texte intégral

Mamba-FETrack V2: Revisiting State Space Model for Frame-Event based Visual Object Tracking par Wang, Shiao, Huang, Ju, Ma, Qingchuan, Gao, Jinfeng, Xu, Chunyi, Wang, Xiao, Chen, Lan, Jiang, Bo

Table des matières: “… garnered increasing attention in recent years. However, most existing multimodal tracking algorithms depend…”
Accéder au texte intégral

3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation par Lou, Tianrui, Jia, Xiaojun, Liang, Siyuan, Liang, Jiawei, Zhang, Ming, Xiao, Yanjun, Cao, Xiaochun

Table des matières: “… optimization approach that adjusts the imaging background of each viewpoint, helping the algorithm filter out…”
Accéder au texte intégral

MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMs par Mitra, Purbesh, Ulukus, Sennur

Table des matières: “… that employing group relative policy optimization (GRPO) algorithm for reinforcement learning (RL) training…”
Accéder au texte intégral

RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents par Wang, Peisong, Ma, Ruotian, Zhang, Bang, Chen, Xingyu, He, Zhiwei, Luo, Kang, Lv, Qingsong, Jiang, Qingxuan, Xie, Zheng, Wang, Shanyi, Li, Yuan, Ye, Fanghua, Li, Jian, Yang, Yifan, Tu, Zhaopeng, Li, Xiaolong

Table des matières: “…Large language models (LLMs) excel at logical and algorithmic reasoning, yet their emotional…”
Accéder au texte intégral

2.5D Object Detection for Intelligent Roadside Infrastructure par Polley, Nikolai, Boualili, Yacin, Mütsch, Ferdinand, Zipfl, Maximilian, Fleck, Tobias, Zöllner, J. Marius

Table des matières: “…) communication. However, conventional 3D object-detection algorithms struggle to generalize under the domain…”
Accéder au texte intégral

Predicting Air Pollution in Cork, Ireland Using Machine Learning par Rashidunnabi, Md, Ananna, Fahmida Faiza, Hambarde, Kailash, Andrade, Bruno Gabriel Nascimento, Venables, Dean, Proenca, Hugo

Table des matières: “… machine learning algorithms, with Extra Trees emerging as the optimal solution, achieving $77…”
Accéder au texte intégral

Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations par Wang, Yuji, Li, Moran, Hu, Xiaobin, Yi, Ran, Zhang, Jiangning, Feng, Han, Cao, Weijian, Wang, Yabiao, Wang, Chengjie, Ma, Lizhuang

Table des matières: “…, and video quality. By leveraging this simple yet robust mechanism, our algorithm secures the runner-up…”
Accéder au texte intégral

MCFormer: A Multi-Cost-Volume Network and Comprehensive Benchmark for Particle Image Velocimetry par Lin, Zicheng, Li, Xiaoqiang, Wang, Yichao, Zhu, Chuang

Table des matières: “… of various optical flow and PIV algorithms. Complementing this, we propose Multi Cost Volume PIV (MCFormer…”
Accéder au texte intégral

Hybrid Approach to Directed Fuzzing par Parygina, Darya, Mezhuev, Timofey, Kuts, Daniil

Table des matières: “… in predefined code regions. However, it still lacks ability to overcome difficult program constraints…”
Accéder au texte intégral

Graph World Model par Feng, Tao, Wu, Yexin, Lin, Guanyu, You, Jiaxuan

Table des matières: “…. The core of a GWM is a generic message-passing algorithm to aggregate structured information, either over a…”
Accéder au texte intégral

BandFuzz: An ML-powered Collaborative Fuzzing Framework par Shi, Wenxuan, Li, Hongwei, Yu, Jiahao, Sun, Xinqian, Guo, Wenbo, Xing, Xinyu

Table des matières: “… resource allocation algorithm driven by our proposed multi-armed bandits model. Different from greedy…”
Accéder au texte intégral