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

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models par Arriola, Marianne, Gokaslan, Aaron, Chiu, Justin T., Yang, Zhihan, Qi, Zhixuan, Han, Jiaqi, Sahoo, Subham Sekhar, Kuleshov, Volodymyr

Table des matières: “… that includes an efficient training algorithm, estimators of gradient variance, and data-driven noise schedules…”
Accéder au texte intégral

RTD-Lite: Scalable Topological Analysis for Comparing Weighted Graphs in Learning Tasks par Tulchinskii, Eduard, Voronkova, Daria, Trofimov, Ilya, Burnaev, Evgeny, Barannikov, Serguei

Table des matières: “… suffer from computational inefficiency on large datasets. We introduce RTD-Lite, a scalable algorithm…”
Accéder au texte intégral

When Astronomy Meets AI: Manazel For Crescent Visibility Prediction in Morocco par Lairgi, Yassir

Table des matières: “…, cultural, and administrative purposes. Manazel (The code and datasets are available at https://github.com…”
Accéder au texte intégral

ZClip: Adaptive Spike Mitigation for LLM Pre-Training par Kumar, Abhay, Owen, Louis, Chowdhury, Nilabhra Roy, Güra, Fabian

Table des matières: “…, an adaptive gradient clipping algorithm that dynamically adjusts the clipping threshold based on statistical…”
Accéder au texte intégral

Unifying Autoregressive and Diffusion-Based Sequence Generation par Fathi, Nima, Scholak, Torsten, Noël, Pierre-André

Table des matières: “… a novel inference algorithm that leverages this new feature in a simplified context inspired from…”
Accéder au texte intégral

On the Temporal Question-Answering Capabilities of Large Language Models Over Anonymized Data par Ruiz, Alfredo Garrachón, de la Rosa, Tomás, Borrajo, Daniel

Table des matières: “… seventeen common temporal reasoning tasks in natural language, focusing on their algorithmic components…”
Accéder au texte intégral

Efficient Formal Verification of Quantum Error Correcting Programs par Huang, Qifan, Zhou, Li, Fang, Wang, Zhao, Mengyu, Ying, Mingsheng

Table des matières: “… by SMT solvers, and for non-Pauli errors, we provide a heuristic algorithm. We formalize the proposed…”
Accéder au texte intégral

Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement par Liu, Chengyuan, Wang, Shihang, Qing, Lizhi, Song, Kaisong, Cao, Junjie, Lin, Jun, Zhang, Ji, Li, Ang, Kuang, Kun, Wu, Fei

Table des matières: “… reasoning tasks such as coding and math, with the help of Monte Carlo Tree Search (MCTS). However, its…”
Accéder au texte intégral

Generation of Musical Timbres using a Text-Guided Diffusion Model par Yuan, Weixuan, Khan, Qadeer, Golkov, Vladimir

Table des matières: “… for subsequently running a phase retrieval algorithm, as related methods do. Audio examples, source code, and a…”
Accéder au texte intégral

Evolution of self-gravitating spherical dark-matter halos with and without new physics par Kamionkowski, Marc, Sigurdson, Kris R.

Table des matières: “…We present an efficient numerical algorithm for evolving self-gravitating systems of dark-matter…”
Accéder au texte intégral

Fine-Tuning Adversarially-Robust Transformers for Single-Image Dehazing par Vasilescu, Vlad, Neacsu, Ana, Faur, Daniela

Table des matières: “… remote sensing scenarios, showcasing their robust behavior for out-of-distribution data. The source code…”
Accéder au texte intégral

WaterDrum: Watermarking for Data-centric Unlearning Metric par Lu, Xinyang, Niu, Xinyuan, Lau, Gregory Kang Ruey, Nhung, Bui Thi Cam, Sim, Rachael Hwee Ling, Himawan, John Russell, Wen, Fanyu, Foo, Chuan-Sheng, Ng, See-Kiong, Low, Bryan Kian Hsiang

Table des matières: “… that can be used to rigorously evaluate unlearning algorithms via WaterDrum. Our code is available at https…”
Accéder au texte intégral

How to Train Your Metamorphic Deep Neural Network par Sommariva, Thomas, Calderara, Simone, Porrello, Angelo

Table des matières: “… of the undelying model, limiting its broader applicability. In this work, we propose a training algorithm…”
Accéder au texte intégral

GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance par Kim, Jinuk, Halabi, Marwa El, Park, Wonpyo, Schaefer, Clemens JS, Lee, Deokjae, Park, Yeonhong, Lee, Jae W., Song, Hyun Oh

Table des matières: “… introduce a novel non-uniform scalar quantization algorithm, which is guaranteed to monotonically decrease…”
Accéder au texte intégral

From RDF Graph Validation to RDF Dataset Validation with SHACL-DS par Dao, Davan Chiem, Debruyne, Christophe

Table des matières: “…, knowledge is hidden in the code, and the constraints are not self-contained nor fully declarative. We…”
Accéder au texte intégral

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO par Xiao, Yicheng, Song, Lin, Chen, Yukang, Luo, Yingmin, Chen, Yuxin, Gan, Yukang, Huang, Wei, Li, Xiu, Qi, Xiaojuan, Shan, Ying

Table des matières: “… Policy Optimization (RGPO) algorithm, utilizing multimodal feedback to effectively guide policy updates…”
Accéder au texte intégral

Variably Scaled Kernels for the regularized solution of the parametric Fourier imaging problem par Volpara, Anna, Lupoli, Alessandro, Perracchione, Emma

Table des matières: “…/ extrapolation algorithms that impose smoothing constraints across contiguous values of the parameter. Previous…”
Accéder au texte intégral

Scaling Offline RL via Efficient and Expressive Shortcut Models par Espinosa-Dice, Nicolas, Zhang, Yiyi, Chen, Yiding, Guo, Bradley, Oertell, Owen, Swamy, Gokul, Brantley, Kiante, Sun, Wen

Table des matières: “… offline RL algorithm that leverages shortcut models - a novel class of generative models - to scale both…”
Accéder au texte intégral

State Space Model Programming in Turing.jl par Hargreaves, Tim, Li, Qing, Knipp, Charles, Wantiez, Frederic, Godsill, Simon J., Ge, Hong

Table des matières: “… various inference algorithms, including Kalman filtering, particle filtering, and combinations thereof…”
Accéder au texte intégral

FSM Modeling For Off-Blockchain Computation par Liu, Christian Gang

Table des matières: “… of concerns and FSM modeling to model a smart contract and generate its code. We then (i) use our algorithm…”
Accéder au texte intégral