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

Inductive Synthesis of Inductive Heap Predicates -- Extended Version von Yang, Ziyi, Sergey, Ilya

Inhaltsangabe: “… learning algorithm. The key contributions of our work are (a) the formulation of ILP-based learning only …”
Volltext

LightMamba: Efficient Mamba Acceleration on FPGA with Quantization and Hardware Co-design von Wei, Renjie, Xu, Songqiang, Zhong, Linfeng, Yang, Zebin, Guo, Qingyu, Wang, Yuan, Wang, Runsheng, Li, Meng

Inhaltsangabe: “… . In this paper, we propose LightMamba that co-designs the quantization algorithm and FPGA accelerator …”
Volltext

From Euler to AI: Unifying Formulas for Mathematical Constants von Raz, Tomer, Shalyt, Michael, Leibtag, Elyasheev, Kalisch, Rotem, Weinbaum, Shachar, Hadad, Yaron, Kaminer, Ido

Inhaltsangabe: “… formulas. Our system combines Large Language Models (LLMs) for systematic formula harvesting, an LLM-code …”
Volltext

Discrete Codebook World Models for Continuous Control von Scannell, Aidan, Nakhaei, Mohammadreza, Kujanpää, Kalle, Zhao, Yi, Luck, Kevin Sebastian, Solin, Arno, Pajarinen, Joni

Inhaltsangabe: “… are codes from a codebook. We combine DCWM with decision-time planning to get our model-based RL algorithm …”
Volltext

SparseMamba-PCL: Scribble-Supervised Medical Image Segmentation via SAM-Guided Progressive Collaborative Learning von Qiu, Luyi, Till, Tristan, Guo, Xiaobao, Kong, Adams Wai-Kin

Inhaltsangabe: “… Learning framework that leverages novel algorithms and the Med-SAM foundation model to enhance information …”
Volltext

ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability von Sun, Jianwen, Feng, Yukang, Li, Chuanhao, Zhang, Fanrui, Li, Zizhen, Ai, Jiaxin, Zhou, Sizhuo, Dai, Yu, Zhang, Shenglin, Zhang, Kaipeng

Inhaltsangabe: “… is collected for fine-tuning MLLMs. (3) For the training algorithm, we propose a ``what or how to generate …”
Volltext

Efficient Bayesian Computation Using Plug-and-Play Priors for Poisson Inverse Problems von Klatzer, Teresa, Melidonis, Savvas, Pereyra, Marcelo, Zygalakis, Konstantinos C.

Inhaltsangabe: “… problems involving weakly informative Poisson data. Existing PnP Langevin algorithms are not well-suited …”
Volltext

Exploring a Principled Framework for Deep Subspace Clustering von Meng, Xianghan, Huang, Zhiyuan, He, Wei, Qi, Xianbiao, Xiao, Rong, Li, Chun-Guang

Inhaltsangabe: “… subspace clustering algorithms attempt to jointly learn UoS representations and self-expressive …”
Volltext

An Efficient Reservation Protocol for Medium Access: When Tree Splitting Meets Reinforcement Learning von Chen, Yutao, Chen, Wei

Inhaltsangabe: “… decision process or reinforcement learning (RL). The RL-empowered tree-splitting algorithm guarantees …”
Volltext

WaveNet-Volterra Neural Networks for Active Noise Control: A Fully Causal Approach von Bai, Lu, Li, Mengtong, Lian, Siyuan, Chen, Kai, Lu, Jing

Inhaltsangabe: “… the performance of traditional adaptive filters. While deep learning-based ANC algorithms have emerged to address …”
Volltext

GPU-accelerated Evolutionary Many-objective Optimization Using Tensorized NSGA-III von Li, Hao, Liang, Zhenyu, Cheng, Ran

Inhaltsangabe: “… NSGA-III is one of the most widely adopted algorithms for tackling many-objective optimization …”
Volltext

LoRAX: LoRA eXpandable Networks for Continual Synthetic Image Attribution von Sullivan-Pao, Danielle, Tian, Nicole, Khorrami, Pooya

Inhaltsangabe: “… propose LoRA eXpandable Networks (LoRAX), a parameter-efficient class incremental algorithm that adapts …”
Volltext

Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction von Nagarajan, Vaishnavh, Wu, Chen Henry, Ding, Charles, Raghunathan, Aditi

Inhaltsangabe: “… of the code available under https://github.com/chenwu98/algorithmic-creativity  …”
Volltext

Blending 3D Geometry and Machine Learning for Multi-View Stereopsis von Vats, Vibhas, Reza, Md. Alimoor, Crandall, David, Jung, Soon-heung

Inhaltsangabe: “… consistency constraints. In contrast, modern learning-based algorithms often rely on the plane sweep algorithm …”
Volltext

PIRATES -- a machine-learning framework for polarized, interferometric image reconstruction von Lilley, Lucinda, Norris, Barnaby, Tuthill, Peter, Spalding, Eckhart, Lucas, Miles, Zhang, Manxuan, Millar-Blanchaer, Maxwell, Pinte, Christophe, Bottom, Michael, Guyon, Olivier, Lozi, Julien, Deo, Vincent, Vievard, Sébastien, Wong, Alison P, Ahn, Kyohoon, Ashcraft, Jaren

Inhaltsangabe: “… usually relies on heavy regularization for convergence. Conventional algorithms regularize in the pixel …”
Volltext

Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles von Gupta, Kushagra, Murthy, Surya, Karabag, Mustafa O., Topcu, Ufuk, Fridovich-Keil, David

Inhaltsangabe: “… in the decision space. To this end, we propose a cooperative bargaining algorithm where a mediator has access …”
Volltext

Deep Koopman operator framework for causal discovery in nonlinear dynamical systems von Nathaniel, Juan, Roesch, Carla, Buch, Jatan, DeSantis, Derek, Rupe, Adam, Lamb, Kara, Gentine, Pierre

Inhaltsangabe: “… We use a deep Koopman operator-theoretic formalism to develop a novel causal discovery algorithm …”
Volltext

Stochastic Forward-Forward Learning through Representational Dimensionality Compression von Zhu, Zhichao, Qi, Yang, Ma, Hengyuan, Lu, Wenlian, Feng, Jianfeng

Inhaltsangabe: “… The Forward-Forward (FF) learning algorithm provides a bottom-up alternative to backpropagation (BP …”
Volltext

Scalable and adaptive prediction bands with kernel sum-of-squares von Allain, Louis, da Veiga, Sébastien, Staber, Brian

Inhaltsangabe: “… semidefinite programming algorithms. Second, we introduce a new hyperparameter tuning strategy tailored …”
Volltext

Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings von Tan, Rong-Xi, Chen, Ming, Xue, Ke, Wang, Yao, Wang, Yaoyuan, Fu, Sheng, Qian, Chao

Inhaltsangabe: “… overcome traditional barriers in universal BBO, paving the way for general-purpose BBO algorithms. The code …”
Volltext