Results 201 to 210 of about 1,601 (294)

Credit‐Driven Adaptive Grouping for Refined Cooperative Multi‐Agent Reinforcement Learning

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Policy heterogeneity is crucial for achieving sophisticated coordination in complex collaborative tasks, which has emerged as one of the key challenges in multi‐agent reinforcement learning (MARL) in recent years. Notably, the grouping paradigm has made remarkable progress in addressing policy heterogeneity.
Yirui Liu   +6 more
wiley   +1 more source

Quantum-like Qualia hypothesis: from quantum cognition to quantum perception. [PDF]

open access: yesFront Psychol
Tsuchiya N   +4 more
europepmc   +1 more source

Diversified Composite Prompting to Enhance Generalisation of Vision‐Language Models

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT In recent years, prompt learning has shown promise in transferring pretrained vision‐language models (VLMs) to downstream tasks. However, existing methods face two challenges in improving generalisation: (1) When leveraging the collaborative effect of multimodal prompts, it is often assumed that text and visual modalities share the same prompt
Xiaoyong Mei   +5 more
wiley   +1 more source

M3LoRA: Flexible Task Adaptation via Multiple Low‐Rank Matrices With Mixture‐of‐Subspaces and Minor Singular Components Initialization

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Parameter‐efficient fine‐tuning (PEFT) has become a crucial paradigm for domain adaptation, achieving strong performance by updating only a small fraction of model parameters. Among various PEFT methods, low‐rank adaptation (LoRA) is widely adopted due to its structural simplicity and computational efficiency.
Xu Luo   +4 more
wiley   +1 more source

Video Super‐Resolution via Effective Spatio‐Temporal Alignment Network

open access: yesCAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Extracting spatio‐temporal cues from neighbouring frames is challenging in video super‐resolution (VSR). Although deformable alignment‐based VSR methods have shown promise in aligning neighbouring frames with the reference frame, most existing methods rely on one or a few traditional convolutions to estimate motion offsets for spatio‐temporal ...
Bin Guo   +7 more
wiley   +1 more source

Classification of Broadband Oscillations Using Wavelet Convolution and Multi‐Channel Attention Network

open access: yesEnergy Internet, EarlyView.
ABSTRACT Accurate identification of broadband oscillation types is a prerequisite for implementing appropriate control strategies. The strongly nonlinear, nonstationary and multi‐modal characteristics of broadband oscillation signals impose higher demands on identification methods. Practical applications face challenges such as coupling effects between
Jinduo Yang   +7 more
wiley   +1 more source

State of health estimation for lithium‐ion batteries using modern heuristic algorithm optimized multiple kernel extreme learning

open access: yesEnergy Conversion and Economics, EarlyView.
Abstract Accurate state of health (SOH) estimation is crucial for the safe operation of lithium‐ion batteries. To address the limited capability of traditional models in characterizing nonlinear degradation, this study proposes a novel data‐driven SOH estimation framework.
Yumin Zhang   +6 more
wiley   +1 more source

Citizens are more willing to co‐produce when participants represent community demographics

open access: yesAustralian Journal of Public Administration, EarlyView.
Abstract Despite co‐production's potential to address democratic deficits, the role of representation in co‐production and its impact on public perceptions remain largely under‐analysed empirically. Employing a vignette survey design, this study tests how representation in co‐production affects citizens’ intentions to get involved.
Wonhyuk Cho   +3 more
wiley   +1 more source

Home - About - Disclaimer - Privacy