A new graph-regularized learning framework incorporates psychological interdependencies among emotion classes to improve EEG-based emotion recognition.
Researchers propose a new evaluation standard to address long-term risks and engagement-driven biases in healthcare-focused large language models.
A new framework aims to improve the explainability of temporal graph networks by analyzing how historical events stored in memory modules influence model predictions.
A comprehensive survey evaluates the progress of large language models in medical reasoning by mapping clinical competencies to computational methods.
Researchers propose using a live relational data structure called a Context Graph to enable enterprise AI agents to proactively share information before being asked.
The XFACTORS framework combines contrastive supervision with the information bottleneck principle to achieve stable and scalable disentangled representation learning.
This paper argues that causal abstraction theory provides a valuable framework for explaining how neural networks implement specific computational processes.
A new image enhancement framework called NamedCurves+ utilizes color naming concepts to make deep-learning-based photo editing more interpretable and adjustable for users.
Researchers have introduced MambaLIE, a state space model-based framework designed to enhance low-light images by leveraging scene light intensity.
The paper proposes a robust weighted triangulation method to improve causal effect estimation when dealing with model uncertainty in observational data.
Researchers have introduced MAVEN, a multi-stage agentic pipeline designed to generate high-quality structured video annotations and reasoning traces for training vision-language models.
The proposed ADORN framework utilizes Q-learning to optimize retraining schedules for machine learning models facing performance drift in Open Radio Access Networks.
This paper provides a theoretical spectral analysis of dueling Q-learning to better understand its convergence properties and performance in reinforcement learning.
OmniFood-Bench is a new benchmark designed to assess how well vision-language models can reason about nutritional content and provide personalized dietary advice.
The MetaNCA framework is introduced to improve the adaptability and architectural generalization of neural cellular automata models through localized interactions.
MSRNet is a multi-scale recursive network designed to improve the detection and segmentation of camouflaged objects in challenging visual environments.
The proposed MetaHGNIE framework utilizes hypergraph contrastive learning to better capture high-order interactions and estimate node importance in heterogeneous knowledge graphs.
This study utilizes generative AI to create precise facial emotion stimuli, helping researchers better analyze perceptual differences in autistic individuals.
Researchers from MIT Lincoln Laboratory and the US Air Force found that chatbots can enable non-technical military personnel to build functional software applications.
SwinIFS utilizes landmark guidance and hierarchical attention mechanisms within a Swin Transformer to reconstruct high-quality facial images while preserving identity details.
Huawei has unveiled its LogicFolding architecture for the upcoming Kirin 2026 mobile processor, which reportedly increases transistor density by 55 percent to boost performance without relying on more advanced lithography nodes.
Researchers have developed a method to infer latent thermophysical properties of a scene from time-resolved thermal observations.
Researchers have developed ASMR, an agentic framework designed to automatically generate structured schemas from historical ship maintenance reports.
The paper evaluates an explainable AI-guided adaptive fusion method that combines unimodal and cross-modal experts for multimodal emotion and sentiment recognition.