A new industrial dataset covering machinery usage and failures in Nigeria has been released to support quantitative analysis and language model training for African economies.
A new multi-agent framework utilizes cognitive appraisal theory to enable dynamic emotional evolution in persona-based dialogue systems.
The proposed SHIFT framework improves survival prediction from genomic data by handling structural feature missingness across different clinical institutions.
SolarChain-Eval is a new physics-constrained benchmark designed to evaluate the performance and trustworthiness of autonomous AI agents in decentralized energy markets.
The proposed BioModule framework aims to bridge the gap between 3D human pose estimation and the prediction of biomechanical attributes for clinical and sports applications.
This work investigates the key factors in dexterous play pretraining to enable multi-fingered robots to perform precise, contact-rich assembly tasks.
This paper proposes an algorithm and theoretical framework to mitigate object hallucinations in multimodal large language models by addressing attention distraction and visual blur.
A new curvature-aware optimization framework uses minimum description length principles to guide layer-adaptive capacity allocation and pruning in large language models.
GenDA is a generative data assimilation framework that uses graph-based diffusion models to reconstruct high-resolution urban wind fields from sparse sensor data.
CoCo-Fed is a federated learning framework designed to reduce memory usage and communication bandwidth constraints when deploying large neural networks at the wireless edge.
The proposed Token-Domain Multiple Access scheme utilizes pretrained large models to optimize semantic recovery and efficiency in massive token-based communication networks.
The paper proposes a theoretical framework to integrate application-layer cognitive protocols directly into a native meta-architecture for large language models.
A case study demonstrates how ChatGPT was used for rapid prototyping to process event camera data and estimate lunar lander trajectories for an European Space Agency competition.
The authors propose expanding the agentic inequality framework to include interaction-level architectural differences, highlighting how varying context access affects user experiences with AI agents.
A new face-swapping pipeline protects pedestrian privacy in autonomous vehicle training datasets while preserving critical behavioral features needed for trajectory prediction.
Researchers designed a hybrid data synthesis pipeline that combines text-to-image and image-to-image generation to improve instance segmentation for rare object categories.
Hangzhou-based logicalqubit has introduced a quantum cloud platform offering both physical and logical qubit capabilities to transition from hardware sales to cloud services.
Researchers adapted the Joint Embedding Predictive Architecture to analyze compact network security fingerprints for threat detection.
This paper provides a structured analysis of the evaluation methodologies and design paradigms that have driven progress in deep reinforcement learning over the past decade.
This paper introduces a method that uses large language models as judges to align metrics for personality recognition without relying on rigid psychological theories.
TOPO-Bench is an open-source framework designed to standardize the evaluation of topological mapping systems and quantify the impact of perceptual aliasing.
Researchers developed Safe Flow Q-Learning, an offline reinforcement learning method that integrates a reachability-inspired safety value function to maintain strict safety constraints.
The SHARP framework is proposed to help streaming sequence models learn long-range, non-stationary temporal patterns without needing to revisit past observations.
Researchers developed a method to optimize token generation ordering in masked diffusion models to improve performance in multimodal understanding and image synthesis.