A new face-swapping pipeline protects pedestrian privacy in autonomous vehicle training datasets while preserving critical behavioral features needed for trajectory prediction.
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.
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.
A new multi-agent framework utilizes cognitive appraisal theory to enable dynamic emotional evolution in persona-based dialogue systems.
The paper proposes a data-efficient method that uses pretrained vision models to help mobile robots avoid dynamic obstacles in unstructured real-world environments.
This paper introduces a language-independent conceptual model that uses symbolic forms and object identity to manage semantic persistence in large language model workflows.
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.
This paper proposes an algorithm and theoretical framework to mitigate object hallucinations in multimodal large language models by addressing attention distraction and visual blur.
The paper proposes a theoretical framework to integrate application-layer cognitive protocols directly into a native meta-architecture for large language models.
The proposed PolyUQuest framework improves web-based retrieval-augmented generation by utilizing heterogeneous graphs to preserve the structural and semantic layout of HTML pages.
SolarChain-Eval is a new physics-constrained benchmark designed to evaluate the performance and trustworthiness of autonomous AI agents in decentralized energy markets.
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.
This paper introduces a method that uses large language models as judges to align metrics for personality recognition without relying on rigid psychological theories.
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.
Researchers developed a method to optimize token generation ordering in masked diffusion models to improve performance in multimodal understanding and image synthesis.
The SHARP framework is proposed to help streaming sequence models learn long-range, non-stationary temporal patterns without needing to revisit past observations.
TOPO-Bench is an open-source framework designed to standardize the evaluation of topological mapping systems and quantify the impact of perceptual aliasing.
Researchers adapted the Joint Embedding Predictive Architecture to analyze compact network security fingerprints for threat detection.
Researchers developed Safe Flow Q-Learning, an offline reinforcement learning method that integrates a reachability-inspired safety value function to maintain strict safety constraints.
As AI inference costs decline rapidly, researchers are exploring how data systems must evolve to support, manage, and be driven by autonomous AI agents.
New Ruipeng Group is participating in the beta testing of Alipay's new AI platform to integrate voice-activated pet healthcare services.
Ruichen Pet Hospital Group has joined Alipay's AI open platform to offer voice-activated pet health and medical services.
Wisson has launched an automated electric vehicle charging robot designed to adaptively service over 130 different car models.