Goto

Collaborating Authors

 apa


Young NYC Marathon runner collapses and dies two miles from finish line

BBC News

A 24-year-old runner in the New York City Marathon collapsed and died just two miles from the finish line, despite being in perfect health, perfect shape, her father has said. Rachel Apa, from Lewisberry, Pennsylvania, was running on Sunday with the Parkinson's Foundation Champions to raise money and honor her grandfather who had the disease, she said in a fundraising page. It was Apa's first marathon, though she was an athlete and had trained for months, father Steve Apa told the New York Times. She died from rhabdomyolysis, a rare condition where muscles break down and poison the bloodstream, which can be brought on by overexertion, her father said. Near mile marker 24, Apa collapsed in Central Park and a bystander performed CPR before race medical staff arrived, race organiser New York Road Runners told the BBC's US partner CBS News.


Stochastic Shortest Path with Sparse Adversarial Costs

Neural Information Processing Systems

We study the adversarial Stochastic Shortest Path (SSP) problem with sparse costs under full-information feedback. In the known transition setting, existing bounds based on Online Mirror Descent (OMD) with negative-entropy regularization scale with?




Multi-agentactiveperceptionwithpredictionrewards

Neural Information Processing Systems

Active perception,collecting observations to reduce uncertainty about ahidden variable, isone of the fundamental capabilities of an intelligent agent [2]. In multi-agent active perceptiona team of autonomous agents cooperatively gathers observations to infer the value of a hidden variable.


Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

Neural Information Processing Systems

Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images. Recent studies have shown that training GANs with limited data remains formidable due to discriminator overfitting, the underlying cause that impedes the generator's convergence. This paper introduces a novel strategy called Adaptive Pseudo Augmentation (APA) to encourage healthy competition between the generator and the discriminator. As an alternative method to existing approaches that rely on standard data augmentations or model regularization, APA alleviates overfitting by employing the generator itself to augment the real data distribution with generated images, which deceives the discriminator adaptively. Extensive experiments demonstrate the effectiveness of APA in improving synthesis quality in the low-data regime. We provide a theoretical analysis to examine the convergence and rationality of our new training strategy. APA is simple and effective. It can be added seamlessly to powerful contemporary GANs, such as StyleGAN2, with negligible computational cost.




VTutor: An Open-Source SDK for Generative AI-Powered Animated Pedagogical Agents with Multi-Media Output

arXiv.org Artificial Intelligence

The rapid evolution of large language models (LLMs) has transformed human-computer interaction (HCI), but the interaction with LLMs is currently mainly focused on text-based interactions, while other multi-model approaches remain under-explored. This paper introduces VTutor, an open-source Software Development Kit (SDK) that combines generative AI with advanced animation technologies to create engaging, adaptable, and realistic APAs for human-AI multi-media interactions. VTutor leverages LLMs for real-time personalized feedback, advanced lip synchronization for natural speech alignment, and WebGL rendering for seamless web integration. Supporting various 2D and 3D character models, VTutor enables researchers and developers to design emotionally resonant, contextually adaptive learning agents. This toolkit enhances learner engagement, feedback receptivity, and human-AI interaction while promoting trustworthy AI principles in education. VTutor sets a new standard for next-generation APAs, offering an accessible, scalable solution for fostering meaningful and immersive human-AI interaction experiences. The VTutor project is open-sourced and welcomes community-driven contributions and showcases.


Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

Neural Information Processing Systems

Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images. Recent studies have shown that training GANs with limited data remains formidable due to discriminator overfitting, the underlying cause that impedes the generator's convergence. This paper introduces a novel strategy called Adaptive Pseudo Augmentation (APA) to encourage healthy competition between the generator and the discriminator. As an alternative method to existing approaches that rely on standard data augmentations or model regularization, APA alleviates overfitting by employing the generator itself to augment the real data distribution with generated images, which deceives the discriminator adaptively. Extensive experiments demonstrate the effectiveness of APA in improving synthesis quality in the low-data regime.