As large language models revolutionize natural language processing, there is an increasing need for robust detection methods to distinguish between AI-generated and human-written text.
The recent growth of large language models has led to an increase in the presence of AI-generated content on platforms. To maintain authenticity and prevent the spread of misinformation, it has become crucial to develop detection methods. DetectGPT and similar works have made progress in identifying machine-generated text using probability analysis. For the final project of CPSC 588 AI Foundation Models at Yale University, our group investigated and aimed to improve the existing model’s performance in detecting AI-generated sentences.
Procedural generation offers a dynamic, efficient alternative to traditional modeling methods, creating diverse and intricate environments.
Procedural generation provides a solution to the challenges of traditional modeling, which can be time-consuming and lacks the variability needed for large-scale projects. This post explores a project developed by Andrew Yi and me for the Advanced Topics in Computer Graphics course at Yale University, where we aimed to create detailed, realistic 3D environments, focusing on urban landscapes and celestial bodies.
As large language models revolutionize natural language processing, there is an increasing need for robust detection methods to distinguish between AI-generated and human-written text.
The recent growth of large language models has led to an increase in the presence of AI-generated content on platforms. To maintain authenticity and prevent the spread of misinformation, it has become crucial to develop detection methods. DetectGPT and similar works have made progress in identifying machine-generated text using probability analysis. For the final project of CPSC 588 AI Foundation Models at Yale University, our group investigated and aimed to improve the existing model’s performance in detecting AI-generated sentences.
Atmospheric scattering is a complex process that occurs when sunlight interacts with particles in a planetary atmosphere, resulting in visually striking phenomena such as the blue sky and colorful sunsets.
Atmospheric scattering is complicated. It involves intricate light interactions with various particles and gases within a planet’s atmosphere, and the light transport equation in a participating medium applied to the atmosphere is very difficult to solve. Therefore, many promises have been made in earlier works to render atmospheric phenomena such as sunsets, sky colors, and aerial perspectives in real-time. Eric Bruneton and Fabrice Neyret’s approach aims to overcome these challenges by employing precomputed atmospheric scattering techniques. The method significantly reduces the computational demands commonly associated with atmospheric rendering using precomputed look-up tables for key components like transmittance, single scattering, multiple scattering, and ground irradiance.
