Eleventh Hour Enthusiast·Aug 23An Energy Correction for Diffusion Language ModelsMasked diffusion predicts tokens independently, and an energy on the full sequence adds back what that misses
Jae H. Park·Mar 17Importance Sampling in Disguise: Inside the Objectives of VAEs and Diffusion ModelsVariational Autoencoders (VAEs) and Denoising Diffusion Probabilistic Models (DDPMs) are often presented as different generative models…
Patrick Nevill·Dec 26, 2024Efficient LLM Validation Using Importance SamplingEvaluating the performance of LLM models can be challenging, especially when dealing with tasks where labeled data is scarce or expensive…
Kibicho Murage·Dec 20, 2024Paper Implementation : Sequential Monte Carlo Methods for Statistical Analysis of TablesImplemented this in C and Julia, lol it took me 2 years to understand the paper — skill issue on my end
Matthew MacFarquhar·Nov 16, 2024Ray Tracing in One Weekend: Part 11 Importance Sampling on LightsIntroduction
