4 papers
Heterogeneous Decentralized Diffusion Models
Zhiying Jiang, Raihan Seraj, Marcos Villagra +1
Training frontier-scale diffusion models often requires substantial computational resources concentrated in tightly-coupled clusters, limiting participation to well-resourced insti…
Expert-Data Alignment Governs Generation Quality in Decentralized Diffusion Models
Marcos Villagra, Bidhan Roy, Raihan Seraj +1
Decentralized Diffusion Models (DDMs) route denoising through experts trained independently on disjoint data clusters, which can strongly disagree in their predictions. What govern…
Paris: A Decentralized Trained Open-Weight Diffusion Model
Zhiying Jiang, Raihan Seraj, Marcos Villagra +1
We present Paris, the first publicly released diffusion model pre-trained entirely through decentralized computation. Paris demonstrates that high-quality text-to-image generation…
Contextual bandits with entropy-based human feedback
Raihan Seraj, Lili Meng, Tristan Sylvain
In recent years, preference-based human feedback mechanisms have become essential for enhancing model performance across diverse applications, including conversational AI systems s…