9 papers
Normalizing Trajectory Models
Jiatao Gu, Tianrong Chen, Ying Shen +3
Diffusion-based models decompose sampling into many small Gaussian denoising steps -- an assumption that breaks down when generation is compressed to a few coarse transitions. Exis…
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
Ying Shen, Tianrong Chen, Yuan Gao +6
Deep generative models have advanced rapidly across text and vision, motivating unified multimodal systems that can understand, reason over, and generate interleaved text-image seq…
Normalizing Flows with Iterative Denoising
Tianrong Chen, Jiatao Gu, David Berthelot +2
Normalizing Flows (NFs) are a classical family of likelihood-based methods that have received revived attention. Recent efforts such as TARFlow have shown that NFs are capable of a…
Grokking of Diffusion Models: Case Study on Modular Addition
Joon Hyeok Kim, Yong-Hyun Park, Mattis Dalsætra Ãstby +1
Despite their empirical success, how diffusion models generalize remains poorly understood from a mechanistic perspective. We demonstrate that diffusion models trained with flow-ma…
The Coupling Within: Flow Matching via Distilled Normalizing Flows
David Berthelot, Tianrong Chen, Jiatao Gu +6
Flow models have rapidly become the go-to method for training and deploying large-scale generators, owing their success to inference-time flexibility via adjustable integration ste…
One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation
Yuan Gao, Chen Chen, Tianrong Chen +1
Visual generative models (e.g., diffusion models) typically operate in compressed latent spaces to balance training efficiency and sample quality. In parallel, there has been growi…