1 citations · 1 across the 4 of their papers we have counts for
4 papers
Posterior Augmented Flow Matching
George Stoica, Sayak Paul, Matthew Wallingford +6
Flow matching (FM) trains a time-dependent vector field that transports samples from a simple prior to a complex data distribution. However, for high-dimensional images, each train…
Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding
Christopher Clark, Jieyu Zhang, Zixian Ma +18
Today's strongest video-language models (VLMs) remain proprietary. The strongest open-weight models either rely on synthetic data from proprietary VLMs, effectively distilling from…
Resolving Interference (RI): Disentangling Models for Improved Model Merging
Pratik Ramesh, George Stoica, Arun Iyer +2
Model merging has shown that multitask models can be created by directly combining the parameters of different models that are each specialized on tasks of interest. However, model…
Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation
Yang Fei, George Stoica, Jingyuan Liu +4
Reality is a dance between rigid constraints and deformable structures. For video models, that means generating motion that preserves fidelity as well as structure. Despite progres…