1 citations · 1 across the 1 of their papers we have counts for
3 papers
Exploring Diffusion Transformer Designs via Grafting
Keshigeyan Chandrasegaran, Michael Poli, Daniel Y. Fu +9
Designing model architectures requires decisions such as selecting operators (e.g., attention, convolution) and configurations (e.g., depth, width). However, evaluating the impact…
HourVideo: 1-Hour Video-Language Understanding
Keshigeyan Chandrasegaran, Agrim Gupta, Lea M. Hadzic +7
We present HourVideo, a benchmark dataset for hour-long video-language understanding. Our dataset consists of a novel task suite comprising summarization, perception (recall, track…
Photorealistic Video Generation with Diffusion Models
Agrim Gupta, Lijun Yu, Kihyuk Sohn +6
We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encod…