5 papers
IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder
Yitong Chen, Zijie Diao, Junke Wang +5
Built on pretrained vision foundation models (VFMs), representation autoencoders (RAEs) have recently emerged as a promising approach for constructing semantically rich latent spac…
All-in-One Conditioning for Text-to-Image Synthesis
Hirunima Jayasekara, Chuong Huynh, Yixuan Ren +2
Accurate interpretation and visual representation of complex prompts involving multiple objects, attributes, and spatial relationships is a critical challenge in text-to-image synt…
Characterizing Motion Encoding in Video Diffusion Timesteps
Vatsal Baherwani, Yixuan Ren, Abhinav Shrivastava
Text-to-video diffusion models synthesize temporal motion and spatial appearance through iterative denoising, yet how motion is encoded across timesteps remains poorly understood.…
NeRV-Diffusion: Diffuse Implicit Neural Representations for Video Synthesis
Yixuan Ren, Hanyu Wang, Hao Chen +2
We present NeRV-Diffusion, an implicit latent video diffusion model that synthesizes videos via generating neural network weights. The generated weights can be rearranged as the pa…
LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior
Hanyu Wang, Saksham Suri, Yixuan Ren +2
We present LARP, a novel video tokenizer designed to overcome limitations in current video tokenization methods for autoregressive (AR) generative models. Unlike traditional patchw…