activity
20222024
most citedPosition Prediction as an Effective Pretraining Strategy

8 citations · 18 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2024

World-consistent Video Diffusion with Explicit 3D Modeling

Qihang Zhang, Shuangfei Zhai, Miguel Angel Bautista +4

Recent advancements in diffusion models have set new benchmarks in image and video generation, enabling realistic visual synthesis across single- and multi-frame contexts. However,…

cs.LG20242 cited

How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks

Etai Littwin, Omid Saremi, Madhu Advani +4

Two competing paradigms exist for self-supervised learning of data representations. Joint Embedding Predictive Architecture (JEPA) is a class of architectures in which semantically…

cs.CV20241 cited

Many-to-many Image Generation with Auto-regressive Diffusion Models

Ying Shen, Yizhe Zhang, Shuangfei Zhai +3

Recent advancements in image generation have made significant progress, yet existing models present limitations in perceiving and generating an arbitrary number of interrelated ima…

cs.CV20246 cited

Scalable Pre-training of Large Autoregressive Image Models

Alaaeldin El-Nouby, Michal Klein, Shuangfei Zhai +5

This paper introduces AIM, a collection of vision models pre-trained with an autoregressive objective. These models are inspired by their textual counterparts, i.e., Large Language…

cs.CV20231 cited

Diffusion Probabilistic Fields

Peiye Zhuang, Samira Abnar, Jiatao Gu +3

Diffusion probabilistic models have quickly become a major approach for generative modeling of images, 3D geometry, video and other domains. However, to adapt diffusion generative…

cs.LG20228 cited

Position Prediction as an Effective Pretraining Strategy

Shuangfei Zhai, Navdeep Jaitly, Jason Ramapuram +7

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of thei…