Joshua Susskind

9

Papers

0

Total Citations

Papers (9)

World-consistent Video Diffusion with Explicit 3D Modeling

Multimodal Autoregressive Pre-training of Large Vision Encoders

Scaling Laws for Native Multimodal Models

Learning From Simulated and Unsupervised Images Through Adversarial Training

Adversarial Fisher Vectors for Unsupervised Representation Learning

Collegial Ensembles

GAUDI: A Neural Architect for Immersive 3D Scene Generation

Transformers learn through gradual rank increase

PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model